Expose a new indexer parameter to enable the creation of a document dictionary

.github/ISSUE_TEMPLATE/sprint_issue.md

@@ -22,20 +22,6 @@ Related product discussion:
 
 <!---If necessary, create a list with technical/product steps-->
 
-### Are you modifying a database?
-- [ ] If not, add the `no db change` label to your PR, and you're good to merge.
-- [ ] If yes, add the `db change` label to your PR. You'll receive a message explaining you what to do.
-
-### Reminders when modifying the API
-
-- [ ] Update the openAPI file with utoipa:
-  - [ ] If a new module has been introduced, create a new structure deriving [the OpenAPI proc-macro](https://docs.rs/utoipa/latest/utoipa/derive.OpenApi.html) and nest it in the main [openAPI structure](https://github.com/meilisearch/meilisearch/blob/f2185438eed60fa32d25b15480c5ee064f6fba4a/crates/meilisearch/src/routes/mod.rs#L64-L78).
-  - [ ] If a new route has been introduced, add the [path decorator](https://docs.rs/utoipa/latest/utoipa/attr.path.html) to it and add the route at the top of the file in its openAPI structure.
-  - [ ] If a structure which is deserialized or serialized in the API has been introduced or modified, it must derive the [`schema`](https://docs.rs/utoipa/latest/utoipa/macro.schema.html) or the [`IntoParams`](https://docs.rs/utoipa/latest/utoipa/derive.IntoParams.html) proc-macro.
-        If it's a **new** structure you must also add it to the big list of structures [in the main `OpenApi` structure](https://github.com/meilisearch/meilisearch/blob/f2185438eed60fa32d25b15480c5ee064f6fba4a/crates/meilisearch/src/routes/mod.rs#L88).
-  - [ ] Once everything is done, start Meilisearch with the swagger flag: `cargo run --features swagger`, open `http://localhost:7700/scalar` on your browser, and ensure everything works as expected.
-  - For more info, refer to [this presentation](https://pitch.com/v/generating-the-openapi-file-jrn3nh).
-
 ### Reminders when modifying the Setting API
 
 <!--- Special steps to remind when adding a new index setting -->

.github/workflows/bench-manual.yml

@@ -1,27 +1,28 @@
 name: Bench (manual)
 
 on:
-  workflow_dispatch:
+    workflow_dispatch:
-    inputs:
+        inputs:
-      workload:
+            workload:
-        description: "The path to the workloads to execute (workloads/...)"
+                description: 'The path to the workloads to execute (workloads/...)'
-        required: true
+                required: true
-        default: "workloads/movies.json"
+                default: 'workloads/movies.json'
 
 env:
-  WORKLOAD_NAME: ${{ github.event.inputs.workload }}
+    WORKLOAD_NAME: ${{ github.event.inputs.workload }}
 
 jobs:
-  benchmarks:
+    benchmarks:
-    name: Run and upload benchmarks
+        name: Run and upload benchmarks
-    runs-on: benchmarks
+        runs-on: benchmarks
-    timeout-minutes: 180 # 3h
+        timeout-minutes: 180 # 3h
-    steps:
+        steps:
-      - uses: actions/checkout@v3
+            - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.85
+            - uses: dtolnay/rust-toolchain@1.81
-        with:
+              with:
-          profile: minimal
+                profile: minimal
+
+            - name: Run benchmarks - workload ${WORKLOAD_NAME} - branch ${{ github.ref }} - commit ${{ github.sha }}
+              run: |
+               cargo xtask bench --api-key "${{ secrets.BENCHMARK_API_KEY }}" --dashboard-url "${{ vars.BENCHMARK_DASHBOARD_URL }}" --reason "Manual [Run #${{ github.run_id }}](https://github.com/meilisearch/meilisearch/actions/runs/${{ github.run_id }})" -- ${WORKLOAD_NAME}
 
-      - name: Run benchmarks - workload ${WORKLOAD_NAME} - branch ${{ github.ref }} - commit ${{ github.sha }}
-        run: |
-          cargo xtask bench --api-key "${{ secrets.BENCHMARK_API_KEY }}" --dashboard-url "${{ vars.BENCHMARK_DASHBOARD_URL }}" --reason "Manual [Run #${{ github.run_id }}](https://github.com/meilisearch/meilisearch/actions/runs/${{ github.run_id }})" -- ${WORKLOAD_NAME}

.github/workflows/bench-pr.yml

@@ -1,82 +1,82 @@
 name: Bench (PR)
 on:
-  issue_comment:
+    issue_comment:
-    types: [created]
+        types: [created]
 
 permissions:
-  issues: write
+    issues: write
 
 env:
-  GH_TOKEN: ${{ secrets.MEILI_BOT_GH_PAT }}
+    GH_TOKEN: ${{ secrets.MEILI_BOT_GH_PAT }}
 
 jobs:
-  run-benchmarks-on-comment:
+    run-benchmarks-on-comment:
-    if: startsWith(github.event.comment.body, '/bench')
+      if: startsWith(github.event.comment.body, '/bench')
-    name: Run and upload benchmarks
+      name: Run and upload benchmarks
-    runs-on: benchmarks
+      runs-on: benchmarks
-    timeout-minutes: 180 # 3h
+      timeout-minutes: 180 # 3h
-    steps:
+      steps:
-      - name: Check permissions
+        - name: Check permissions
-        id: permission
+          id: permission
-        env:
+          env:
-          PR_AUTHOR: ${{github.event.issue.user.login }}
+            PR_AUTHOR: ${{github.event.issue.user.login }}
-          COMMENT_AUTHOR: ${{github.event.comment.user.login }}
+            COMMENT_AUTHOR: ${{github.event.comment.user.login }}
-          REPOSITORY: ${{github.repository}}
+            REPOSITORY: ${{github.repository}}
-          PR_ID: ${{github.event.issue.number}}
+            PR_ID: ${{github.event.issue.number}}
-        run: |
+          run: |
-          PR_REPOSITORY=$(gh api /repos/"$REPOSITORY"/pulls/"$PR_ID" --jq .head.repo.full_name)
+            PR_REPOSITORY=$(gh api /repos/"$REPOSITORY"/pulls/"$PR_ID" --jq .head.repo.full_name)
-          if $(gh api /repos/"$REPOSITORY"/collaborators/"$PR_AUTHOR"/permission --jq .user.permissions.push)
+            if $(gh api /repos/"$REPOSITORY"/collaborators/"$PR_AUTHOR"/permission --jq .user.permissions.push)
-          then
+            then
-            echo "::notice title=Authentication success::PR author authenticated"
+              echo "::notice title=Authentication success::PR author authenticated"
-          else
+            else
-            echo "::error title=Authentication error::PR author doesn't have push permission on this repository"
+              echo "::error title=Authentication error::PR author doesn't have push permission on this repository"
-            exit 1
+              exit 1
-          fi
+            fi
-          if $(gh api /repos/"$REPOSITORY"/collaborators/"$COMMENT_AUTHOR"/permission --jq .user.permissions.push)
+            if $(gh api /repos/"$REPOSITORY"/collaborators/"$COMMENT_AUTHOR"/permission --jq .user.permissions.push)
-          then
+            then
-            echo "::notice title=Authentication success::Comment author authenticated"
+              echo "::notice title=Authentication success::Comment author authenticated"
-          else
+            else
-            echo "::error title=Authentication error::Comment author doesn't have push permission on this repository"
+              echo "::error title=Authentication error::Comment author doesn't have push permission on this repository"
-            exit 1
+              exit 1
-          fi
+            fi
-          if [ "$PR_REPOSITORY" = "$REPOSITORY" ]
+            if [ "$PR_REPOSITORY" = "$REPOSITORY" ]
-          then
+            then
-            echo "::notice title=Authentication success::PR started from main repository"
+              echo "::notice title=Authentication success::PR started from main repository"
-          else
+            else
-            echo "::error title=Authentication error::PR started from a fork"
+              echo "::error title=Authentication error::PR started from a fork"
-            exit 1
+              exit 1
-          fi
+            fi
 
-      - name: Check for Command
+        - name: Check for Command
-        id: command
+          id: command
-        uses: xt0rted/slash-command-action@v2
+          uses: xt0rted/slash-command-action@v2
-        with:
+          with:
-          command: bench
+              command: bench
-          reaction-type: "rocket"
+              reaction-type: "rocket"
-          repo-token: ${{ env.GH_TOKEN }}
+              repo-token: ${{ env.GH_TOKEN }}
 
-      - uses: xt0rted/pull-request-comment-branch@v3
+        - uses: xt0rted/pull-request-comment-branch@v3
-        id: comment-branch
+          id: comment-branch
-        with:
+          with:
-          repo_token: ${{ env.GH_TOKEN }}
+            repo_token: ${{ env.GH_TOKEN }}
 
-      - uses: actions/checkout@v3
+        - uses: actions/checkout@v3
-        if: success()
+          if: success()
-        with:
+          with:
-          fetch-depth: 0 # fetch full history to be able to get main commit sha
+            fetch-depth: 0 # fetch full history to be able to get main commit sha
-          ref: ${{ steps.comment-branch.outputs.head_ref }}
+            ref: ${{ steps.comment-branch.outputs.head_ref }}
 
-      - uses: dtolnay/rust-toolchain@1.85
+        - uses: dtolnay/rust-toolchain@1.81
-        with:
+          with:
-          profile: minimal
+            profile: minimal
 
-      - name: Run benchmarks on PR ${{ github.event.issue.id }}
+        - name: Run benchmarks on PR ${{ github.event.issue.id }}
-        run: |
+          run: |
-          cargo xtask bench --api-key "${{ secrets.BENCHMARK_API_KEY }}" \
+            cargo xtask bench --api-key "${{ secrets.BENCHMARK_API_KEY }}" \
-             --dashboard-url "${{ vars.BENCHMARK_DASHBOARD_URL }}" \
+               --dashboard-url "${{ vars.BENCHMARK_DASHBOARD_URL }}" \
-             --reason "[Comment](${{ github.event.comment.html_url }}) on [#${{ github.event.issue.number }}](${{ github.event.issue.html_url }})" \
+               --reason "[Comment](${{ github.event.comment.html_url }}) on [#${{ github.event.issue.number }}](${{ github.event.issue.html_url }})" \
-             -- ${{ steps.command.outputs.command-arguments }} > benchlinks.txt
+               -- ${{ steps.command.outputs.command-arguments }} > benchlinks.txt
 
-      - name: Send comment in PR
+        - name: Send comment in PR
-        run: |
+          run: |
-          gh pr comment ${{github.event.issue.number}} --body-file benchlinks.txt
+            gh pr comment ${{github.event.issue.number}} --body-file benchlinks.txt

.github/workflows/bench-push-indexing.yml

@@ -1,22 +1,23 @@
 name: Indexing bench (push)
 
 on:
-  push:
+    push:
-    branches:
+        branches:
-      - main
+            - main
 
 jobs:
-  benchmarks:
+    benchmarks:
-    name: Run and upload benchmarks
+        name: Run and upload benchmarks
-    runs-on: benchmarks
+        runs-on: benchmarks
-    timeout-minutes: 180 # 3h
+        timeout-minutes: 180 # 3h
-    steps:
+        steps:
-      - uses: actions/checkout@v3
+          - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.85
+          - uses: dtolnay/rust-toolchain@1.81
-        with:
+            with:
-          profile: minimal
+              profile: minimal
+
+          # Run benchmarks
+          - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch main - Commit ${{ github.sha }}
+            run: |
+              cargo xtask bench --api-key "${{ secrets.BENCHMARK_API_KEY }}" --dashboard-url "${{ vars.BENCHMARK_DASHBOARD_URL }}" --reason "Push on `main` [Run #${{ github.run_id }}](https://github.com/meilisearch/meilisearch/actions/runs/${{ github.run_id }})" -- workloads/*.json
 
-      # Run benchmarks
-      - name: Run benchmarks - Dataset ${BENCH_NAME} - Branch main - Commit ${{ github.sha }}
-        run: |
-          cargo xtask bench --api-key "${{ secrets.BENCHMARK_API_KEY }}" --dashboard-url "${{ vars.BENCHMARK_DASHBOARD_URL }}" --reason "Push on `main` [Run #${{ github.run_id }}](https://github.com/meilisearch/meilisearch/actions/runs/${{ github.run_id }})" -- workloads/*.json

.github/workflows/benchmarks-manual.yml

@@ -4,9 +4,9 @@ on:
   workflow_dispatch:
     inputs:
       dataset_name:
-        description: "The name of the dataset used to benchmark (search_songs, search_wiki, search_geo or indexing)"
+        description: 'The name of the dataset used to benchmark (search_songs, search_wiki, search_geo or indexing)'
         required: false
-        default: "search_songs"
+        default: 'search_songs'
 
 env:
   BENCH_NAME: ${{ github.event.inputs.dataset_name }}
@@ -18,7 +18,7 @@ jobs:
     timeout-minutes: 4320 # 72h
     steps:
       - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.85
+      - uses: dtolnay/rust-toolchain@1.81
         with:
           profile: minimal
 
@@ -67,7 +67,7 @@ jobs:
           out_dir: critcmp_results
 
       # Helper
-      - name: "README: compare with another benchmark"
+      - name: 'README: compare with another benchmark'
         run: |
           echo "${{ steps.file.outputs.basename }}.json has just been pushed."
           echo 'How to compare this benchmark with another one?'

.github/workflows/benchmarks-pr.yml

@@ -44,7 +44,7 @@ jobs:
             exit 1
           fi
 
-      - uses: dtolnay/rust-toolchain@1.85
+      - uses: dtolnay/rust-toolchain@1.81
         with:
           profile: minimal
 

.github/workflows/benchmarks-push-indexing.yml

@@ -16,7 +16,7 @@ jobs:
     timeout-minutes: 4320 # 72h
     steps:
       - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.85
+      - uses: dtolnay/rust-toolchain@1.81
         with:
           profile: minimal
 
@@ -69,7 +69,7 @@ jobs:
         run: telegraf --config https://eu-central-1-1.aws.cloud2.influxdata.com/api/v2/telegrafs/08b52e34a370b000 --once --debug
 
       # Helper
-      - name: "README: compare with another benchmark"
+      - name: 'README: compare with another benchmark'
         run: |
           echo "${{ steps.file.outputs.basename }}.json has just been pushed."
           echo 'How to compare this benchmark with another one?'

.github/workflows/benchmarks-push-search-geo.yml

@@ -15,7 +15,7 @@ jobs:
     runs-on: benchmarks
     steps:
       - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.85
+      - uses: dtolnay/rust-toolchain@1.81
         with:
           profile: minimal
 
@@ -68,7 +68,7 @@ jobs:
         run: telegraf --config https://eu-central-1-1.aws.cloud2.influxdata.com/api/v2/telegrafs/08b52e34a370b000 --once --debug
 
       # Helper
-      - name: "README: compare with another benchmark"
+      - name: 'README: compare with another benchmark'
         run: |
           echo "${{ steps.file.outputs.basename }}.json has just been pushed."
           echo 'How to compare this benchmark with another one?'

.github/workflows/benchmarks-push-search-songs.yml

@@ -15,7 +15,7 @@ jobs:
     runs-on: benchmarks
     steps:
       - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.85
+      - uses: dtolnay/rust-toolchain@1.81
         with:
           profile: minimal
 
@@ -68,7 +68,7 @@ jobs:
         run: telegraf --config https://eu-central-1-1.aws.cloud2.influxdata.com/api/v2/telegrafs/08b52e34a370b000 --once --debug
 
       # Helper
-      - name: "README: compare with another benchmark"
+      - name: 'README: compare with another benchmark'
         run: |
           echo "${{ steps.file.outputs.basename }}.json has just been pushed."
           echo 'How to compare this benchmark with another one?'

.github/workflows/benchmarks-push-search-wiki.yml

@@ -15,7 +15,7 @@ jobs:
     runs-on: benchmarks
     steps:
       - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.85
+      - uses: dtolnay/rust-toolchain@1.81
         with:
           profile: minimal
 
@@ -68,7 +68,7 @@ jobs:
         run: telegraf --config https://eu-central-1-1.aws.cloud2.influxdata.com/api/v2/telegrafs/08b52e34a370b000 --once --debug
 
       # Helper
-      - name: "README: compare with another benchmark"
+      - name: 'README: compare with another benchmark'
         run: |
           echo "${{ steps.file.outputs.basename }}.json has just been pushed."
           echo 'How to compare this benchmark with another one?'

.github/workflows/check-valid-milestone.yml

@@ -1,100 +0,0 @@
-name: PR Milestone Check
-
-on:
-  pull_request:
-    types: [opened, reopened, edited, synchronize, milestoned, demilestoned]
-    branches:
-      - "main"
-      - "release-v*.*.*"
-
-jobs:
-  check-milestone:
-    name: Check PR Milestone
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v3
-
-      - name: Validate PR milestone
-        uses: actions/github-script@v7
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          script: |
-            // Get PR number directly from the event payload
-            const prNumber = context.payload.pull_request.number;
-
-            // Get PR details
-            const { data: prData } = await github.rest.pulls.get({
-              owner: 'meilisearch',
-              repo: 'meilisearch',
-              pull_number: prNumber
-            });
-
-            // Get base branch name
-            const baseBranch = prData.base.ref;
-            console.log(`Base branch: ${baseBranch}`);
-
-            // Get PR milestone
-            const prMilestone = prData.milestone;
-            if (!prMilestone) {
-              core.setFailed('PR must have a milestone assigned');
-              return;
-            }
-            console.log(`PR milestone: ${prMilestone.title}`);
-
-            // Validate milestone format: vx.y.z
-            const milestoneRegex = /^v\d+\.\d+\.\d+$/;
-            if (!milestoneRegex.test(prMilestone.title)) {
-              core.setFailed(`Milestone "${prMilestone.title}" does not follow the required format vx.y.z`);
-              return;
-            }
-
-            // For main branch PRs, check if the milestone is the highest one
-            if (baseBranch === 'main') {
-              // Get all milestones
-              const { data: milestones } = await github.rest.issues.listMilestones({
-                owner: 'meilisearch',
-                repo: 'meilisearch',
-                state: 'open',
-                sort: 'due_on',
-                direction: 'desc'
-              });
-
-              // Sort milestones by version number (vx.y.z)
-              const sortedMilestones = milestones
-                .filter(m => milestoneRegex.test(m.title))
-                .sort((a, b) => {
-                  const versionA = a.title.substring(1).split('.').map(Number);
-                  const versionB = b.title.substring(1).split('.').map(Number);
-
-                  // Compare major version
-                  if (versionA[0] !== versionB[0]) return versionB[0] - versionA[0];
-                  // Compare minor version
-                  if (versionA[1] !== versionB[1]) return versionB[1] - versionA[1];
-                  // Compare patch version
-                  return versionB[2] - versionA[2];
-                });
-
-              if (sortedMilestones.length === 0) {
-                core.setFailed('No valid milestones found in the repository. Please create at least one milestone with the format vx.y.z');
-                return;
-              }
-
-              const highestMilestone = sortedMilestones[0];
-              console.log(`Highest milestone: ${highestMilestone.title}`);
-
-              if (prMilestone.title !== highestMilestone.title) {
-                core.setFailed(`PRs targeting the main branch must use the highest milestone (${highestMilestone.title}), but this PR uses ${prMilestone.title}`);
-                return;
-              }
-            } else {
-              // For release branches, the milestone should match the branch version
-              const branchVersion = baseBranch.substring(8); // remove 'release-'
-              if (prMilestone.title !== branchVersion) {
-                core.setFailed(`PRs targeting release branch "${baseBranch}" must use the matching milestone "${branchVersion}", but this PR uses "${prMilestone.title}"`);
-                return;
-              }
-            }
-
-            console.log('PR milestone validation passed!');

.github/workflows/db-change-comments.yml

@@ -1,57 +0,0 @@
-name: Comment when db change labels are added
-
-on:
-  pull_request:
-    types: [labeled]
-
-env:
-  MESSAGE: |
-    ### Hello, I'm a bot 🤖 
-
-    You are receiving this message because you declared that this PR make changes to the Meilisearch database.
-    Depending on the nature of the change, additional actions might be required on your part. The following sections detail the additional actions depending on the nature of the change, please copy the relevant section in the description of your PR, and make sure to perform the required actions.
-
-    Thank you for contributing to Meilisearch :heart:
-
-    ## This PR makes forward-compatible changes
-
-    *Forward-compatible changes are changes to the database such that databases created in an older version of Meilisearch are still valid in the new version of Meilisearch. They usually represent additive changes, like adding a new optional attribute or setting.*
-
-    - [ ] Detail the change to the DB format and why they are forward compatible
-    - [ ] Forward-compatibility: A database created before this PR and using the features touched by this PR was able to be opened by a Meilisearch produced by the code of this PR.
-
-
-    ## This PR makes breaking changes
-
-    *Breaking changes are changes to the database such that databases created in an older version of Meilisearch need changes to remain valid in the new version of Meilisearch. This typically happens when the way to store the data changed (change of database, new required key, etc). This can also happen due to breaking changes in the API of an experimental feature. ⚠️ This kind of changes are more difficult to achieve safely, so proceed with caution and test dumpless upgrade right before merging the PR.*
-
-    - [ ] Detail the changes to the DB format,
-        - [ ] which are compatible, and why
-        - [ ] which are not compatible, why, and how they will be fixed up in the upgrade
-     - [ ] /!\ Ensure all the read operations still work!
-        - If the change happened in milli, you may need to check the version of the database before doing any read operation
-        - If the change happened in the index-scheduler, make sure the new code can immediately read the old database
-        - If the change happened in the meilisearch-auth database, reach out to the team; we don't know yet how to handle these changes
-      - [ ] Write the code to go from the old database to the new one
-        - If the change happened in milli, the upgrade function should be written and called [here](https://github.com/meilisearch/meilisearch/blob/3fd86e8d76d7d468b0095d679adb09211ca3b6c0/crates/milli/src/update/upgrade/mod.rs#L24-L47)
-        - If the change happened in the index-scheduler, we've never done it yet, but the right place to do it should be [here](https://github.com/meilisearch/meilisearch/blob/3fd86e8d76d7d468b0095d679adb09211ca3b6c0/crates/index-scheduler/src/scheduler/process_upgrade/mod.rs#L13)
-      - [ ] Write an integration test [here](https://github.com/meilisearch/meilisearch/blob/main/crates/meilisearch/tests/upgrade/mod.rs) ensuring you can read the old database, upgrade to the new database, and read the new database as expected
-    
-
-jobs:
-  add-comment:
-    runs-on: ubuntu-latest
-    if: github.event.label.name == 'db change'
-    steps:
-      - name: Add comment
-        uses: actions/github-script@v7
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-          script: |
-            const message = process.env.MESSAGE;
-            github.rest.issues.createComment({
-              issue_number: context.issue.number,
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              body: message
-            })

.github/workflows/db-change-missing.yml

@@ -1,28 +0,0 @@
-name: Check db change labels
-
-on:
-  pull_request:
-    types: [opened, synchronize, reopened, labeled, unlabeled]
-
-jobs:
-  check-labels:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-      - name: Check db change labels
-        id: check_labels
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          URL=/repos/meilisearch/meilisearch/pulls/${{ github.event.pull_request.number }}/labels
-          echo ${{ github.event.pull_request.number }}
-          echo $URL
-          LABELS=$(gh api -H "Accept: application/vnd.github+json" -H "X-GitHub-Api-Version: 2022-11-28" /repos/${{ github.repository }}/issues/${{ github.event.pull_request.number }}/labels -q .[].name)
-          echo "Labels: $LABELS"
-          if [[ ! "$LABELS" =~ "db change" && ! "$LABELS" =~ "no db change" ]]; then
-            echo "::error::Pull request must contain either the 'db change' or 'no db change' label."
-            exit 1
-          else
-            echo "The label is set"
-          fi

.github/workflows/flaky-tests.yml

@@ -9,22 +9,22 @@ jobs:
   flaky:
     runs-on: ubuntu-latest
     container:
-      # Use ubuntu-22.04 to compile with glibc 2.35
+      # Use ubuntu-20.04 to compile with glibc 2.28
-      image: ubuntu:22.04
+      image: ubuntu:20.04
     steps:
-      - uses: actions/checkout@v3
+    - uses: actions/checkout@v3
-      - name: Install needed dependencies
+    - name: Install needed dependencies
-        run: |
+      run: |
-          apt-get update && apt-get install -y curl
+        apt-get update && apt-get install -y curl
-          apt-get install build-essential -y
+        apt-get install build-essential -y
-      - uses: dtolnay/rust-toolchain@1.85
+    - uses: dtolnay/rust-toolchain@1.81
-      - name: Install cargo-flaky
+    - name: Install cargo-flaky
-        run: cargo install cargo-flaky
+      run: cargo install cargo-flaky
-      - name: Run cargo flaky in the dumps
+    - name: Run cargo flaky in the dumps
-        run: cd crates/dump; cargo flaky -i 100 --release
+      run: cd crates/dump; cargo flaky -i 100 --release
-      - name: Run cargo flaky in the index-scheduler
+    - name: Run cargo flaky in the index-scheduler
-        run: cd crates/index-scheduler; cargo flaky -i 100 --release
+      run: cd crates/index-scheduler; cargo flaky -i 100 --release
-      - name: Run cargo flaky in the auth
+    - name: Run cargo flaky in the auth
-        run: cd crates/meilisearch-auth; cargo flaky -i 100 --release
+      run: cd crates/meilisearch-auth; cargo flaky -i 100 --release
-      - name: Run cargo flaky in meilisearch
+    - name: Run cargo flaky in meilisearch
-        run: cd crates/meilisearch; cargo flaky -i 100 --release
+      run: cd crates/meilisearch; cargo flaky -i 100 --release

.github/workflows/fuzzer-indexing.yml

@@ -12,7 +12,7 @@ jobs:
     timeout-minutes: 4320 # 72h
     steps:
       - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.85
+      - uses: dtolnay/rust-toolchain@1.81
         with:
           profile: minimal
 

.github/workflows/milestone-workflow.yml

@@ -5,7 +5,6 @@ name: Milestone's workflow
 # For each Milestone created (not opened!), and if the release is NOT a patch release (only the patch changed)
 # - the roadmap issue is created, see https://github.com/meilisearch/engine-team/blob/main/issue-templates/roadmap-issue.md
 # - the changelog issue is created, see https://github.com/meilisearch/engine-team/blob/main/issue-templates/changelog-issue.md
-# - update the ruleset to add the current release version to the list of allowed versions and be able to use the merge queue.
 
 # For each Milestone closed
 # - the `release_version` label is created
@@ -22,9 +21,10 @@ env:
   GH_TOKEN: ${{ secrets.MEILI_BOT_GH_PAT }}
 
 jobs:
-  # -----------------
+
-  # MILESTONE CREATED
+# -----------------
-  # -----------------
+# MILESTONE CREATED
+# -----------------
 
   get-release-version:
     if: github.event.action == 'created'
@@ -148,41 +148,9 @@ jobs:
             --body-file $ISSUE_TEMPLATE \
             --milestone $MILESTONE_VERSION
 
-  update-ruleset:
+# ----------------
-    runs-on: ubuntu-latest
+# MILESTONE CLOSED
-    if: github.event.action == 'created'
+# ----------------
-    steps:
-      - uses: actions/checkout@v3
-      - name: Install jq
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y jq
-      - name: Update ruleset
-        env:
-          # gh api repos/meilisearch/meilisearch/rulesets --jq '.[] | {name: .name, id: .id}'
-          RULESET_ID: 4253297
-          BRANCH_NAME: ${{ github.event.inputs.branch_name }}
-        run: |
-          echo "RULESET_ID: ${{ env.RULESET_ID }}"
-          echo "BRANCH_NAME: ${{ env.BRANCH_NAME }}"
-
-          # Get current ruleset conditions
-          CONDITIONS=$(gh api repos/meilisearch/meilisearch/rulesets/${{ env.RULESET_ID }} --jq '{ conditions: .conditions }')
-
-          # Update the conditions by appending the milestone version
-          UPDATED_CONDITIONS=$(echo $CONDITIONS | jq '.conditions.ref_name.include += ["refs/heads/release-'${{ env.MILESTONE_VERSION }}'"]')
-
-          # Update the ruleset from stdin (-)
-          echo $UPDATED_CONDITIONS |
-            gh api repos/meilisearch/meilisearch/rulesets/${{ env.RULESET_ID }} \
-              --method PUT \
-              -H "Accept: application/vnd.github+json" \
-              -H "X-GitHub-Api-Version: 2022-11-28" \
-              --input -
-
-  # ----------------
-  # MILESTONE CLOSED
-  # ----------------
 
   create-release-label:
     if: github.event.action == 'closed'

.github/workflows/publish-apt-brew-pkg.yml

@@ -18,28 +18,28 @@ jobs:
     runs-on: ubuntu-latest
     needs: check-version
     container:
-      # Use ubuntu-22.04 to compile with glibc 2.35
+      # Use ubuntu-20.04 to compile with glibc 2.28
-      image: ubuntu:22.04
+      image: ubuntu:20.04
     steps:
-      - name: Install needed dependencies
+    - name: Install needed dependencies
-        run: |
+      run: |
-          apt-get update && apt-get install -y curl
+        apt-get update && apt-get install -y curl
-          apt-get install build-essential -y
+        apt-get install build-essential -y
-      - uses: dtolnay/rust-toolchain@1.85
+    - uses: dtolnay/rust-toolchain@1.81
-      - name: Install cargo-deb
+    - name: Install cargo-deb
-        run: cargo install cargo-deb
+      run: cargo install cargo-deb
-      - uses: actions/checkout@v3
+    - uses: actions/checkout@v3
-      - name: Build deb package
+    - name: Build deb package
-        run: cargo deb -p meilisearch -o target/debian/meilisearch.deb
+      run: cargo deb -p meilisearch -o target/debian/meilisearch.deb
-      - name: Upload debian pkg to release
+    - name: Upload debian pkg to release
-        uses: svenstaro/upload-release-action@2.11.1
+      uses: svenstaro/upload-release-action@2.7.0
-        with:
+      with:
-          repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
+        repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
-          file: target/debian/meilisearch.deb
+        file: target/debian/meilisearch.deb
-          asset_name: meilisearch.deb
+        asset_name: meilisearch.deb
-          tag: ${{ github.ref }}
+        tag: ${{ github.ref }}
-      - name: Upload debian pkg to apt repository
+    - name: Upload debian pkg to apt repository
-        run: curl -F package=@target/debian/meilisearch.deb https://${{ secrets.GEMFURY_PUSH_TOKEN }}@push.fury.io/meilisearch/
+      run: curl -F package=@target/debian/meilisearch.deb https://${{ secrets.GEMFURY_PUSH_TOKEN }}@push.fury.io/meilisearch/
 
   homebrew:
     name: Bump Homebrew formula

.github/workflows/publish-binaries.yml

@@ -3,7 +3,7 @@ name: Publish binaries to GitHub release
 on:
   workflow_dispatch:
   schedule:
-    - cron: "0 2 * * *" # Every day at 2:00am
+    - cron: '0 2 * * *' # Every day at 2:00am
   release:
     types: [published]
 
@@ -37,26 +37,26 @@ jobs:
     runs-on: ubuntu-latest
     needs: check-version
     container:
-      # Use ubuntu-22.04 to compile with glibc 2.35
+      # Use ubuntu-20.04 to compile with glibc 2.28
-      image: ubuntu:22.04
+      image: ubuntu:20.04
     steps:
-      - uses: actions/checkout@v3
+    - uses: actions/checkout@v3
-      - name: Install needed dependencies
+    - name: Install needed dependencies
-        run: |
+      run: |
-          apt-get update && apt-get install -y curl
+        apt-get update && apt-get install -y curl
-          apt-get install build-essential -y
+        apt-get install build-essential -y
-      - uses: dtolnay/rust-toolchain@1.85
+    - uses: dtolnay/rust-toolchain@1.81
-      - name: Build
+    - name: Build
-        run: cargo build --release --locked
+      run: cargo build --release --locked
-      # No need to upload binaries for dry run (cron)
+    # No need to upload binaries for dry run (cron)
-      - name: Upload binaries to release
+    - name: Upload binaries to release
-        if: github.event_name == 'release'
+      if: github.event_name == 'release'
-        uses: svenstaro/upload-release-action@2.11.1
+      uses: svenstaro/upload-release-action@2.7.0
-        with:
+      with:
-          repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
+        repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
-          file: target/release/meilisearch
+        file: target/release/meilisearch
-          asset_name: meilisearch-linux-amd64
+        asset_name: meilisearch-linux-amd64
-          tag: ${{ github.ref }}
+        tag: ${{ github.ref }}
 
   publish-macos-windows:
     name: Publish binary for ${{ matrix.os }}
@@ -74,19 +74,19 @@ jobs:
             artifact_name: meilisearch.exe
             asset_name: meilisearch-windows-amd64.exe
     steps:
-      - uses: actions/checkout@v3
+    - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.85
+    - uses: dtolnay/rust-toolchain@1.81
-      - name: Build
+    - name: Build
-        run: cargo build --release --locked
+      run: cargo build --release --locked
-      # No need to upload binaries for dry run (cron)
+    # No need to upload binaries for dry run (cron)
-      - name: Upload binaries to release
+    - name: Upload binaries to release
-        if: github.event_name == 'release'
+      if: github.event_name == 'release'
-        uses: svenstaro/upload-release-action@2.11.1
+      uses: svenstaro/upload-release-action@2.7.0
-        with:
+      with:
-          repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
+        repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
-          file: target/release/${{ matrix.artifact_name }}
+        file: target/release/${{ matrix.artifact_name }}
-          asset_name: ${{ matrix.asset_name }}
+        asset_name: ${{ matrix.asset_name }}
-          tag: ${{ github.ref }}
+        tag: ${{ github.ref }}
 
   publish-macos-apple-silicon:
     name: Publish binary for macOS silicon
@@ -101,7 +101,7 @@ jobs:
       - name: Checkout repository
         uses: actions/checkout@v3
       - name: Installing Rust toolchain
-        uses: dtolnay/rust-toolchain@1.85
+        uses: dtolnay/rust-toolchain@1.81
         with:
           profile: minimal
           target: ${{ matrix.target }}
@@ -113,7 +113,7 @@ jobs:
       - name: Upload the binary to release
         # No need to upload binaries for dry run (cron)
         if: github.event_name == 'release'
-        uses: svenstaro/upload-release-action@2.11.1
+        uses: svenstaro/upload-release-action@2.7.0
         with:
           repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
           file: target/${{ matrix.target }}/release/meilisearch
@@ -127,8 +127,8 @@ jobs:
     env:
       DEBIAN_FRONTEND: noninteractive
     container:
-      # Use ubuntu-22.04 to compile with glibc 2.35
+      # Use ubuntu-20.04 to compile with glibc 2.28
-      image: ubuntu:22.04
+      image: ubuntu:20.04
     strategy:
       matrix:
         include:
@@ -148,7 +148,7 @@ jobs:
           add-apt-repository "deb [arch=$(dpkg --print-architecture)] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable"
           apt-get update -y && apt-get install -y docker-ce
       - name: Installing Rust toolchain
-        uses: dtolnay/rust-toolchain@1.85
+        uses: dtolnay/rust-toolchain@1.81
         with:
           profile: minimal
           target: ${{ matrix.target }}
@@ -178,7 +178,7 @@ jobs:
       - name: Upload the binary to release
         # No need to upload binaries for dry run (cron)
         if: github.event_name == 'release'
-        uses: svenstaro/upload-release-action@2.11.1
+        uses: svenstaro/upload-release-action@2.7.0
         with:
           repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
           file: target/${{ matrix.target }}/release/meilisearch

.github/workflows/publish-docker-images.yml

@@ -104,22 +104,3 @@ jobs:
           repository: meilisearch/meilisearch-cloud
           event-type: cloud-docker-build
           client-payload: '{ "meilisearch_version": "${{ github.ref_name }}", "stable": "${{ steps.check-tag-format.outputs.stable }}" }'
-
-      # Send notification to Swarmia to notify of a deployment: https://app.swarmia.com
-      # - name: 'Setup jq'
-      #   uses: dcarbone/install-jq-action
-      # - name: Send deployment to Swarmia
-      #   if: github.event_name == 'push' && success()
-      #   run: |
-      #     JSON_STRING=$( jq --null-input --compact-output \
-      #     --arg version "${{ github.ref_name }}" \
-      #     --arg appName "meilisearch" \
-      #     --arg environment "production" \
-      #     --arg commitSha "${{ github.sha }}" \
-      #     --arg repositoryFullName "${{ github.repository }}" \
-      #     '{"version": $version, "appName": $appName, "environment": $environment, "commitSha": $commitSha, "repositoryFullName": $repositoryFullName}' )
-
-      #     curl -H "Authorization: ${{ secrets.SWARMIA_DEPLOYMENTS_AUTHORIZATION }}" \
-      #       -H "Content-Type: application/json" \
-      #       -d "$JSON_STRING" \
-      #       https://hook.swarmia.com/deployments

.github/workflows/sdks-tests.yml

@@ -22,7 +22,7 @@ jobs:
     outputs:
       docker-image: ${{ steps.define-image.outputs.docker-image }}
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - name: Define the Docker image we need to use
         id: define-image
         run: |
@@ -46,13 +46,13 @@ jobs:
       MEILISEARCH_VERSION: ${{ needs.define-docker-image.outputs.docker-image }}
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-dotnet
       - name: Setup .NET Core
         uses: actions/setup-dotnet@v4
         with:
-          dotnet-version: "8.0.x"
+          dotnet-version: "6.0.x"
       - name: Install dependencies
         run: dotnet restore
       - name: Build
@@ -75,7 +75,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-dart
       - uses: dart-lang/setup-dart@v1
@@ -103,7 +103,7 @@ jobs:
         uses: actions/setup-go@v5
         with:
           go-version: stable
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-go
       - name: Get dependencies
@@ -129,7 +129,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-java
       - name: Set up Java
@@ -156,7 +156,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-js
       - name: Setup node
@@ -191,7 +191,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-php
       - name: Install PHP
@@ -220,7 +220,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-python
       - name: Set up Python
@@ -245,7 +245,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-ruby
       - name: Set up Ruby 3
@@ -270,7 +270,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-rust
       - name: Build
@@ -291,7 +291,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-swift
       - name: Run tests
@@ -314,7 +314,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-js-plugins
       - name: Setup node
@@ -345,7 +345,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-rails
       - name: Set up Ruby 3
@@ -369,7 +369,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           repository: meilisearch/meilisearch-symfony
       - name: Install PHP

.github/workflows/test-suite.yml

@@ -4,9 +4,13 @@ on:
   workflow_dispatch:
   schedule:
     # Everyday at 5:00am
-    - cron: "0 5 * * *"
+    - cron: '0 5 * * *'
   pull_request:
-  merge_group:
+  push:
+    # trying and staging branches are for Bors config
+    branches:
+      - trying
+      - staging
 
 env:
   CARGO_TERM_COLOR: always
@@ -15,11 +19,11 @@ env:
 
 jobs:
   test-linux:
-    name: Tests on ubuntu-22.04
+    name: Tests on ubuntu-20.04
     runs-on: ubuntu-latest
     container:
-      # Use ubuntu-22.04 to compile with glibc 2.35
+      # Use ubuntu-20.04 to compile with glibc 2.28
-      image: ubuntu:22.04
+      image: ubuntu:20.04
     steps:
       - uses: actions/checkout@v3
       - name: Install needed dependencies
@@ -27,9 +31,9 @@ jobs:
           apt-get update && apt-get install -y curl
           apt-get install build-essential -y
       - name: Setup test with Rust stable
-        uses: dtolnay/rust-toolchain@1.85
+        uses: dtolnay/rust-toolchain@1.81
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.8.0
+        uses: Swatinem/rust-cache@v2.7.7
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -51,8 +55,8 @@ jobs:
     steps:
       - uses: actions/checkout@v3
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.8.0
+        uses: Swatinem/rust-cache@v2.7.7
-      - uses: dtolnay/rust-toolchain@1.85
+      - uses: dtolnay/rust-toolchain@1.81
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -68,8 +72,8 @@ jobs:
     name: Tests almost all features
     runs-on: ubuntu-latest
     container:
-      # Use ubuntu-22.04 to compile with glibc 2.35
+      # Use ubuntu-20.04 to compile with glibc 2.28
-      image: ubuntu:22.04
+      image: ubuntu:20.04
     if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
     steps:
       - uses: actions/checkout@v3
@@ -77,51 +81,19 @@ jobs:
         run: |
           apt-get update
           apt-get install --assume-yes build-essential curl
-      - uses: dtolnay/rust-toolchain@1.85
+      - uses: dtolnay/rust-toolchain@1.81
       - name: Run cargo build with almost all features
         run: |
-          cargo build --workspace --locked --release --features "$(cargo xtask list-features --exclude-feature cuda,test-ollama)"
+          cargo build --workspace --locked --release --features "$(cargo xtask list-features --exclude-feature cuda)"
       - name: Run cargo test with almost all features
         run: |
-          cargo test --workspace --locked --release --features "$(cargo xtask list-features --exclude-feature cuda,test-ollama)"
+          cargo test --workspace --locked --release --features "$(cargo xtask list-features --exclude-feature cuda)"
-
-  ollama-ubuntu:
-    name: Test with Ollama
-    runs-on: ubuntu-latest
-    env:
-      MEILI_TEST_OLLAMA_SERVER: "http://localhost:11434"
-    steps:
-      - uses: actions/checkout@v3
-      - name: Install Ollama
-        run: |
-          curl -fsSL https://ollama.com/install.sh | sudo -E sh
-      - name: Start serving
-        run: |
-          # Run it in the background, there is no way to daemonise at the moment
-          ollama serve &
-
-          # A short pause is required before the HTTP port is opened
-          sleep 5
-
-          # This endpoint blocks until ready
-          time curl -i http://localhost:11434
-
-      - name: Pull nomic-embed-text & all-minilm
-        run: |
-          ollama pull nomic-embed-text
-          ollama pull all-minilm
-
-      - name: Run cargo test
-        uses: actions-rs/cargo@v1
-        with:
-          command: test
-          args: --locked --release --all --features test-ollama ollama
 
   test-disabled-tokenization:
     name: Test disabled tokenization
     runs-on: ubuntu-latest
     container:
-      image: ubuntu:22.04
+      image: ubuntu:20.04
     if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
     steps:
       - uses: actions/checkout@v3
@@ -129,7 +101,7 @@ jobs:
         run: |
           apt-get update
           apt-get install --assume-yes build-essential curl
-      - uses: dtolnay/rust-toolchain@1.85
+      - uses: dtolnay/rust-toolchain@1.81
       - name: Run cargo tree without default features and check lindera is not present
         run: |
           if cargo tree -f '{p} {f}' -e normal --no-default-features | grep -qz lindera; then
@@ -145,17 +117,17 @@ jobs:
     name: Run tests in debug
     runs-on: ubuntu-latest
     container:
-      # Use ubuntu-22.04 to compile with glibc 2.35
+      # Use ubuntu-20.04 to compile with glibc 2.28
-      image: ubuntu:22.04
+      image: ubuntu:20.04
     steps:
       - uses: actions/checkout@v3
       - name: Install needed dependencies
         run: |
           apt-get update && apt-get install -y curl
           apt-get install build-essential -y
-      - uses: dtolnay/rust-toolchain@1.85
+      - uses: dtolnay/rust-toolchain@1.81
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.8.0
+        uses: Swatinem/rust-cache@v2.7.7
       - name: Run tests in debug
         uses: actions-rs/cargo@v1
         with:
@@ -167,12 +139,12 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.85
+      - uses: dtolnay/rust-toolchain@1.81
         with:
           profile: minimal
           components: clippy
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.8.0
+        uses: Swatinem/rust-cache@v2.7.7
       - name: Run cargo clippy
         uses: actions-rs/cargo@v1
         with:
@@ -184,14 +156,14 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.85
+      - uses: dtolnay/rust-toolchain@1.81
         with:
           profile: minimal
           toolchain: nightly-2024-07-09
           override: true
           components: rustfmt
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.8.0
+        uses: Swatinem/rust-cache@v2.7.7
       - name: Run cargo fmt
         # Since we never ran the `build.rs` script in the benchmark directory we are missing one auto-generated import file.
         # Since we want to trigger (and fail) this action as fast as possible, instead of building the benchmark crate

.github/workflows/update-cargo-toml-version.yml

@@ -4,7 +4,7 @@ on:
   workflow_dispatch:
     inputs:
       new_version:
-        description: "The new version (vX.Y.Z)"
+        description: 'The new version (vX.Y.Z)'
         required: true
 
 env:
@@ -18,7 +18,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
-      - uses: dtolnay/rust-toolchain@1.85
+      - uses: dtolnay/rust-toolchain@1.81
         with:
           profile: minimal
       - name: Install sd

.gitignore

@@ -11,21 +11,12 @@
 /bench
 /_xtask_benchmark.ms
 /benchmarks
-.DS_Store
 
 # Snapshots
 ## ... large
 *.full.snap
-## ... unreviewed
+##  ... unreviewed
 *.snap.new
-## ... pending
-*.pending-snap
-
-# Tmp files
-.tmp*
-
-# Database snapshot
-crates/meilisearch/db.snapshot
 
 # Fuzzcheck data for the facet indexing fuzz test
 crates/milli/fuzz/update::facet::incremental::fuzz::fuzz/

CONTRIBUTING.md

@@ -57,17 +57,9 @@ This command will be triggered to each PR as a requirement for merging it.
 You can set the `LINDERA_CACHE` environment variable to speed up your successive builds by up to 2 minutes.
 It'll store some built artifacts in the directory of your choice.
 
-We recommend using the `$HOME/.cache/meili/lindera` directory:
+We recommend using the standard `$HOME/.cache/lindera` directory:
 ```sh
-export LINDERA_CACHE=$HOME/.cache/meili/lindera
+export LINDERA_CACHE=$HOME/.cache/lindera
-```
-
-You can set the `MILLI_BENCH_DATASETS_PATH` environment variable to further speed up your builds.
-It'll store some big files used for the benchmarks in the directory of your choice.
-
-We recommend using the `$HOME/.cache/meili/benches` directory:
-```sh
-export MILLI_BENCH_DATASETS_PATH=$HOME/.cache/meili/benches
 ```
 
 Furthermore, you can improve incremental compilation by setting the `MEILI_NO_VERGEN` environment variable.
@@ -103,11 +95,6 @@ Meilisearch follows the [cargo xtask](https://github.com/matklad/cargo-xtask) wo
 
 Run `cargo xtask --help` from the root of the repository to find out what is available.
 
-#### Update the openAPI file if the API changed
-
-To update the openAPI file in the code, see [sprint_issue.md](https://github.com/meilisearch/meilisearch/blob/main/.github/ISSUE_TEMPLATE/sprint_issue.md#reminders-when-modifying-the-api).
-If you want to update the openAPI file on the [open-api repository](https://github.com/meilisearch/open-api), see [update-openapi-issue.md](https://github.com/meilisearch/engine-team/blob/main/issue-templates/update-openapi-issue.md).
-
 ### Logging
 
 Meilisearch uses [`tracing`](https://lib.rs/crates/tracing) for logging purposes. Tracing logs are structured and can be displayed as JSON to the end user, so prefer passing arguments as fields rather than interpolating them in the message.
@@ -158,7 +145,7 @@ Some notes on GitHub PRs:
 - The PR title should be accurate and descriptive of the changes.
 - [Convert your PR as a draft](https://help.github.com/en/github/collaborating-with-issues-and-pull-requests/changing-the-stage-of-a-pull-request) if your changes are a work in progress: no one will review it until you pass your PR as ready for review.<br>
   The draft PRs are recommended when you want to show that you are working on something and make your work visible.
-- The branch related to the PR must be **up-to-date with `main`** before merging. Fortunately, this project uses [GitHub Merge Queues](https://github.blog/news-insights/product-news/github-merge-queue-is-generally-available/) to automatically enforce this requirement without the PR author having to rebase manually.
+- The branch related to the PR must be **up-to-date with `main`** before merging. Fortunately, this project uses [Bors](https://github.com/bors-ng/bors-ng) to automatically enforce this requirement without the PR author having to rebase manually.
 
 ## Release Process (for internal team only)
 
@@ -166,7 +153,8 @@ Meilisearch tools follow the [Semantic Versioning Convention](https://semver.org
 
 ### Automation to rebase and Merge the PRs
 
-This project uses GitHub Merge Queues that helps us manage pull requests merging.
+This project integrates a bot that helps us manage pull requests merging.<br>
+_[Read more about this](https://github.com/meilisearch/integration-guides/blob/main/resources/bors.md)._
 
 ### How to Publish a new Release
 

Cargo.toml

@@ -22,7 +22,7 @@ members = [
 ]
 
 [workspace.package]
-version = "1.16.0"
+version = "1.12.2"
 authors = [
     "Quentin de Quelen <quentin@dequelen.me>",
     "Clément Renault <clement@meilisearch.com>",
@@ -36,12 +36,6 @@ license = "MIT"
 [profile.release]
 codegen-units = 1
 
-# We now compile heed without the NDEBUG define for better performance.
-# However, we still enable debug assertions for a better detection of
-# disk corruption on the cloud or in OSS.
-[profile.release.package.heed]
-debug-assertions = true
-
 [profile.dev.package.flate2]
 opt-level = 3
 

Dockerfile

@@ -1,5 +1,5 @@
 # Compile
-FROM    rust:1.85-alpine3.20 AS compiler
+FROM    rust:1.81.0-alpine3.20 AS compiler
 
 RUN     apk add -q --no-cache build-base openssl-dev
 

README.md

@@ -20,7 +20,7 @@
 <p align="center">
   <a href="https://deps.rs/repo/github/meilisearch/meilisearch"><img src="https://deps.rs/repo/github/meilisearch/meilisearch/status.svg" alt="Dependency status"></a>
   <a href="https://github.com/meilisearch/meilisearch/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-informational" alt="License"></a>
-  <a href="https://github.com/meilisearch/meilisearch/queue"><img alt="Merge Queues enabled" src="https://img.shields.io/badge/Merge_Queues-enabled-%2357cf60?logo=github"></a>
+  <a href="https://ms-bors.herokuapp.com/repositories/52"><img src="https://bors.tech/images/badge_small.svg" alt="Bors enabled"></a>
 </p>
 
 <p align="center">⚡ A lightning-fast search engine that fits effortlessly into your apps, websites, and workflow 🔍</p>
@@ -41,7 +41,7 @@
 - [**Movies**](https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=organization) — An application to help you find streaming platforms to watch movies using [hybrid search](https://www.meilisearch.com/solutions/hybrid-search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos).
 - [**Ecommerce**](https://ecommerce.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Ecommerce website using disjunctive [facets](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos), range and rating filtering, and pagination.
 - [**Songs**](https://music.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Search through 47 million of songs.
-- [**SaaS**](https://saas.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Search for contacts, deals, and companies in this [multi-tenant](https://www.meilisearch.com/docs/learn/security/multitenancy_tenant_tokens?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) CRM application.
+- [**SaaS**](https://saas.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Search for contacts, deals, and companies in this [multi-tenant](https://www.meilisearch.com/docs/learn/security/multitenancy_tenant_tokens?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) CRM application.
 
 See the list of all our example apps in our [demos repository](https://github.com/meilisearch/demos).
 
@@ -99,7 +99,7 @@ If you want to know more about the kind of data we collect and what we use it fo
 
 ## 📫 Get in touch!
 
-Meilisearch is a search engine created by [Meili](https://www.meilisearch.com/careers), a software development company headquartered in France and with team members all over the world. Want to know more about us? [Check out our blog!](https://blog.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=contact)
+Meilisearch is a search engine created by [Meili]([https://www.welcometothejungle.com/en/companies/meilisearch](https://www.meilisearch.com/careers)), a software development company headquartered in France and with team members all over the world. Want to know more about us? [Check out our blog!](https://blog.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=contact)
 
 🗞 [Subscribe to our newsletter](https://meilisearch.us2.list-manage.com/subscribe?u=27870f7b71c908a8b359599fb&id=79582d828e) if you don't want to miss any updates! We promise we won't clutter your mailbox: we only send one edition every two months.
 

assets/grafana-dashboard.json

@@ -1501,300 +1501,6 @@
       "title": "Task queue latency",
       "type": "timeseries"
     },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "color": {
-            "mode": "palette-classic"
-          },
-          "custom": {
-            "axisBorderShow": false,
-            "axisCenteredZero": false,
-            "axisColorMode": "text",
-            "axisLabel": "",
-            "axisPlacement": "auto",
-            "barAlignment": 0,
-            "drawStyle": "line",
-            "fillOpacity": 15,
-            "gradientMode": "none",
-            "hideFrom": {
-              "legend": false,
-              "tooltip": false,
-              "viz": false
-            },
-            "insertNulls": false,
-            "lineInterpolation": "linear",
-            "lineWidth": 1,
-            "pointSize": 5,
-            "scaleDistribution": {
-              "type": "linear"
-            },
-            "showPoints": "never",
-            "spanNulls": false,
-            "stacking": {
-              "group": "A",
-              "mode": "none"
-            },
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "mappings": [],
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green"
-              },
-              {
-                "color": "red",
-                "value": 80
-              }
-            ]
-          },
-          "unit": "none"
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 11,
-        "w": 12,
-        "x": 12,
-        "y": 51
-      },
-      "id": 29,
-      "interval": "5s",
-      "options": {
-        "legend": {
-          "calcs": [],
-          "displayMode": "list",
-          "placement": "right",
-          "showLegend": true
-        },
-        "tooltip": {
-          "mode": "single",
-          "sort": "none"
-        }
-      },
-      "pluginVersion": "8.1.4",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "editorMode": "builder",
-          "exemplar": true,
-          "expr": "meilisearch_task_queue_used_size{instance=\"$instance\", job=\"$job\"}",
-          "interval": "",
-          "legendFormat": "{{value}} ",
-          "range": true,
-          "refId": "A"
-        }
-      ],
-      "title": "Task queue used size in bytes",
-      "type": "timeseries"
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "color": {
-            "mode": "palette-classic"
-          },
-          "custom": {
-            "axisBorderShow": false,
-            "axisCenteredZero": false,
-            "axisColorMode": "text",
-            "axisLabel": "",
-            "axisPlacement": "auto",
-            "barAlignment": 0,
-            "drawStyle": "line",
-            "fillOpacity": 15,
-            "gradientMode": "none",
-            "hideFrom": {
-              "legend": false,
-              "tooltip": false,
-              "viz": false
-            },
-            "insertNulls": false,
-            "lineInterpolation": "linear",
-            "lineWidth": 1,
-            "pointSize": 5,
-            "scaleDistribution": {
-              "type": "linear"
-            },
-            "showPoints": "never",
-            "spanNulls": false,
-            "stacking": {
-              "group": "A",
-              "mode": "none"
-            },
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "mappings": [],
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green"
-              },
-              {
-                "color": "red",
-                "value": 80
-              }
-            ]
-          },
-          "unit": "none"
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 11,
-        "w": 12,
-        "x": 12,
-        "y": 51
-      },
-      "id": 29,
-      "interval": "5s",
-      "options": {
-        "legend": {
-          "calcs": [],
-          "displayMode": "list",
-          "placement": "right",
-          "showLegend": true
-        },
-        "tooltip": {
-          "mode": "single",
-          "sort": "none"
-        }
-      },
-      "pluginVersion": "8.1.4",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "editorMode": "builder",
-          "exemplar": true,
-          "expr": "meilisearch_task_queue_size_until_stop_registering{instance=\"$instance\", job=\"$job\"}",
-          "interval": "",
-          "legendFormat": "{{value}} ",
-          "range": true,
-          "refId": "A"
-        }
-      ],
-      "title": "Task queue available size until it stop receiving tasks.",
-      "type": "timeseries"
-    },
-    {
-      "datasource": {
-        "type": "prometheus",
-        "uid": "${DS_PROMETHEUS}"
-      },
-      "fieldConfig": {
-        "defaults": {
-          "color": {
-            "mode": "palette-classic"
-          },
-          "custom": {
-            "axisBorderShow": false,
-            "axisCenteredZero": false,
-            "axisColorMode": "text",
-            "axisLabel": "",
-            "axisPlacement": "auto",
-            "barAlignment": 0,
-            "drawStyle": "line",
-            "fillOpacity": 15,
-            "gradientMode": "none",
-            "hideFrom": {
-              "legend": false,
-              "tooltip": false,
-              "viz": false
-            },
-            "insertNulls": false,
-            "lineInterpolation": "linear",
-            "lineWidth": 1,
-            "pointSize": 5,
-            "scaleDistribution": {
-              "type": "linear"
-            },
-            "showPoints": "never",
-            "spanNulls": false,
-            "stacking": {
-              "group": "A",
-              "mode": "none"
-            },
-            "thresholdsStyle": {
-              "mode": "off"
-            }
-          },
-          "mappings": [],
-          "thresholds": {
-            "mode": "absolute",
-            "steps": [
-              {
-                "color": "green"
-              },
-              {
-                "color": "red",
-                "value": 80
-              }
-            ]
-          },
-          "unit": "none"
-        },
-        "overrides": []
-      },
-      "gridPos": {
-        "h": 11,
-        "w": 12,
-        "x": 12,
-        "y": 51
-      },
-      "id": 29,
-      "interval": "5s",
-      "options": {
-        "legend": {
-          "calcs": [],
-          "displayMode": "list",
-          "placement": "right",
-          "showLegend": true
-        },
-        "tooltip": {
-          "mode": "single",
-          "sort": "none"
-        }
-      },
-      "pluginVersion": "8.1.4",
-      "targets": [
-        {
-          "datasource": {
-            "type": "prometheus",
-            "uid": "${DS_PROMETHEUS}"
-          },
-          "editorMode": "builder",
-          "exemplar": true,
-          "expr": "meilisearch_task_queue_max_size{instance=\"$instance\", job=\"$job\"}",
-          "interval": "",
-          "legendFormat": "{{value}} ",
-          "range": true,
-          "refId": "A"
-        }
-      ],
-      "title": "Task queue maximum possible size",
-      "type": "stat"
-    },
     {
       "collapsed": true,
       "datasource": {

bors.toml

@@ -0,0 +1,11 @@
+status = [
+    'Tests on ubuntu-20.04',
+    'Tests on macos-13',
+    'Tests on windows-2022',
+    'Run Clippy',
+    'Run Rustfmt',
+    'Run tests in debug',
+]
+pr_status = ['Milestone Check']
+# 3 hours timeout
+timeout-sec = 10800

crates/benchmarks/Cargo.toml

@@ -11,27 +11,27 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.98"
+anyhow = "1.0.95"
-bumpalo = "3.18.1"
+bumpalo = "3.16.0"
 csv = "1.3.1"
 memmap2 = "0.9.5"
 milli = { path = "../milli" }
-mimalloc = { version = "0.1.47", default-features = false }
+mimalloc = { version = "0.1.43", default-features = false }
-serde_json = { version = "1.0.140", features = ["preserve_order"] }
+serde_json = { version = "1.0.135", features = ["preserve_order"] }
-tempfile = "3.20.0"
+tempfile = "3.15.0"
 
 [dev-dependencies]
-criterion = { version = "0.6.0", features = ["html_reports"] }
+criterion = { version = "0.5.1", features = ["html_reports"] }
 rand = "0.8.5"
 rand_chacha = "0.3.1"
-roaring = "0.10.12"
+roaring = "0.10.10"
 
 [build-dependencies]
-anyhow = "1.0.98"
+anyhow = "1.0.95"
-bytes = "1.10.1"
+bytes = "1.9.0"
-convert_case = "0.8.0"
+convert_case = "0.6.0"
-flate2 = "1.1.2"
+flate2 = "1.0.35"
-reqwest = { version = "0.12.20", features = ["blocking", "rustls-tls"], default-features = false }
+reqwest = { version = "0.12.12", features = ["blocking", "rustls-tls"], default-features = false }
 
 [features]
 default = ["milli/all-tokenizations"]
@@ -51,8 +51,3 @@ harness = false
 [[bench]]
 name = "indexing"
 harness = false
-
-[[bench]]
-name = "sort"
-harness = false
-

crates/benchmarks/benches/indexing.rs

@@ -10,9 +10,9 @@ use milli::documents::PrimaryKey;
 use milli::heed::{EnvOpenOptions, RwTxn};
 use milli::progress::Progress;
 use milli::update::new::indexer;
-use milli::update::{IndexerConfig, Settings};
+use milli::update::{IndexDocumentsMethod, IndexerConfig, Settings};
-use milli::vector::RuntimeEmbedders;
+use milli::vector::EmbeddingConfigs;
-use milli::{FilterableAttributesRule, Index};
+use milli::Index;
 use rand::seq::SliceRandom;
 use rand_chacha::rand_core::SeedableRng;
 use roaring::RoaringBitmap;
@@ -35,11 +35,10 @@ fn setup_dir(path: impl AsRef<Path>) {
 fn setup_index() -> Index {
     let path = "benches.mmdb";
     setup_dir(path);
-    let options = EnvOpenOptions::new();
+    let mut options = EnvOpenOptions::new();
-    let mut options = options.read_txn_without_tls();
     options.map_size(100 * 1024 * 1024 * 1024); // 100 GB
     options.max_readers(100);
-    Index::new(options, path, true).unwrap()
+    Index::new(options, path).unwrap()
 }
 
 fn setup_settings<'t>(
@@ -58,14 +57,13 @@ fn setup_settings<'t>(
     let searchable_fields = searchable_fields.iter().map(|s| s.to_string()).collect();
     builder.set_searchable_fields(searchable_fields);
 
-    let filterable_fields =
+    let filterable_fields = filterable_fields.iter().map(|s| s.to_string()).collect();
-        filterable_fields.iter().map(|s| FilterableAttributesRule::Field(s.to_string())).collect();
     builder.set_filterable_fields(filterable_fields);
 
     let sortable_fields = sortable_fields.iter().map(|s| s.to_string()).collect();
     builder.set_sortable_fields(sortable_fields);
 
-    builder.execute(&|| false, &Progress::default(), Default::default()).unwrap();
+    builder.execute(|_| (), || false).unwrap();
 }
 
 fn setup_index_with_settings(
@@ -140,9 +138,10 @@ fn indexing_songs_default(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::SMOL_SONGS, "csv");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -166,10 +165,9 @@ fn indexing_songs_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -207,9 +205,10 @@ fn reindexing_songs_default(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::SMOL_SONGS, "csv");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -233,10 +232,9 @@ fn reindexing_songs_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -252,9 +250,10 @@ fn reindexing_songs_default(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::SMOL_SONGS, "csv");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -278,10 +277,9 @@ fn reindexing_songs_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -321,9 +319,10 @@ fn deleting_songs_in_batches_default(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::SMOL_SONGS, "csv");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -347,10 +346,9 @@ fn deleting_songs_in_batches_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -398,9 +396,10 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::SMOL_SONGS_1_2, "csv");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -424,10 +423,9 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -443,9 +441,10 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::SMOL_SONGS_3_4, "csv");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -469,10 +468,9 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -484,9 +482,10 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::SMOL_SONGS_4_4, "csv");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -510,10 +509,9 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -551,10 +549,11 @@ fn indexing_songs_without_faceted_numbers(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::SMOL_SONGS, "csv");
 
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -578,10 +577,9 @@ fn indexing_songs_without_faceted_numbers(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -619,9 +617,10 @@ fn indexing_songs_without_faceted_fields(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::SMOL_SONGS, "csv");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -645,10 +644,9 @@ fn indexing_songs_without_faceted_fields(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -686,9 +684,10 @@ fn indexing_wiki(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::SMOL_WIKI_ARTICLES, "csv");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -712,10 +711,9 @@ fn indexing_wiki(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -752,9 +750,10 @@ fn reindexing_wiki(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::SMOL_WIKI_ARTICLES, "csv");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -778,10 +777,9 @@ fn reindexing_wiki(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -797,9 +795,10 @@ fn reindexing_wiki(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::SMOL_WIKI_ARTICLES, "csv");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -823,10 +822,9 @@ fn reindexing_wiki(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -865,9 +863,10 @@ fn deleting_wiki_in_batches_default(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::SMOL_WIKI_ARTICLES, "csv");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -891,10 +890,9 @@ fn deleting_wiki_in_batches_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -941,10 +939,11 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents =
                     utils::documents_from(datasets_paths::SMOL_WIKI_ARTICLES_1_2, "csv");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -968,10 +967,9 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -987,10 +985,11 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents =
                     utils::documents_from(datasets_paths::SMOL_WIKI_ARTICLES_3_4, "csv");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -1014,10 +1013,9 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1029,10 +1027,11 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents =
                     utils::documents_from(datasets_paths::SMOL_WIKI_ARTICLES_4_4, "csv");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -1056,10 +1055,9 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1097,9 +1095,10 @@ fn indexing_movies_default(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::MOVIES, "json");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -1123,10 +1122,9 @@ fn indexing_movies_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1163,9 +1161,10 @@ fn reindexing_movies_default(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::MOVIES, "json");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -1189,10 +1188,9 @@ fn reindexing_movies_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1208,9 +1206,10 @@ fn reindexing_movies_default(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::MOVIES, "json");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -1234,10 +1233,9 @@ fn reindexing_movies_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1276,9 +1274,10 @@ fn deleting_movies_in_batches_default(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::MOVIES, "json");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -1302,10 +1301,9 @@ fn deleting_movies_in_batches_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1351,10 +1349,9 @@ fn delete_documents_from_ids(index: Index, document_ids_to_delete: Vec<RoaringBi
             new_fields_ids_map,
             Some(primary_key),
             &document_changes,
-            RuntimeEmbedders::default(),
+            EmbeddingConfigs::default(),
             &|| false,
             &Progress::default(),
-            &Default::default(),
         )
         .unwrap();
 
@@ -1390,9 +1387,10 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::MOVIES_1_2, "json");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -1416,10 +1414,9 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1435,9 +1432,10 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::MOVIES_3_4, "json");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -1461,10 +1459,9 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1476,9 +1473,10 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::MOVIES_4_4, "json");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -1502,10 +1500,9 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1566,9 +1563,10 @@ fn indexing_nested_movies_default(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::NESTED_MOVIES, "json");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -1592,10 +1590,9 @@ fn indexing_nested_movies_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1657,9 +1654,10 @@ fn deleting_nested_movies_in_batches_default(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::NESTED_MOVIES, "json");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -1683,10 +1681,9 @@ fn deleting_nested_movies_in_batches_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1740,9 +1737,10 @@ fn indexing_nested_movies_without_faceted_fields(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::NESTED_MOVIES, "json");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -1766,10 +1764,9 @@ fn indexing_nested_movies_without_faceted_fields(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1807,9 +1804,10 @@ fn indexing_geo(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::SMOL_ALL_COUNTRIES, "jsonl");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -1833,10 +1831,9 @@ fn indexing_geo(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1873,9 +1870,10 @@ fn reindexing_geo(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::SMOL_ALL_COUNTRIES, "jsonl");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -1899,10 +1897,9 @@ fn reindexing_geo(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1918,9 +1915,10 @@ fn reindexing_geo(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::SMOL_ALL_COUNTRIES, "jsonl");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -1944,10 +1942,9 @@ fn reindexing_geo(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1986,9 +1983,10 @@ fn deleting_geo_in_batches_default(c: &mut Criterion) {
                 let db_fields_ids_map = index.fields_ids_map(&rtxn).unwrap();
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer =
+                    indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
                 let documents = utils::documents_from(datasets_paths::SMOL_ALL_COUNTRIES, "jsonl");
-                indexer.replace_documents(&documents).unwrap();
+                indexer.add_documents(&documents).unwrap();
 
                 let indexer_alloc = Bump::new();
                 let (document_changes, _operation_stats, primary_key) = indexer
@@ -2012,10 +2010,9 @@ fn deleting_geo_in_batches_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    RuntimeEmbedders::default(),
+                    EmbeddingConfigs::default(),
                     &|| false,
                     &Progress::default(),
-                    &Default::default(),
                 )
                 .unwrap();
 

crates/benchmarks/benches/search_geo.rs

@@ -3,7 +3,6 @@ mod utils;
 
 use criterion::{criterion_group, criterion_main};
 use milli::update::Settings;
-use milli::FilterableAttributesRule;
 use utils::Conf;
 
 #[cfg(not(windows))]
@@ -22,10 +21,8 @@ fn base_conf(builder: &mut Settings) {
         ["name", "alternatenames", "elevation"].iter().map(|s| s.to_string()).collect();
     builder.set_searchable_fields(searchable_fields);
 
-    let filterable_fields = ["_geo", "population", "elevation"]
+    let filterable_fields =
-        .iter()
+        ["_geo", "population", "elevation"].iter().map(|s| s.to_string()).collect();
-        .map(|s| FilterableAttributesRule::Field(s.to_string()))
-        .collect();
     builder.set_filterable_fields(filterable_fields);
 
     let sortable_fields =

crates/benchmarks/benches/search_songs.rs

@@ -3,7 +3,6 @@ mod utils;
 
 use criterion::{criterion_group, criterion_main};
 use milli::update::Settings;
-use milli::FilterableAttributesRule;
 use utils::Conf;
 
 #[cfg(not(windows))]
@@ -23,7 +22,7 @@ fn base_conf(builder: &mut Settings) {
 
     let faceted_fields = ["released-timestamp", "duration-float", "genre", "country", "artist"]
         .iter()
-        .map(|s| FilterableAttributesRule::Field(s.to_string()))
+        .map(|s| s.to_string())
         .collect();
     builder.set_filterable_fields(faceted_fields);
 }

crates/benchmarks/benches/sort.rs

@@ -1,114 +0,0 @@
-//! This benchmark module is used to compare the performance of sorting documents in /search VS /documents
-//!
-//! The tests/benchmarks were designed in the context of a query returning only 20 documents.
-
-mod datasets_paths;
-mod utils;
-
-use criterion::{criterion_group, criterion_main};
-use milli::update::Settings;
-use utils::Conf;
-
-#[cfg(not(windows))]
-#[global_allocator]
-static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
-
-fn base_conf(builder: &mut Settings) {
-    let displayed_fields =
-        ["geonameid", "name", "asciiname", "alternatenames", "_geo", "population"]
-            .iter()
-            .map(|s| s.to_string())
-            .collect();
-    builder.set_displayed_fields(displayed_fields);
-
-    let sortable_fields =
-        ["_geo", "name", "population", "elevation", "timezone", "modification-date"]
-            .iter()
-            .map(|s| s.to_string())
-            .collect();
-    builder.set_sortable_fields(sortable_fields);
-}
-
-#[rustfmt::skip]
-const BASE_CONF: Conf = Conf {
-    dataset: datasets_paths::SMOL_ALL_COUNTRIES,
-    dataset_format: "jsonl",
-    configure: base_conf,
-    primary_key: Some("geonameid"),
-    queries: &[""],
-    offsets: &[
-        Some((0, 20)), // The most common query in the real world
-        Some((0, 500)), // A query that ranges over many documents
-        Some((980, 20)), // The worst query that could happen in the real world
-        Some((800_000, 20)) // The worst query
-    ],
-    get_documents: true,
-    ..Conf::BASE
-};
-
-fn bench_sort(c: &mut criterion::Criterion) {
-    #[rustfmt::skip]
-    let confs = &[
-        utils::Conf {
-            group_name: "without sort",
-            sort: None,
-            ..BASE_CONF
-        },
-
-        utils::Conf {
-            group_name: "sort on many different values",
-            sort: Some(vec!["name:asc"]),
-            ..BASE_CONF
-        },
-
-        utils::Conf {
-            group_name: "sort on many similar values",
-            sort: Some(vec!["timezone:desc"]),
-            ..BASE_CONF
-        },
-
-        utils::Conf {
-            group_name: "sort on many similar then different values",
-            sort: Some(vec!["timezone:desc", "name:asc"]),
-            ..BASE_CONF
-        },
-
-        utils::Conf {
-            group_name: "sort on many different then similar values",
-            sort: Some(vec!["timezone:desc", "name:asc"]),
-            ..BASE_CONF
-        },
-
-        utils::Conf {
-            group_name: "geo sort",
-            sample_size: Some(10),
-            sort: Some(vec!["_geoPoint(45.4777599, 9.1967508):asc"]),
-            ..BASE_CONF
-        },
-
-        utils::Conf {
-            group_name: "sort on many similar values then geo sort",
-            sample_size: Some(50),
-            sort: Some(vec!["timezone:desc", "_geoPoint(45.4777599, 9.1967508):asc"]),
-            ..BASE_CONF
-        },
-
-        utils::Conf {
-            group_name: "sort on many different values then geo sort",
-            sample_size: Some(50),
-            sort: Some(vec!["name:desc", "_geoPoint(45.4777599, 9.1967508):asc"]),
-            ..BASE_CONF
-        },
-
-        utils::Conf {
-            group_name: "sort on many fields",
-            sort: Some(vec!["population:asc", "name:asc", "elevation:asc", "timezone:asc"]),
-            ..BASE_CONF
-        },
-    ];
-
-    utils::run_benches(c, confs);
-}
-
-criterion_group!(benches, bench_sort);
-criterion_main!(benches);

crates/benchmarks/benches/utils.rs

@@ -9,12 +9,11 @@ use anyhow::Context;
 use bumpalo::Bump;
 use criterion::BenchmarkId;
 use memmap2::Mmap;
-use milli::documents::sort::recursive_sort;
 use milli::heed::EnvOpenOptions;
 use milli::progress::Progress;
 use milli::update::new::indexer;
-use milli::update::{IndexerConfig, Settings};
+use milli::update::{IndexDocumentsMethod, IndexerConfig, Settings};
-use milli::vector::RuntimeEmbedders;
+use milli::vector::EmbeddingConfigs;
 use milli::{Criterion, Filter, Index, Object, TermsMatchingStrategy};
 use serde_json::Value;
 
@@ -36,12 +35,6 @@ pub struct Conf<'a> {
     pub configure: fn(&mut Settings),
     pub filter: Option<&'a str>,
     pub sort: Option<Vec<&'a str>>,
-    /// set to skip documents (offset, limit)
-    pub offsets: &'a [Option<(usize, usize)>],
-    /// enable if you want to bench getting documents without querying
-    pub get_documents: bool,
-    /// configure the benchmark sample size
-    pub sample_size: Option<usize>,
     /// enable or disable the optional words on the query
     pub optional_words: bool,
     /// primary key, if there is None we'll auto-generate docids for every documents
@@ -59,9 +52,6 @@ impl Conf<'_> {
         configure: |_| (),
         filter: None,
         sort: None,
-        offsets: &[None],
-        get_documents: false,
-        sample_size: None,
         optional_words: true,
         primary_key: None,
     };
@@ -75,11 +65,10 @@ pub fn base_setup(conf: &Conf) -> Index {
     }
     create_dir_all(conf.database_name).unwrap();
 
-    let options = EnvOpenOptions::new();
+    let mut options = EnvOpenOptions::new();
-    let mut options = options.read_txn_without_tls();
     options.map_size(100 * 1024 * 1024 * 1024); // 100 GB
     options.max_readers(100);
-    let index = Index::new(options, conf.database_name, true).unwrap();
+    let index = Index::new(options, conf.database_name).unwrap();
 
     let config = IndexerConfig::default();
     let mut wtxn = index.write_txn().unwrap();
@@ -100,7 +89,7 @@ pub fn base_setup(conf: &Conf) -> Index {
 
     (conf.configure)(&mut builder);
 
-    builder.execute(&|| false, &Progress::default(), Default::default()).unwrap();
+    builder.execute(|_| (), || false).unwrap();
     wtxn.commit().unwrap();
 
     let config = IndexerConfig::default();
@@ -110,8 +99,8 @@ pub fn base_setup(conf: &Conf) -> Index {
     let mut new_fields_ids_map = db_fields_ids_map.clone();
 
     let documents = documents_from(conf.dataset, conf.dataset_format);
-    let mut indexer = indexer::DocumentOperation::new();
+    let mut indexer = indexer::DocumentOperation::new(IndexDocumentsMethod::ReplaceDocuments);
-    indexer.replace_documents(&documents).unwrap();
+    indexer.add_documents(&documents).unwrap();
 
     let indexer_alloc = Bump::new();
     let (document_changes, _operation_stats, primary_key) = indexer
@@ -135,10 +124,9 @@ pub fn base_setup(conf: &Conf) -> Index {
         new_fields_ids_map,
         primary_key,
         &document_changes,
-        RuntimeEmbedders::default(),
+        EmbeddingConfigs::default(),
         &|| false,
         &Progress::default(),
-        &Default::default(),
     )
     .unwrap();
 
@@ -155,79 +143,25 @@ pub fn run_benches(c: &mut criterion::Criterion, confs: &[Conf]) {
         let file_name = Path::new(conf.dataset).file_name().and_then(|f| f.to_str()).unwrap();
         let name = format!("{}: {}", file_name, conf.group_name);
         let mut group = c.benchmark_group(&name);
-        if let Some(sample_size) = conf.sample_size {
-            group.sample_size(sample_size);
-        }
 
         for &query in conf.queries {
-            for offset in conf.offsets {
+            group.bench_with_input(BenchmarkId::from_parameter(query), &query, |b, &query| {
-                let parameter = match offset {
+                b.iter(|| {
-                    None => query.to_string(),
+                    let rtxn = index.read_txn().unwrap();
-                    Some((offset, limit)) => format!("{query}[{offset}:{limit}]"),
+                    let mut search = index.search(&rtxn);
-                };
+                    search.query(query).terms_matching_strategy(TermsMatchingStrategy::default());
-                group.bench_with_input(
+                    if let Some(filter) = conf.filter {
-                    BenchmarkId::from_parameter(parameter),
+                        let filter = Filter::from_str(filter).unwrap().unwrap();
-                    &query,
+                        search.filter(filter);
-                    |b, &query| {
+                    }
-                        b.iter(|| {
+                    if let Some(sort) = &conf.sort {
-                            let rtxn = index.read_txn().unwrap();
+                        let sort = sort.iter().map(|sort| sort.parse().unwrap()).collect();
-                            let mut search = index.search(&rtxn);
+                        search.sort_criteria(sort);
-                            search
+                    }
-                                .query(query)
+                    let _ids = search.execute().unwrap();
-                                .terms_matching_strategy(TermsMatchingStrategy::default());
-                            if let Some(filter) = conf.filter {
-                                let filter = Filter::from_str(filter).unwrap().unwrap();
-                                search.filter(filter);
-                            }
-                            if let Some(sort) = &conf.sort {
-                                let sort = sort.iter().map(|sort| sort.parse().unwrap()).collect();
-                                search.sort_criteria(sort);
-                            }
-                            if let Some((offset, limit)) = offset {
-                                search.offset(*offset).limit(*limit);
-                            }
-
-                            let _ids = search.execute().unwrap();
-                        });
-                    },
-                );
-            }
-        }
-
-        if conf.get_documents {
-            for offset in conf.offsets {
-                let parameter = match offset {
-                    None => String::from("get_documents"),
-                    Some((offset, limit)) => format!("get_documents[{offset}:{limit}]"),
-                };
-                group.bench_with_input(BenchmarkId::from_parameter(parameter), &(), |b, &()| {
-                    b.iter(|| {
-                        let rtxn = index.read_txn().unwrap();
-                        if let Some(sort) = &conf.sort {
-                            let sort = sort.iter().map(|sort| sort.parse().unwrap()).collect();
-                            let all_docs = index.documents_ids(&rtxn).unwrap();
-                            let facet_sort =
-                                recursive_sort(&index, &rtxn, sort, &all_docs).unwrap();
-                            let iter = facet_sort.iter().unwrap();
-                            if let Some((offset, limit)) = offset {
-                                let _results = iter.skip(*offset).take(*limit).collect::<Vec<_>>();
-                            } else {
-                                let _results = iter.collect::<Vec<_>>();
-                            }
-                        } else {
-                            let all_docs = index.documents_ids(&rtxn).unwrap();
-                            if let Some((offset, limit)) = offset {
-                                let _results =
-                                    all_docs.iter().skip(*offset).take(*limit).collect::<Vec<_>>();
-                            } else {
-                                let _results = all_docs.iter().collect::<Vec<_>>();
-                            }
-                        }
-                    });
                 });
-            }
+            });
         }
-
         group.finish();
 
         index.prepare_for_closing().wait();

crates/benchmarks/build.rs

@@ -67,7 +67,7 @@ fn main() -> anyhow::Result<()> {
         writeln!(
             &mut manifest_paths_file,
             r#"pub const {}: &str = {:?};"#,
-            dataset.to_case(Case::UpperSnake),
+            dataset.to_case(Case::ScreamingSnake),
             out_file.display(),
         )?;
 

crates/build-info/Cargo.toml

@@ -11,8 +11,8 @@ license.workspace = true
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
-time = { version = "0.3.41", features = ["parsing"] }
+time = { version = "0.3.37", features = ["parsing"] }
 
 [build-dependencies]
-anyhow = "1.0.98"
+anyhow = "1.0.95"
-vergen-git2 = "1.0.7"
+vergen-git2 = "1.0.2"

crates/dump/Cargo.toml

@@ -11,21 +11,21 @@ readme.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.98"
+anyhow = "1.0.95"
-flate2 = "1.1.2"
+flate2 = "1.0.35"
-http = "1.3.1"
+http = "1.2.0"
 meilisearch-types = { path = "../meilisearch-types" }
-once_cell = "1.21.3"
+once_cell = "1.20.2"
 regex = "1.11.1"
-roaring = { version = "0.10.12", features = ["serde"] }
+roaring = { version = "0.10.10", features = ["serde"] }
-serde = { version = "1.0.219", features = ["derive"] }
+serde = { version = "1.0.217", features = ["derive"] }
-serde_json = { version = "1.0.140", features = ["preserve_order"] }
+serde_json = { version = "1.0.135", features = ["preserve_order"] }
-tar = "0.4.44"
+tar = "0.4.43"
-tempfile = "3.20.0"
+tempfile = "3.15.0"
-thiserror = "2.0.12"
+thiserror = "2.0.9"
-time = { version = "0.3.41", features = ["serde-well-known", "formatting", "parsing", "macros"] }
+time = { version = "0.3.37", features = ["serde-well-known", "formatting", "parsing", "macros"] }
 tracing = "0.1.41"
-uuid = { version = "1.17.0", features = ["serde", "v4"] }
+uuid = { version = "1.11.0", features = ["serde", "v4"] }
 
 [dev-dependencies]
 big_s = "1.0.2"

crates/dump/README.md

@@ -10,10 +10,8 @@ dump
 ├── instance-uid.uuid
 ├── keys.jsonl
 ├── metadata.json
-├── tasks
+└── tasks
-│   ├── update_files
+    ├── update_files
-│   │   └── [task_id].jsonl
+    │   └── [task_id].jsonl
-│   └── queue.jsonl
-└── batches
     └── queue.jsonl
-```
+```

crates/dump/src/lib.rs

@@ -1,17 +1,12 @@
 #![allow(clippy::type_complexity)]
 #![allow(clippy::wrong_self_convention)]
 
-use std::collections::BTreeMap;
-
 use meilisearch_types::batches::BatchId;
-use meilisearch_types::byte_unit::Byte;
 use meilisearch_types::error::ResponseError;
 use meilisearch_types::keys::Key;
 use meilisearch_types::milli::update::IndexDocumentsMethod;
 use meilisearch_types::settings::Unchecked;
-use meilisearch_types::tasks::{
+use meilisearch_types::tasks::{Details, IndexSwap, KindWithContent, Status, Task, TaskId};
-    Details, ExportIndexSettings, IndexSwap, KindWithContent, Status, Task, TaskId,
-};
 use meilisearch_types::InstanceUid;
 use roaring::RoaringBitmap;
 use serde::{Deserialize, Serialize};
@@ -146,15 +141,6 @@ pub enum KindDump {
         instance_uid: Option<InstanceUid>,
     },
     SnapshotCreation,
-    Export {
-        url: String,
-        api_key: Option<String>,
-        payload_size: Option<Byte>,
-        indexes: BTreeMap<String, ExportIndexSettings>,
-    },
-    UpgradeDatabase {
-        from: (u32, u32, u32),
-    },
 }
 
 impl From<Task> for TaskDump {
@@ -224,18 +210,6 @@ impl From<KindWithContent> for KindDump {
                 KindDump::DumpCreation { keys, instance_uid }
             }
             KindWithContent::SnapshotCreation => KindDump::SnapshotCreation,
-            KindWithContent::Export { url, api_key, payload_size, indexes } => KindDump::Export {
-                url,
-                api_key,
-                payload_size,
-                indexes: indexes
-                    .into_iter()
-                    .map(|(pattern, settings)| (pattern.to_string(), settings))
-                    .collect(),
-            },
-            KindWithContent::UpgradeDatabase { from: version } => {
-                KindDump::UpgradeDatabase { from: version }
-            }
         }
     }
 }
@@ -248,16 +222,14 @@ pub(crate) mod test {
 
     use big_s::S;
     use maplit::{btreemap, btreeset};
-    use meilisearch_types::batches::{Batch, BatchEnqueuedAt, BatchStats};
     use meilisearch_types::facet_values_sort::FacetValuesSort;
-    use meilisearch_types::features::{Network, Remote, RuntimeTogglableFeatures};
+    use meilisearch_types::features::RuntimeTogglableFeatures;
     use meilisearch_types::index_uid_pattern::IndexUidPattern;
     use meilisearch_types::keys::{Action, Key};
+    use meilisearch_types::milli;
     use meilisearch_types::milli::update::Setting;
-    use meilisearch_types::milli::{self, FilterableAttributesRule};
     use meilisearch_types::settings::{Checked, FacetingSettings, Settings};
-    use meilisearch_types::task_view::DetailsView;
+    use meilisearch_types::tasks::{Details, Status};
-    use meilisearch_types::tasks::{BatchStopReason, Details, Kind, Status};
     use serde_json::{json, Map, Value};
     use time::macros::datetime;
     use uuid::Uuid;
@@ -299,10 +271,7 @@ pub(crate) mod test {
         let settings = Settings {
             displayed_attributes: Setting::Set(vec![S("race"), S("name")]).into(),
             searchable_attributes: Setting::Set(vec![S("name"), S("race")]).into(),
-            filterable_attributes: Setting::Set(vec![
+            filterable_attributes: Setting::Set(btreeset! { S("race"), S("age") }),
-                FilterableAttributesRule::Field(S("race")),
-                FilterableAttributesRule::Field(S("age")),
-            ]),
             sortable_attributes: Setting::Set(btreeset! { S("age") }),
             ranking_rules: Setting::NotSet,
             stop_words: Setting::NotSet,
@@ -325,41 +294,11 @@ pub(crate) mod test {
             localized_attributes: Setting::NotSet,
             facet_search: Setting::NotSet,
             prefix_search: Setting::NotSet,
-            chat: Setting::NotSet,
             _kind: std::marker::PhantomData,
         };
         settings.check()
     }
 
-    pub fn create_test_batches() -> Vec<Batch> {
-        vec![Batch {
-            uid: 0,
-            details: DetailsView {
-                received_documents: Some(12),
-                indexed_documents: Some(Some(10)),
-                ..DetailsView::default()
-            },
-            progress: None,
-            stats: BatchStats {
-                total_nb_tasks: 1,
-                status: maplit::btreemap! { Status::Succeeded => 1 },
-                types: maplit::btreemap! { Kind::DocumentAdditionOrUpdate => 1 },
-                index_uids: maplit::btreemap! { "doggo".to_string() => 1 },
-                progress_trace: Default::default(),
-                write_channel_congestion: None,
-                internal_database_sizes: Default::default(),
-            },
-            embedder_stats: Default::default(),
-            enqueued_at: Some(BatchEnqueuedAt {
-                earliest: datetime!(2022-11-11 0:00 UTC),
-                oldest: datetime!(2022-11-11 0:00 UTC),
-            }),
-            started_at: datetime!(2022-11-20 0:00 UTC),
-            finished_at: Some(datetime!(2022-11-21 0:00 UTC)),
-            stop_reason: BatchStopReason::Unspecified.to_string(),
-        }]
-    }
-
     pub fn create_test_tasks() -> Vec<(TaskDump, Option<Vec<Document>>)> {
         vec![
             (
@@ -482,15 +421,6 @@ pub(crate) mod test {
         index.flush().unwrap();
         index.settings(&settings).unwrap();
 
-        // ========== pushing the batch queue
-        let batches = create_test_batches();
-
-        let mut batch_queue = dump.create_batches_queue().unwrap();
-        for batch in &batches {
-            batch_queue.push_batch(batch).unwrap();
-        }
-        batch_queue.flush().unwrap();
-
         // ========== pushing the task queue
         let tasks = create_test_tasks();
 
@@ -519,10 +449,6 @@ pub(crate) mod test {
 
         dump.create_experimental_features(features).unwrap();
 
-        // ========== network
-        let network = create_test_network();
-        dump.create_network(network).unwrap();
-
         // create the dump
         let mut file = tempfile::tempfile().unwrap();
         dump.persist_to(&mut file).unwrap();
@@ -535,13 +461,6 @@ pub(crate) mod test {
         RuntimeTogglableFeatures::default()
     }
 
-    fn create_test_network() -> Network {
-        Network {
-            local: Some("myself".to_string()),
-            remotes: maplit::btreemap! {"other".to_string() => Remote { url: "http://test".to_string(), search_api_key: Some("apiKey".to_string()) }},
-        }
-    }
-
     #[test]
     fn test_creating_and_read_dump() {
         let mut file = create_test_dump();
@@ -590,9 +509,5 @@ pub(crate) mod test {
         // ==== checking the features
         let expected = create_test_features();
         assert_eq!(dump.features().unwrap().unwrap(), expected);
-
-        // ==== checking the network
-        let expected = create_test_network();
-        assert_eq!(&expected, dump.network().unwrap().unwrap());
     }
 }

crates/dump/src/reader/compat/v5_to_v6.rs

@@ -1,4 +1,3 @@
-use std::num::NonZeroUsize;
 use std::str::FromStr;
 
 use super::v4_to_v5::{CompatIndexV4ToV5, CompatV4ToV5};
@@ -197,10 +196,6 @@ impl CompatV5ToV6 {
     pub fn features(&self) -> Result<Option<v6::RuntimeTogglableFeatures>> {
         Ok(None)
     }
-
-    pub fn network(&self) -> Result<Option<&v6::Network>> {
-        Ok(None)
-    }
 }
 
 pub enum CompatIndexV5ToV6 {
@@ -323,16 +318,7 @@ impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
         v6::Settings {
             displayed_attributes: v6::Setting::from(settings.displayed_attributes).into(),
             searchable_attributes: v6::Setting::from(settings.searchable_attributes).into(),
-            filterable_attributes: match settings.filterable_attributes {
+            filterable_attributes: settings.filterable_attributes.into(),
-                v5::settings::Setting::Set(filterable_attributes) => v6::Setting::Set(
-                    filterable_attributes
-                        .into_iter()
-                        .map(v6::FilterableAttributesRule::Field)
-                        .collect(),
-                ),
-                v5::settings::Setting::Reset => v6::Setting::Reset,
-                v5::settings::Setting::NotSet => v6::Setting::NotSet,
-            },
             sortable_attributes: settings.sortable_attributes.into(),
             ranking_rules: {
                 match settings.ranking_rules {
@@ -374,7 +360,6 @@ impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
                     },
                     disable_on_words: typo.disable_on_words.into(),
                     disable_on_attributes: typo.disable_on_attributes.into(),
-                    disable_on_numbers: v6::Setting::NotSet,
                 }),
                 v5::Setting::Reset => v6::Setting::Reset,
                 v5::Setting::NotSet => v6::Setting::NotSet,
@@ -389,13 +374,7 @@ impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
             },
             pagination: match settings.pagination {
                 v5::Setting::Set(pagination) => v6::Setting::Set(v6::PaginationSettings {
-                    max_total_hits: match pagination.max_total_hits {
+                    max_total_hits: pagination.max_total_hits.into(),
-                        v5::Setting::Set(max_total_hits) => v6::Setting::Set(
-                            max_total_hits.try_into().unwrap_or(NonZeroUsize::new(1).unwrap()),
-                        ),
-                        v5::Setting::Reset => v6::Setting::Reset,
-                        v5::Setting::NotSet => v6::Setting::NotSet,
-                    },
                 }),
                 v5::Setting::Reset => v6::Setting::Reset,
                 v5::Setting::NotSet => v6::Setting::NotSet,
@@ -405,7 +384,6 @@ impl<T> From<v5::Settings<T>> for v6::Settings<v6::Unchecked> {
             search_cutoff_ms: v6::Setting::NotSet,
             facet_search: v6::Setting::NotSet,
             prefix_search: v6::Setting::NotSet,
-            chat: v6::Setting::NotSet,
             _kind: std::marker::PhantomData,
         }
     }

crates/dump/src/reader/mod.rs

@@ -23,7 +23,6 @@ mod v6;
 pub type Document = serde_json::Map<String, serde_json::Value>;
 pub type UpdateFile = dyn Iterator<Item = Result<Document>>;
 
-#[allow(clippy::large_enum_variant)]
 pub enum DumpReader {
     Current(V6Reader),
     Compat(CompatV5ToV6),
@@ -102,13 +101,6 @@ impl DumpReader {
         }
     }
 
-    pub fn batches(&mut self) -> Result<Box<dyn Iterator<Item = Result<v6::Batch>> + '_>> {
-        match self {
-            DumpReader::Current(current) => Ok(current.batches()),
-            DumpReader::Compat(_compat) => Ok(Box::new(std::iter::empty())),
-        }
-    }
-
     pub fn keys(&mut self) -> Result<Box<dyn Iterator<Item = Result<v6::Key>> + '_>> {
         match self {
             DumpReader::Current(current) => Ok(current.keys()),
@@ -116,28 +108,12 @@ impl DumpReader {
         }
     }
 
-    pub fn chat_completions_settings(
-        &mut self,
-    ) -> Result<Box<dyn Iterator<Item = Result<(String, v6::ChatCompletionSettings)>> + '_>> {
-        match self {
-            DumpReader::Current(current) => current.chat_completions_settings(),
-            DumpReader::Compat(_compat) => Ok(Box::new(std::iter::empty())),
-        }
-    }
-
     pub fn features(&self) -> Result<Option<v6::RuntimeTogglableFeatures>> {
         match self {
             DumpReader::Current(current) => Ok(current.features()),
             DumpReader::Compat(compat) => compat.features(),
         }
     }
-
-    pub fn network(&self) -> Result<Option<&v6::Network>> {
-        match self {
-            DumpReader::Current(current) => Ok(current.network()),
-            DumpReader::Compat(compat) => compat.network(),
-        }
-    }
 }
 
 impl From<V6Reader> for DumpReader {
@@ -243,10 +219,6 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2024-05-16 15:51:34.151044 +00:00:00");
         insta::assert_debug_snapshot!(dump.instance_uid().unwrap(), @"None");
 
-        // batches didn't exists at the time
-        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
-        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
-
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -356,7 +328,6 @@ pub(crate) mod test {
         }
 
         assert_eq!(dump.features().unwrap().unwrap(), RuntimeTogglableFeatures::default());
-        assert_eq!(dump.network().unwrap(), None);
     }
 
     #[test]
@@ -368,10 +339,6 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2023-07-06 7:10:27.21958 +00:00:00");
         insta::assert_debug_snapshot!(dump.instance_uid().unwrap(), @"None");
 
-        // batches didn't exists at the time
-        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
-        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
-
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -406,27 +373,6 @@ pub(crate) mod test {
         assert_eq!(dump.features().unwrap().unwrap(), RuntimeTogglableFeatures::default());
     }
 
-    #[test]
-    fn import_dump_v6_network() {
-        let dump = File::open("tests/assets/v6-with-network.dump").unwrap();
-        let dump = DumpReader::open(dump).unwrap();
-
-        // top level infos
-        insta::assert_snapshot!(dump.date().unwrap(), @"2025-01-29 15:45:32.738676 +00:00:00");
-        insta::assert_debug_snapshot!(dump.instance_uid().unwrap(), @"None");
-
-        // network
-
-        let network = dump.network().unwrap().unwrap();
-        insta::assert_snapshot!(network.local.as_ref().unwrap(), @"ms-0");
-        insta::assert_snapshot!(network.remotes.get("ms-0").as_ref().unwrap().url, @"http://localhost:7700");
-        insta::assert_snapshot!(network.remotes.get("ms-0").as_ref().unwrap().search_api_key.is_none(), @"true");
-        insta::assert_snapshot!(network.remotes.get("ms-1").as_ref().unwrap().url, @"http://localhost:7701");
-        insta::assert_snapshot!(network.remotes.get("ms-1").as_ref().unwrap().search_api_key.is_none(), @"true");
-        insta::assert_snapshot!(network.remotes.get("ms-2").as_ref().unwrap().url, @"http://ms-5679.example.meilisearch.io");
-        insta::assert_snapshot!(network.remotes.get("ms-2").as_ref().unwrap().search_api_key.as_ref().unwrap(), @"foo");
-    }
-
     #[test]
     fn import_dump_v5() {
         let dump = File::open("tests/assets/v5.dump").unwrap();
@@ -436,10 +382,6 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-04 15:55:10.344982459 +00:00:00");
         insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
 
-        // batches didn't exists at the time
-        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
-        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
-
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -520,10 +462,6 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-06 12:53:49.131989609 +00:00:00");
         insta::assert_snapshot!(dump.instance_uid().unwrap().unwrap(), @"9e15e977-f2ae-4761-943f-1eaf75fd736d");
 
-        // batches didn't exists at the time
-        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
-        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
-
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -601,10 +539,6 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-07 11:39:03.709153554 +00:00:00");
         assert_eq!(dump.instance_uid().unwrap(), None);
 
-        // batches didn't exists at the time
-        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
-        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
-
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -698,10 +632,6 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2022-10-09 20:27:59.904096267 +00:00:00");
         assert_eq!(dump.instance_uid().unwrap(), None);
 
-        // batches didn't exists at the time
-        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
-        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
-
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -795,10 +725,6 @@ pub(crate) mod test {
         insta::assert_snapshot!(dump.date().unwrap(), @"2023-01-30 16:26:09.247261 +00:00:00");
         assert_eq!(dump.instance_uid().unwrap(), None);
 
-        // batches didn't exists at the time
-        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
-        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
-
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();
@@ -875,10 +801,6 @@ pub(crate) mod test {
         assert_eq!(dump.date(), None);
         assert_eq!(dump.instance_uid().unwrap(), None);
 
-        // batches didn't exists at the time
-        let batches = dump.batches().unwrap().collect::<Result<Vec<_>>>().unwrap();
-        meili_snap::snapshot!(meili_snap::json_string!(batches), @"[]");
-
         // tasks
         let tasks = dump.tasks().unwrap().collect::<Result<Vec<_>>>().unwrap();
         let (tasks, update_files): (Vec<_>, Vec<_>) = tasks.into_iter().unzip();

crates/dump/src/reader/snapshots/dump__reader__test__import_dump_v6_with_vectors-5.snap

@@ -1,5 +1,5 @@
 ---
-source: crates/dump/src/reader/mod.rs
+source: dump/src/reader/mod.rs
 expression: vector_index.settings().unwrap()
 ---
 {
@@ -49,7 +49,6 @@ expression: vector_index.settings().unwrap()
       "source": "huggingFace",
       "model": "BAAI/bge-base-en-v1.5",
       "revision": "617ca489d9e86b49b8167676d8220688b99db36e",
-      "pooling": "forceMean",
       "documentTemplate": "{% for field in fields %} {{ field.name }}: {{ field.value }}\n{% endfor %}"
     }
   },

crates/dump/src/reader/v4/meta.rs

@@ -108,7 +108,7 @@ where
         /// not supported on untagged enums.
         struct StarOrVisitor<T>(PhantomData<T>);
 
-        impl<T, FE> Visitor<'_> for StarOrVisitor<T>
+        impl<'de, T, FE> Visitor<'de> for StarOrVisitor<T>
         where
             T: FromStr<Err = FE>,
             FE: Display,

crates/dump/src/reader/v4/tasks.rs

@@ -99,7 +99,7 @@ impl Task {
     /// Return true when a task is finished.
     /// A task is finished when its last state is either `Succeeded` or `Failed`.
     pub fn is_finished(&self) -> bool {
-        self.events.last().is_some_and(|event| {
+        self.events.last().map_or(false, |event| {
             matches!(event, TaskEvent::Succeded { .. } | TaskEvent::Failed { .. })
         })
     }

crates/dump/src/reader/v5/meta.rs

@@ -108,7 +108,7 @@ where
         /// not supported on untagged enums.
         struct StarOrVisitor<T>(PhantomData<T>);
 
-        impl<T, FE> Visitor<'_> for StarOrVisitor<T>
+        impl<'de, T, FE> Visitor<'de> for StarOrVisitor<T>
         where
             T: FromStr<Err = FE>,
             FE: Display,

crates/dump/src/reader/v5/tasks.rs

@@ -114,7 +114,7 @@ impl Task {
     /// Return true when a task is finished.
     /// A task is finished when its last state is either `Succeeded` or `Failed`.
     pub fn is_finished(&self) -> bool {
-        self.events.last().is_some_and(|event| {
+        self.events.last().map_or(false, |event| {
             matches!(event, TaskEvent::Succeeded { .. } | TaskEvent::Failed { .. })
         })
     }

crates/dump/src/reader/v6/mod.rs

@@ -1,10 +1,8 @@
-use std::ffi::OsStr;
 use std::fs::{self, File};
 use std::io::{BufRead, BufReader, ErrorKind};
 use std::path::Path;
 
 pub use meilisearch_types::milli;
-use meilisearch_types::milli::vector::hf::OverridePooling;
 use tempfile::TempDir;
 use time::OffsetDateTime;
 use tracing::debug;
@@ -20,11 +18,8 @@ pub type Checked = meilisearch_types::settings::Checked;
 pub type Unchecked = meilisearch_types::settings::Unchecked;
 
 pub type Task = crate::TaskDump;
-pub type Batch = meilisearch_types::batches::Batch;
 pub type Key = meilisearch_types::keys::Key;
-pub type ChatCompletionSettings = meilisearch_types::features::ChatCompletionSettings;
 pub type RuntimeTogglableFeatures = meilisearch_types::features::RuntimeTogglableFeatures;
-pub type Network = meilisearch_types::features::Network;
 
 // ===== Other types to clarify the code of the compat module
 // everything related to the tasks
@@ -48,17 +43,13 @@ pub type ResponseError = meilisearch_types::error::ResponseError;
 pub type Code = meilisearch_types::error::Code;
 pub type RankingRuleView = meilisearch_types::settings::RankingRuleView;
 
-pub type FilterableAttributesRule = meilisearch_types::milli::FilterableAttributesRule;
-
 pub struct V6Reader {
     dump: TempDir,
     instance_uid: Option<Uuid>,
     metadata: Metadata,
     tasks: BufReader<File>,
-    batches: Option<BufReader<File>>,
     keys: BufReader<File>,
     features: Option<RuntimeTogglableFeatures>,
-    network: Option<Network>,
 }
 
 impl V6Reader {
@@ -86,38 +77,13 @@ impl V6Reader {
         } else {
             None
         };
-        let batches = match File::open(dump.path().join("batches").join("queue.jsonl")) {
-            Ok(file) => Some(BufReader::new(file)),
-            // The batch file was only introduced during the v1.13, anything prior to that won't have batches
-            Err(err) if err.kind() == ErrorKind::NotFound => None,
-            Err(e) => return Err(e.into()),
-        };
-
-        let network_file = match fs::read(dump.path().join("network.json")) {
-            Ok(network_file) => Some(network_file),
-            Err(error) => match error.kind() {
-                // Allows the file to be missing, this will only result in all experimental features disabled.
-                ErrorKind::NotFound => {
-                    debug!("`network.json` not found in dump");
-                    None
-                }
-                _ => return Err(error.into()),
-            },
-        };
-        let network = if let Some(network_file) = network_file {
-            Some(serde_json::from_reader(&*network_file)?)
-        } else {
-            None
-        };
 
         Ok(V6Reader {
             metadata: serde_json::from_reader(&*meta_file)?,
             instance_uid,
             tasks: BufReader::new(File::open(dump.path().join("tasks").join("queue.jsonl"))?),
-            batches,
             keys: BufReader::new(File::open(dump.path().join("keys.jsonl"))?),
             features,
-            network,
             dump,
         })
     }
@@ -158,7 +124,7 @@ impl V6Reader {
         &mut self,
     ) -> Box<dyn Iterator<Item = Result<(Task, Option<Box<super::UpdateFile>>)>> + '_> {
         Box::new((&mut self.tasks).lines().map(|line| -> Result<_> {
-            let task: Task = serde_json::from_str(&line?)?;
+            let task: Task = serde_json::from_str(&line?).unwrap();
 
             let update_file_path = self
                 .dump
@@ -170,7 +136,8 @@ impl V6Reader {
             if update_file_path.exists() {
                 Ok((
                     task,
-                    Some(Box::new(UpdateFile::new(&update_file_path)?) as Box<super::UpdateFile>),
+                    Some(Box::new(UpdateFile::new(&update_file_path).unwrap())
+                        as Box<super::UpdateFile>),
                 ))
             } else {
                 Ok((task, None))
@@ -178,57 +145,15 @@ impl V6Reader {
         }))
     }
 
-    pub fn batches(&mut self) -> Box<dyn Iterator<Item = Result<Batch>> + '_> {
-        match self.batches.as_mut() {
-            Some(batches) => Box::new((batches).lines().map(|line| -> Result<_> {
-                let batch = serde_json::from_str(&line?)?;
-                Ok(batch)
-            })),
-            None => Box::new(std::iter::empty()) as Box<dyn Iterator<Item = Result<Batch>> + '_>,
-        }
-    }
-
     pub fn keys(&mut self) -> Box<dyn Iterator<Item = Result<Key>> + '_> {
         Box::new(
             (&mut self.keys).lines().map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }),
         )
     }
 
-    pub fn chat_completions_settings(
-        &mut self,
-    ) -> Result<Box<dyn Iterator<Item = Result<(String, ChatCompletionSettings)>> + '_>> {
-        let entries = match fs::read_dir(self.dump.path().join("chat-completions-settings")) {
-            Ok(entries) => entries,
-            Err(e) if e.kind() == ErrorKind::NotFound => return Ok(Box::new(std::iter::empty())),
-            Err(e) => return Err(e.into()),
-        };
-        Ok(Box::new(
-            entries
-                .map(|entry| -> Result<Option<_>> {
-                    let entry = entry?;
-                    let file_name = entry.file_name();
-                    let path = Path::new(&file_name);
-                    if entry.file_type()?.is_file() && path.extension() == Some(OsStr::new("json"))
-                    {
-                        let name = path.file_stem().unwrap().to_str().unwrap().to_string();
-                        let file = File::open(entry.path())?;
-                        let settings = serde_json::from_reader(file)?;
-                        Ok(Some((name, settings)))
-                    } else {
-                        Ok(None)
-                    }
-                })
-                .filter_map(|entry| entry.transpose()),
-        ))
-    }
-
     pub fn features(&self) -> Option<RuntimeTogglableFeatures> {
         self.features
     }
-
-    pub fn network(&self) -> Option<&Network> {
-        self.network.as_ref()
-    }
 }
 
 pub struct UpdateFile {
@@ -285,29 +210,7 @@ impl V6IndexReader {
     }
 
     pub fn settings(&mut self) -> Result<Settings<Checked>> {
-        let mut settings: Settings<Unchecked> = serde_json::from_reader(&mut self.settings)?;
+        let settings: Settings<Unchecked> = serde_json::from_reader(&mut self.settings)?;
-        patch_embedders(&mut settings);
         Ok(settings.check())
     }
 }
-
-fn patch_embedders(settings: &mut Settings<Unchecked>) {
-    if let Setting::Set(embedders) = &mut settings.embedders {
-        for settings in embedders.values_mut() {
-            let Setting::Set(settings) = &mut settings.inner else {
-                continue;
-            };
-            if settings.source != Setting::Set(milli::vector::settings::EmbedderSource::HuggingFace)
-            {
-                continue;
-            }
-            settings.pooling = match settings.pooling {
-                Setting::Set(pooling) => Setting::Set(pooling),
-                // if the pooling for a hugging face embedder is not set, force it to `forceMean`
-                // for backward compatibility with v1.13
-                // dumps created in v1.14 and up will have the setting set for hugging face embedders
-                Setting::Reset | Setting::NotSet => Setting::Set(OverridePooling::ForceMean),
-            };
-        }
-    }
-}

crates/dump/src/writer.rs

@@ -4,8 +4,7 @@ use std::path::PathBuf;
 
 use flate2::write::GzEncoder;
 use flate2::Compression;
-use meilisearch_types::batches::Batch;
+use meilisearch_types::features::RuntimeTogglableFeatures;
-use meilisearch_types::features::{ChatCompletionSettings, Network, RuntimeTogglableFeatures};
 use meilisearch_types::keys::Key;
 use meilisearch_types::settings::{Checked, Settings};
 use serde_json::{Map, Value};
@@ -51,18 +50,10 @@ impl DumpWriter {
         KeyWriter::new(self.dir.path().to_path_buf())
     }
 
-    pub fn create_chat_completions_settings(&self) -> Result<ChatCompletionsSettingsWriter> {
-        ChatCompletionsSettingsWriter::new(self.dir.path().join("chat-completions-settings"))
-    }
-
     pub fn create_tasks_queue(&self) -> Result<TaskWriter> {
         TaskWriter::new(self.dir.path().join("tasks"))
     }
 
-    pub fn create_batches_queue(&self) -> Result<BatchWriter> {
-        BatchWriter::new(self.dir.path().join("batches"))
-    }
-
     pub fn create_experimental_features(&self, features: RuntimeTogglableFeatures) -> Result<()> {
         Ok(std::fs::write(
             self.dir.path().join("experimental-features.json"),
@@ -70,10 +61,6 @@ impl DumpWriter {
         )?)
     }
 
-    pub fn create_network(&self, network: Network) -> Result<()> {
-        Ok(std::fs::write(self.dir.path().join("network.json"), serde_json::to_string(&network)?)?)
-    }
-
     pub fn persist_to(self, mut writer: impl Write) -> Result<()> {
         let gz_encoder = GzEncoder::new(&mut writer, Compression::default());
         let mut tar_encoder = tar::Builder::new(gz_encoder);
@@ -97,7 +84,7 @@ impl KeyWriter {
     }
 
     pub fn push_key(&mut self, key: &Key) -> Result<()> {
-        serde_json::to_writer(&mut self.keys, &key)?;
+        self.keys.write_all(&serde_json::to_vec(key)?)?;
         self.keys.write_all(b"\n")?;
         Ok(())
     }
@@ -108,24 +95,6 @@ impl KeyWriter {
     }
 }
 
-pub struct ChatCompletionsSettingsWriter {
-    path: PathBuf,
-}
-
-impl ChatCompletionsSettingsWriter {
-    pub(crate) fn new(path: PathBuf) -> Result<Self> {
-        std::fs::create_dir(&path)?;
-        Ok(ChatCompletionsSettingsWriter { path })
-    }
-
-    pub fn push_settings(&mut self, name: &str, settings: &ChatCompletionSettings) -> Result<()> {
-        let mut settings_file = File::create(self.path.join(name).with_extension("json"))?;
-        serde_json::to_writer(&mut settings_file, &settings)?;
-        settings_file.flush()?;
-        Ok(())
-    }
-}
-
 pub struct TaskWriter {
     queue: BufWriter<File>,
     update_files: PathBuf,
@@ -145,7 +114,7 @@ impl TaskWriter {
     /// Pushes tasks in the dump.
     /// If the tasks has an associated `update_file` it'll use the `task_id` as its name.
     pub fn push_task(&mut self, task: &TaskDump) -> Result<UpdateFile> {
-        serde_json::to_writer(&mut self.queue, &task)?;
+        self.queue.write_all(&serde_json::to_vec(task)?)?;
         self.queue.write_all(b"\n")?;
 
         Ok(UpdateFile::new(self.update_files.join(format!("{}.jsonl", task.uid))))
@@ -157,30 +126,6 @@ impl TaskWriter {
     }
 }
 
-pub struct BatchWriter {
-    queue: BufWriter<File>,
-}
-
-impl BatchWriter {
-    pub(crate) fn new(path: PathBuf) -> Result<Self> {
-        std::fs::create_dir(&path)?;
-        let queue = File::create(path.join("queue.jsonl"))?;
-        Ok(BatchWriter { queue: BufWriter::new(queue) })
-    }
-
-    /// Pushes batches in the dump.
-    pub fn push_batch(&mut self, batch: &Batch) -> Result<()> {
-        serde_json::to_writer(&mut self.queue, &batch)?;
-        self.queue.write_all(b"\n")?;
-        Ok(())
-    }
-
-    pub fn flush(mut self) -> Result<()> {
-        self.queue.flush()?;
-        Ok(())
-    }
-}
-
 pub struct UpdateFile {
     path: PathBuf,
     writer: Option<BufWriter<File>>,
@@ -192,8 +137,8 @@ impl UpdateFile {
     }
 
     pub fn push_document(&mut self, document: &Document) -> Result<()> {
-        if let Some(mut writer) = self.writer.as_mut() {
+        if let Some(writer) = self.writer.as_mut() {
-            serde_json::to_writer(&mut writer, &document)?;
+            writer.write_all(&serde_json::to_vec(document)?)?;
             writer.write_all(b"\n")?;
         } else {
             let file = File::create(&self.path).unwrap();
@@ -260,8 +205,8 @@ pub(crate) mod test {
     use super::*;
     use crate::reader::Document;
     use crate::test::{
-        create_test_api_keys, create_test_batches, create_test_documents, create_test_dump,
+        create_test_api_keys, create_test_documents, create_test_dump, create_test_instance_uid,
-        create_test_instance_uid, create_test_settings, create_test_tasks,
+        create_test_settings, create_test_tasks,
     };
 
     fn create_directory_hierarchy(dir: &Path) -> String {
@@ -336,10 +281,8 @@ pub(crate) mod test {
         let dump_path = dump.path();
 
         // ==== checking global file hierarchy (we want to be sure there isn't too many files or too few)
-        insta::assert_snapshot!(create_directory_hierarchy(dump_path), @r"
+        insta::assert_snapshot!(create_directory_hierarchy(dump_path), @r###"
         .
-        ├---- batches/
-        │    └---- queue.jsonl
         ├---- indexes/
         │    └---- doggos/
         │    │    ├---- documents.jsonl
@@ -352,9 +295,8 @@ pub(crate) mod test {
         ├---- experimental-features.json
         ├---- instance_uid.uuid
         ├---- keys.jsonl
-        ├---- metadata.json
+        └---- metadata.json
-        └---- network.json
+        "###);
-        ");
 
         // ==== checking the top level infos
         let metadata = fs::read_to_string(dump_path.join("metadata.json")).unwrap();
@@ -407,16 +349,6 @@ pub(crate) mod test {
             }
         }
 
-        // ==== checking the batch queue
-        let batches_queue = fs::read_to_string(dump_path.join("batches/queue.jsonl")).unwrap();
-        for (batch, expected) in batches_queue.lines().zip(create_test_batches()) {
-            let mut batch = serde_json::from_str::<Batch>(batch).unwrap();
-            if batch.details.settings == Some(Box::new(Settings::<Unchecked>::default())) {
-                batch.details.settings = None;
-            }
-            assert_eq!(batch, expected, "{batch:#?}{expected:#?}");
-        }
-
         // ==== checking the keys
         let keys = fs::read_to_string(dump_path.join("keys.jsonl")).unwrap();
         for (key, expected) in keys.lines().zip(create_test_api_keys()) {

crates/file-store/Cargo.toml

@@ -11,7 +11,7 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-tempfile = "3.20.0"
+tempfile = "3.15.0"
-thiserror = "2.0.12"
+thiserror = "2.0.9"
 tracing = "0.1.41"
-uuid = { version = "1.17.0", features = ["serde", "v4"] }
+uuid = { version = "1.11.0", features = ["serde", "v4"] }

crates/filter-parser/Cargo.toml

@@ -14,7 +14,7 @@ license.workspace = true
 [dependencies]
 nom = "7.1.3"
 nom_locate = "4.2.0"
-unescaper = "0.1.6"
+unescaper = "0.1.5"
 
 [dev-dependencies]
 # fixed version due to format breakages in v1.40

crates/filter-parser/src/condition.rs

@@ -30,25 +30,6 @@ pub enum Condition<'a> {
     StartsWith { keyword: Token<'a>, word: Token<'a> },
 }
 
-impl Condition<'_> {
-    pub fn operator(&self) -> &str {
-        match self {
-            Condition::GreaterThan(_) => ">",
-            Condition::GreaterThanOrEqual(_) => ">=",
-            Condition::Equal(_) => "=",
-            Condition::NotEqual(_) => "!=",
-            Condition::Null => "IS NULL",
-            Condition::Empty => "IS EMPTY",
-            Condition::Exists => "EXISTS",
-            Condition::LowerThan(_) => "<",
-            Condition::LowerThanOrEqual(_) => "<=",
-            Condition::Between { .. } => "TO",
-            Condition::Contains { .. } => "CONTAINS",
-            Condition::StartsWith { .. } => "STARTS WITH",
-        }
-    }
-}
-
 /// condition      = value ("==" | ">" ...) value
 pub fn parse_condition(input: Span) -> IResult<FilterCondition> {
     let operator = alt((tag("<="), tag(">="), tag("!="), tag("<"), tag(">"), tag("=")));

crates/filter-parser/src/error.rs

@@ -35,7 +35,7 @@ impl<E> NomErrorExt<E> for nom::Err<E> {
 pub fn cut_with_err<'a, O>(
     mut parser: impl FnMut(Span<'a>) -> IResult<'a, O>,
     mut with: impl FnMut(Error<'a>) -> Error<'a>,
-) -> impl FnMut(Span<'a>) -> IResult<'a, O> {
+) -> impl FnMut(Span<'a>) -> IResult<O> {
     move |input| match parser.parse(input) {
         Err(nom::Err::Error(e)) => Err(nom::Err::Failure(with(e))),
         rest => rest,
@@ -121,7 +121,7 @@ impl<'a> ParseError<Span<'a>> for Error<'a> {
     }
 }
 
-impl Display for Error<'_> {
+impl<'a> Display for Error<'a> {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         let input = self.context.fragment();
         // When printing our error message we want to escape all `\n` to be sure we keep our format with the

crates/filter-parser/src/lib.rs

@@ -80,7 +80,7 @@ pub struct Token<'a> {
     value: Option<String>,
 }
 
-impl PartialEq for Token<'_> {
+impl<'a> PartialEq for Token<'a> {
     fn eq(&self, other: &Self) -> bool {
         self.span.fragment() == other.span.fragment()
     }
@@ -226,7 +226,7 @@ impl<'a> FilterCondition<'a> {
         }
     }
 
-    pub fn parse(input: &'a str) -> Result<Option<Self>, Error<'a>> {
+    pub fn parse(input: &'a str) -> Result<Option<Self>, Error> {
         if input.trim().is_empty() {
             return Ok(None);
         }
@@ -527,7 +527,7 @@ pub fn parse_filter(input: Span) -> IResult<FilterCondition> {
     terminated(|input| parse_expression(input, 0), eof)(input)
 }
 
-impl std::fmt::Display for FilterCondition<'_> {
+impl<'a> std::fmt::Display for FilterCondition<'a> {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         match self {
             FilterCondition::Not(filter) => {
@@ -576,8 +576,7 @@ impl std::fmt::Display for FilterCondition<'_> {
         }
     }
 }
-
+impl<'a> std::fmt::Display for Condition<'a> {
-impl std::fmt::Display for Condition<'_> {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         match self {
             Condition::GreaterThan(token) => write!(f, "> {token}"),
@@ -595,8 +594,7 @@ impl std::fmt::Display for Condition<'_> {
         }
     }
 }
-
+impl<'a> std::fmt::Display for Token<'a> {
-impl std::fmt::Display for Token<'_> {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         write!(f, "{{{}}}", self.value())
     }

crates/filter-parser/src/value.rs

@@ -52,7 +52,7 @@ fn quoted_by(quote: char, input: Span) -> IResult<Token> {
 }
 
 // word           = (alphanumeric | _ | - | .)+    except for reserved keywords
-pub fn word_not_keyword<'a>(input: Span<'a>) -> IResult<'a, Token<'a>> {
+pub fn word_not_keyword<'a>(input: Span<'a>) -> IResult<Token<'a>> {
     let (input, word): (_, Token<'a>) =
         take_while1(is_value_component)(input).map(|(s, t)| (s, t.into()))?;
     if is_keyword(word.value()) {

crates/flatten-serde-json/Cargo.toml

@@ -16,7 +16,7 @@ license.workspace = true
 serde_json = "1.0"
 
 [dev-dependencies]
-criterion = { version = "0.6.0", features = ["html_reports"] }
+criterion = { version = "0.5.1", features = ["html_reports"] }
 
 [[bench]]
 name = "benchmarks"

crates/fuzzers/Cargo.toml

@@ -12,11 +12,11 @@ license.workspace = true
 
 [dependencies]
 arbitrary = { version = "1.4.1", features = ["derive"] }
-bumpalo = "3.18.1"
+bumpalo = "3.16.0"
-clap = { version = "4.5.40", features = ["derive"] }
+clap = { version = "4.5.24", features = ["derive"] }
-either = "1.15.0"
+either = "1.13.0"
 fastrand = "2.3.0"
 milli = { path = "../milli" }
-serde = { version = "1.0.219", features = ["derive"] }
+serde = { version = "1.0.217", features = ["derive"] }
-serde_json = { version = "1.0.140", features = ["preserve_order"] }
+serde_json = { version = "1.0.135", features = ["preserve_order"] }
-tempfile = "3.20.0"
+tempfile = "3.15.0"

crates/fuzzers/src/bin/fuzz-indexing.rs

@@ -12,8 +12,8 @@ use milli::documents::mmap_from_objects;
 use milli::heed::EnvOpenOptions;
 use milli::progress::Progress;
 use milli::update::new::indexer;
-use milli::update::IndexerConfig;
+use milli::update::{IndexDocumentsMethod, IndexerConfig};
-use milli::vector::RuntimeEmbedders;
+use milli::vector::EmbeddingConfigs;
 use milli::Index;
 use serde_json::Value;
 use tempfile::TempDir;
@@ -57,14 +57,13 @@ fn main() {
         let opt = opt.clone();
 
         let handle = std::thread::spawn(move || {
-            let options = EnvOpenOptions::new();
+            let mut options = EnvOpenOptions::new();
-            let mut options = options.read_txn_without_tls();
             options.map_size(1024 * 1024 * 1024 * 1024);
             let tempdir = match opt.path {
                 Some(path) => TempDir::new_in(path).unwrap(),
                 None => TempDir::new().unwrap(),
             };
-            let index = Index::new(options, tempdir.path(), true).unwrap();
+            let index = Index::new(options, tempdir.path()).unwrap();
             let indexer_config = IndexerConfig::default();
 
             std::thread::scope(|s| {
@@ -89,8 +88,10 @@ fn main() {
                             let mut new_fields_ids_map = db_fields_ids_map.clone();
 
                             let indexer_alloc = Bump::new();
-                            let embedders = RuntimeEmbedders::default();
+                            let embedders = EmbeddingConfigs::default();
-                            let mut indexer = indexer::DocumentOperation::new();
+                            let mut indexer = indexer::DocumentOperation::new(
+                                IndexDocumentsMethod::ReplaceDocuments,
+                            );
 
                             let mut operations = Vec::new();
                             for op in batch.0 {
@@ -114,7 +115,7 @@ fn main() {
                             for op in &operations {
                                 match op {
                                     Either::Left(documents) => {
-                                        indexer.replace_documents(documents).unwrap()
+                                        indexer.add_documents(documents).unwrap()
                                     }
                                     Either::Right(ids) => indexer.delete_documents(ids),
                                 }
@@ -144,13 +145,12 @@ fn main() {
                                 embedders,
                                 &|| false,
                                 &Progress::default(),
-                                &Default::default(),
                             )
                             .unwrap();
 
                             // after executing a batch we check if the database is corrupted
                             let res = index.search(&wtxn).execute().unwrap();
-                            index.documents(&wtxn, res.documents_ids).unwrap();
+                            index.compressed_documents(&wtxn, res.documents_ids).unwrap();
                             progression.fetch_add(1, Ordering::Relaxed);
                         }
                         wtxn.abort();

crates/index-scheduler/Cargo.toml

@@ -11,31 +11,29 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.98"
+anyhow = "1.0.95"
 bincode = "1.3.3"
-byte-unit = "5.1.6"
+bumpalo = "3.16.0"
-bumpalo = "3.18.1"
 bumparaw-collections = "0.1.4"
-convert_case = "0.8.0"
+convert_case = "0.6.0"
 csv = "1.3.1"
 derive_builder = "0.20.2"
 dump = { path = "../dump" }
 enum-iterator = "2.1.0"
 file-store = { path = "../file-store" }
-flate2 = "1.1.2"
+flate2 = "1.0.35"
-indexmap = "2.9.0"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
 memmap2 = "0.9.5"
 page_size = "0.6.0"
 rayon = "1.10.0"
-roaring = { version = "0.10.12", features = ["serde"] }
+roaring = { version = "0.10.10", features = ["serde"] }
-serde = { version = "1.0.219", features = ["derive"] }
+serde = { version = "1.0.217", features = ["derive"] }
-serde_json = { version = "1.0.140", features = ["preserve_order"] }
+serde_json = { version = "1.0.135", features = ["preserve_order"] }
 synchronoise = "1.0.1"
-tempfile = "3.20.0"
+tempfile = "3.15.0"
-thiserror = "2.0.12"
+thiserror = "2.0.9"
-time = { version = "0.3.41", features = [
+time = { version = "0.3.37", features = [
     "serde-well-known",
     "formatting",
     "parsing",
@@ -43,12 +41,12 @@ time = { version = "0.3.41", features = [
 ] }
 tracing = "0.1.41"
 ureq = "2.12.1"
-uuid = { version = "1.17.0", features = ["serde", "v4"] }
+uuid = { version = "1.11.0", features = ["serde", "v4"] }
-backoff = "0.4.0"
 
 [dev-dependencies]
+arroy = "0.5.0"
 big_s = "1.0.2"
-crossbeam-channel = "0.5.15"
+crossbeam-channel = "0.5.14"
 # fixed version due to format breakages in v1.40
 insta = { version = "=1.39.0", features = ["json", "redactions"] }
 maplit = "1.0.2"

crates/index-scheduler/src/dump.rs

@@ -1,11 +1,8 @@
 use std::collections::HashMap;
-use std::io;
 
 use dump::{KindDump, TaskDump, UpdateFile};
-use meilisearch_types::batches::{Batch, BatchId};
 use meilisearch_types::heed::RwTxn;
-use meilisearch_types::index_uid_pattern::IndexUidPattern;
+use meilisearch_types::milli::documents::DocumentsBatchBuilder;
-use meilisearch_types::milli;
 use meilisearch_types::tasks::{Kind, KindWithContent, Status, Task};
 use roaring::RoaringBitmap;
 use uuid::Uuid;
@@ -16,15 +13,9 @@ pub struct Dump<'a> {
     index_scheduler: &'a IndexScheduler,
     wtxn: RwTxn<'a>,
 
-    batch_to_task_mapping: HashMap<BatchId, RoaringBitmap>,
-
     indexes: HashMap<String, RoaringBitmap>,
     statuses: HashMap<Status, RoaringBitmap>,
     kinds: HashMap<Kind, RoaringBitmap>,
-
-    batch_indexes: HashMap<String, RoaringBitmap>,
-    batch_statuses: HashMap<Status, RoaringBitmap>,
-    batch_kinds: HashMap<Kind, RoaringBitmap>,
 }
 
 impl<'a> Dump<'a> {
@@ -35,72 +26,12 @@ impl<'a> Dump<'a> {
         Ok(Dump {
             index_scheduler,
             wtxn,
-            batch_to_task_mapping: HashMap::new(),
             indexes: HashMap::new(),
             statuses: HashMap::new(),
             kinds: HashMap::new(),
-            batch_indexes: HashMap::new(),
-            batch_statuses: HashMap::new(),
-            batch_kinds: HashMap::new(),
         })
     }
 
-    /// Register a new batch coming from a dump in the scheduler.
-    /// By taking a mutable ref we're pretty sure no one will ever import a dump while actix is running.
-    pub fn register_dumped_batch(&mut self, batch: Batch) -> Result<()> {
-        self.index_scheduler.queue.batches.all_batches.put(&mut self.wtxn, &batch.uid, &batch)?;
-        if let Some(enqueued_at) = batch.enqueued_at {
-            utils::insert_task_datetime(
-                &mut self.wtxn,
-                self.index_scheduler.queue.batches.enqueued_at,
-                enqueued_at.earliest,
-                batch.uid,
-            )?;
-            utils::insert_task_datetime(
-                &mut self.wtxn,
-                self.index_scheduler.queue.batches.enqueued_at,
-                enqueued_at.oldest,
-                batch.uid,
-            )?;
-        }
-        utils::insert_task_datetime(
-            &mut self.wtxn,
-            self.index_scheduler.queue.batches.started_at,
-            batch.started_at,
-            batch.uid,
-        )?;
-        if let Some(finished_at) = batch.finished_at {
-            utils::insert_task_datetime(
-                &mut self.wtxn,
-                self.index_scheduler.queue.batches.finished_at,
-                finished_at,
-                batch.uid,
-            )?;
-        }
-
-        for index in batch.stats.index_uids.keys() {
-            match self.batch_indexes.get_mut(index) {
-                Some(bitmap) => {
-                    bitmap.insert(batch.uid);
-                }
-                None => {
-                    let mut bitmap = RoaringBitmap::new();
-                    bitmap.insert(batch.uid);
-                    self.batch_indexes.insert(index.to_string(), bitmap);
-                }
-            };
-        }
-
-        for status in batch.stats.status.keys() {
-            self.batch_statuses.entry(*status).or_default().insert(batch.uid);
-        }
-        for kind in batch.stats.types.keys() {
-            self.batch_kinds.entry(*kind).or_default().insert(batch.uid);
-        }
-
-        Ok(())
-    }
-
     /// Register a new task coming from a dump in the scheduler.
     /// By taking a mutable ref we're pretty sure no one will ever import a dump while actix is running.
     pub fn register_dumped_task(
@@ -108,19 +39,14 @@ impl<'a> Dump<'a> {
         task: TaskDump,
         content_file: Option<Box<UpdateFile>>,
     ) -> Result<Task> {
-        let task_has_no_docs = matches!(task.kind, KindDump::DocumentImport { documents_count, .. } if documents_count == 0);
-
         let content_uuid = match content_file {
             Some(content_file) if task.status == Status::Enqueued => {
-                let (uuid, file) = self.index_scheduler.queue.create_update_file(false)?;
+                let (uuid, mut file) = self.index_scheduler.queue.create_update_file(false)?;
-                let mut writer = io::BufWriter::new(file);
+                let mut builder = DocumentsBatchBuilder::new(&mut file);
                 for doc in content_file {
-                    let doc = doc?;
+                    builder.append_json_object(&doc?)?;
-                    serde_json::to_writer(&mut writer, &doc).map_err(|e| {
-                        Error::from_milli(milli::InternalError::SerdeJson(e).into(), None)
-                    })?;
                 }
-                let file = writer.into_inner().map_err(|e| e.into_error())?;
+                builder.into_inner()?;
                 file.persist()?;
 
                 Some(uuid)
@@ -128,12 +54,6 @@ impl<'a> Dump<'a> {
             // If the task isn't `Enqueued` then just generate a recognisable `Uuid`
             // in case we try to open it later.
             _ if task.status != Status::Enqueued => Some(Uuid::nil()),
-            None if task.status == Status::Enqueued && task_has_no_docs => {
-                let (uuid, file) = self.index_scheduler.queue.create_update_file(false)?;
-                file.persist()?;
-
-                Some(uuid)
-            }
             _ => None,
         };
 
@@ -212,31 +132,10 @@ impl<'a> Dump<'a> {
                     KindWithContent::DumpCreation { keys, instance_uid }
                 }
                 KindDump::SnapshotCreation => KindWithContent::SnapshotCreation,
-                KindDump::Export { url, api_key, payload_size, indexes } => {
-                    KindWithContent::Export {
-                        url,
-                        api_key,
-                        payload_size,
-                        indexes: indexes
-                            .into_iter()
-                            .map(|(pattern, settings)| {
-                                Ok((
-                                    IndexUidPattern::try_from(pattern)
-                                        .map_err(|_| Error::CorruptedDump)?,
-                                    settings,
-                                ))
-                            })
-                            .collect::<Result<_, Error>>()?,
-                    }
-                }
-                KindDump::UpgradeDatabase { from } => KindWithContent::UpgradeDatabase { from },
             },
         };
 
         self.index_scheduler.queue.tasks.all_tasks.put(&mut self.wtxn, &task.uid, &task)?;
-        if let Some(batch_id) = task.batch_uid {
-            self.batch_to_task_mapping.entry(batch_id).or_default().insert(task.uid);
-        }
 
         for index in task.indexes() {
             match self.indexes.get_mut(index) {
@@ -286,14 +185,6 @@ impl<'a> Dump<'a> {
 
     /// Commit all the changes and exit the importing dump state
     pub fn finish(mut self) -> Result<()> {
-        for (batch_id, task_ids) in self.batch_to_task_mapping {
-            self.index_scheduler.queue.batch_to_tasks_mapping.put(
-                &mut self.wtxn,
-                &batch_id,
-                &task_ids,
-            )?;
-        }
-
         for (index, bitmap) in self.indexes {
             self.index_scheduler.queue.tasks.index_tasks.put(&mut self.wtxn, &index, &bitmap)?;
         }
@@ -304,16 +195,6 @@ impl<'a> Dump<'a> {
             self.index_scheduler.queue.tasks.put_kind(&mut self.wtxn, kind, &bitmap)?;
         }
 
-        for (index, bitmap) in self.batch_indexes {
-            self.index_scheduler.queue.batches.index_tasks.put(&mut self.wtxn, &index, &bitmap)?;
-        }
-        for (status, bitmap) in self.batch_statuses {
-            self.index_scheduler.queue.batches.put_status(&mut self.wtxn, status, &bitmap)?;
-        }
-        for (kind, bitmap) in self.batch_kinds {
-            self.index_scheduler.queue.batches.put_kind(&mut self.wtxn, kind, &bitmap)?;
-        }
-
         self.wtxn.commit()?;
         self.index_scheduler.scheduler.wake_up.signal();
 

crates/index-scheduler/src/error.rs

@@ -2,7 +2,6 @@ use std::fmt::Display;
 
 use meilisearch_types::batches::BatchId;
 use meilisearch_types::error::{Code, ErrorCode};
-use meilisearch_types::milli::index::RollbackOutcome;
 use meilisearch_types::tasks::{Kind, Status};
 use meilisearch_types::{heed, milli};
 use thiserror::Error;
@@ -110,8 +109,6 @@ pub enum Error {
     InvalidIndexUid { index_uid: String },
     #[error("Task `{0}` not found.")]
     TaskNotFound(TaskId),
-    #[error("Task `{0}` does not contain any documents. Only `documentAdditionOrUpdate` tasks with the statuses `enqueued` or `processing` contain documents")]
-    TaskFileNotFound(TaskId),
     #[error("Batch `{0}` not found.")]
     BatchNotFound(BatchId),
     #[error("Query parameters to filter the tasks to delete are missing. Available query parameters are: `uids`, `indexUids`, `statuses`, `types`, `canceledBy`, `beforeEnqueuedAt`, `afterEnqueuedAt`, `beforeStartedAt`, `afterStartedAt`, `beforeFinishedAt`, `afterFinishedAt`.")]
@@ -130,8 +127,8 @@ pub enum Error {
         _ => format!("{error}")
     })]
     Milli { error: milli::Error, index_uid: Option<String> },
-    #[error("An unexpected crash occurred when processing the task: {0}")]
+    #[error("An unexpected crash occurred when processing the task.")]
-    ProcessBatchPanicked(String),
+    ProcessBatchPanicked,
     #[error(transparent)]
     FileStore(#[from] file_store::Error),
     #[error(transparent)]
@@ -150,29 +147,7 @@ pub enum Error {
     #[error("Corrupted task queue.")]
     CorruptedTaskQueue,
     #[error(transparent)]
-    DatabaseUpgrade(Box<Self>),
+    TaskDatabaseUpdate(Box<Self>),
-    #[error(transparent)]
-    Export(Box<Self>),
-    #[error("Failed to export documents to remote server {code} ({type}): {message} <{link}>")]
-    FromRemoteWhenExporting { message: String, code: String, r#type: String, link: String },
-    #[error("Failed to rollback for index `{index}`: {rollback_outcome} ")]
-    RollbackFailed { index: String, rollback_outcome: RollbackOutcome },
-    #[error(transparent)]
-    UnrecoverableError(Box<Self>),
-    #[error("The index scheduler is in version v{}.{}.{}, but Meilisearch is in version v{}.{}.{}.\n  - hint: start the correct version of Meilisearch, or consider updating your database. See also <https://www.meilisearch.com/docs/learn/update_and_migration/updating>",
-    index_scheduler_version.0, index_scheduler_version.1, index_scheduler_version.2,
-    package_version.0, package_version.1, package_version.2)]
-    IndexSchedulerVersionMismatch {
-        index_scheduler_version: (u32, u32, u32),
-        package_version: (u32, u32, u32),
-    },
-    #[error("Index `{index}` is in version v{}.{}.{}, but Meilisearch is in version v{}.{}.{}.\n  - note: this is an internal error, please consider filing a bug report: <https://github.com/meilisearch/meilisearch/issues/new?template=bug_report.md>",
-    index_version.0, index_version.1, index_version.2, package_version.0, package_version.1, package_version.2)]
-    IndexVersionMismatch {
-        index: String,
-        index_version: (u32, u32, u32),
-        package_version: (u32, u32, u32),
-    },
     #[error(transparent)]
     HeedTransaction(heed::Error),
 
@@ -212,29 +187,22 @@ impl Error {
             | Error::InvalidTaskCanceledBy { .. }
             | Error::InvalidIndexUid { .. }
             | Error::TaskNotFound(_)
-            | Error::TaskFileNotFound(_)
             | Error::BatchNotFound(_)
             | Error::TaskDeletionWithEmptyQuery
             | Error::TaskCancelationWithEmptyQuery
-            | Error::FromRemoteWhenExporting { .. }
             | Error::AbortedTask
             | Error::Dump(_)
             | Error::Heed(_)
             | Error::Milli { .. }
-            | Error::ProcessBatchPanicked(_)
+            | Error::ProcessBatchPanicked
             | Error::FileStore(_)
             | Error::IoError(_)
             | Error::Persist(_)
             | Error::FeatureNotEnabled(_)
-            | Error::Export(_)
             | Error::Anyhow(_) => true,
             Error::CreateBatch(_)
             | Error::CorruptedTaskQueue
-            | Error::DatabaseUpgrade(_)
+            | Error::TaskDatabaseUpdate(_)
-            | Error::UnrecoverableError(_)
-            | Error::IndexSchedulerVersionMismatch { .. }
-            | Error::IndexVersionMismatch { .. }
-            | Error::RollbackFailed { .. }
             | Error::HeedTransaction(_) => false,
             #[cfg(test)]
             Error::PlannedFailure => false,
@@ -279,7 +247,6 @@ impl ErrorCode for Error {
             Error::InvalidTaskCanceledBy { .. } => Code::InvalidTaskCanceledBy,
             Error::InvalidIndexUid { .. } => Code::InvalidIndexUid,
             Error::TaskNotFound(_) => Code::TaskNotFound,
-            Error::TaskFileNotFound(_) => Code::TaskFileNotFound,
             Error::BatchNotFound(_) => Code::BatchNotFound,
             Error::TaskDeletionWithEmptyQuery => Code::MissingTaskFilters,
             Error::TaskCancelationWithEmptyQuery => Code::MissingTaskFilters,
@@ -287,8 +254,7 @@ impl ErrorCode for Error {
             Error::NoSpaceLeftInTaskQueue => Code::NoSpaceLeftOnDevice,
             Error::Dump(e) => e.error_code(),
             Error::Milli { error, .. } => error.error_code(),
-            Error::ProcessBatchPanicked(_) => Code::Internal,
+            Error::ProcessBatchPanicked => Code::Internal,
-            Error::FromRemoteWhenExporting { .. } => Code::Internal,
             Error::Heed(e) => e.error_code(),
             Error::HeedTransaction(e) => e.error_code(),
             Error::FileStore(e) => e.error_code(),
@@ -300,12 +266,7 @@ impl ErrorCode for Error {
             Error::Anyhow(_) => Code::Internal,
             Error::CorruptedTaskQueue => Code::Internal,
             Error::CorruptedDump => Code::Internal,
-            Error::DatabaseUpgrade(_) => Code::Internal,
+            Error::TaskDatabaseUpdate(_) => Code::Internal,
-            Error::Export(_) => Code::Internal,
-            Error::RollbackFailed { .. } => Code::Internal,
-            Error::UnrecoverableError(_) => Code::Internal,
-            Error::IndexSchedulerVersionMismatch { .. } => Code::Internal,
-            Error::IndexVersionMismatch { .. } => Code::Internal,
             Error::CreateBatch(_) => Code::Internal,
 
             // This one should never be seen by the end user

crates/index-scheduler/src/features.rs

@@ -1,29 +1,18 @@
 use std::sync::{Arc, RwLock};
 
-use meilisearch_types::features::{InstanceTogglableFeatures, Network, RuntimeTogglableFeatures};
+use meilisearch_types::features::{InstanceTogglableFeatures, RuntimeTogglableFeatures};
 use meilisearch_types::heed::types::{SerdeJson, Str};
-use meilisearch_types::heed::{Database, Env, RwTxn, WithoutTls};
+use meilisearch_types::heed::{Database, Env, RwTxn};
 
 use crate::error::FeatureNotEnabledError;
 use crate::Result;
 
-/// The number of database used by features
+const EXPERIMENTAL_FEATURES: &str = "experimental-features";
-const NUMBER_OF_DATABASES: u32 = 1;
-/// Database const names for the `FeatureData`.
-mod db_name {
-    pub const EXPERIMENTAL_FEATURES: &str = "experimental-features";
-}
-
-mod db_keys {
-    pub const EXPERIMENTAL_FEATURES: &str = "experimental-features";
-    pub const NETWORK: &str = "network";
-}
 
 #[derive(Clone)]
 pub(crate) struct FeatureData {
     persisted: Database<Str, SerdeJson<RuntimeTogglableFeatures>>,
     runtime: Arc<RwLock<RuntimeTogglableFeatures>>,
-    network: Arc<RwLock<Network>>,
 }
 
 #[derive(Debug, Clone, Copy)]
@@ -92,88 +81,17 @@ impl RoFeatures {
             .into())
         }
     }
-
-    pub fn check_network(&self, disabled_action: &'static str) -> Result<()> {
-        if self.runtime.network {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action,
-                feature: "network",
-                issue_link: "https://github.com/orgs/meilisearch/discussions/805",
-            }
-            .into())
-        }
-    }
-
-    pub fn check_get_task_documents_route(&self) -> Result<()> {
-        if self.runtime.get_task_documents_route {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action: "Getting the documents of an enqueued task",
-                feature: "get task documents route",
-                issue_link: "https://github.com/orgs/meilisearch/discussions/808",
-            }
-            .into())
-        }
-    }
-
-    pub fn check_composite_embedders(&self, disabled_action: &'static str) -> Result<()> {
-        if self.runtime.composite_embedders {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action,
-                feature: "composite embedders",
-                issue_link: "https://github.com/orgs/meilisearch/discussions/816",
-            }
-            .into())
-        }
-    }
-
-    pub fn check_chat_completions(&self, disabled_action: &'static str) -> Result<()> {
-        if self.runtime.chat_completions {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action,
-                feature: "chat completions",
-                issue_link: "https://github.com/orgs/meilisearch/discussions/835",
-            }
-            .into())
-        }
-    }
-
-    pub fn check_multimodal(&self, disabled_action: &'static str) -> Result<()> {
-        if self.runtime.multimodal {
-            Ok(())
-        } else {
-            Err(FeatureNotEnabledError {
-                disabled_action,
-                feature: "multimodal",
-                issue_link: "https://github.com/orgs/meilisearch/discussions/846",
-            }
-            .into())
-        }
-    }
 }
 
 impl FeatureData {
-    pub(crate) const fn nb_db() -> u32 {
+    pub fn new(env: &Env, instance_features: InstanceTogglableFeatures) -> Result<Self> {
-        NUMBER_OF_DATABASES
+        let mut wtxn = env.write_txn()?;
-    }
+        let runtime_features_db = env.create_database(&mut wtxn, Some(EXPERIMENTAL_FEATURES))?;
-
+        wtxn.commit()?;
-    pub fn new(
-        env: &Env<WithoutTls>,
-        wtxn: &mut RwTxn,
-        instance_features: InstanceTogglableFeatures,
-    ) -> Result<Self> {
-        let runtime_features_db =
-            env.create_database(wtxn, Some(db_name::EXPERIMENTAL_FEATURES))?;
 
+        let txn = env.read_txn()?;
         let persisted_features: RuntimeTogglableFeatures =
-            runtime_features_db.get(wtxn, db_keys::EXPERIMENTAL_FEATURES)?.unwrap_or_default();
+            runtime_features_db.get(&txn, EXPERIMENTAL_FEATURES)?.unwrap_or_default();
         let InstanceTogglableFeatures { metrics, logs_route, contains_filter } = instance_features;
         let runtime = Arc::new(RwLock::new(RuntimeTogglableFeatures {
             metrics: metrics || persisted_features.metrics,
@@ -182,14 +100,7 @@ impl FeatureData {
             ..persisted_features
         }));
 
-        let network_db = runtime_features_db.remap_data_type::<SerdeJson<Network>>();
+        Ok(Self { persisted: runtime_features_db, runtime })
-        let network: Network = network_db.get(wtxn, db_keys::NETWORK)?.unwrap_or_default();
-
-        Ok(Self {
-            persisted: runtime_features_db,
-            runtime,
-            network: Arc::new(RwLock::new(network)),
-        })
     }
 
     pub fn put_runtime_features(
@@ -197,7 +108,7 @@ impl FeatureData {
         mut wtxn: RwTxn,
         features: RuntimeTogglableFeatures,
     ) -> Result<()> {
-        self.persisted.put(&mut wtxn, db_keys::EXPERIMENTAL_FEATURES, &features)?;
+        self.persisted.put(&mut wtxn, EXPERIMENTAL_FEATURES, &features)?;
         wtxn.commit()?;
 
         // safe to unwrap, the lock will only fail if:
@@ -218,21 +129,4 @@ impl FeatureData {
     pub fn features(&self) -> RoFeatures {
         RoFeatures::new(self)
     }
-
-    pub fn put_network(&self, mut wtxn: RwTxn, new_network: Network) -> Result<()> {
-        self.persisted.remap_data_type::<SerdeJson<Network>>().put(
-            &mut wtxn,
-            db_keys::NETWORK,
-            &new_network,
-        )?;
-        wtxn.commit()?;
-
-        let mut network = self.network.write().unwrap();
-        *network = new_network;
-        Ok(())
-    }
-
-    pub fn network(&self) -> Network {
-        Network::clone(&*self.network.read().unwrap())
-    }
 }

crates/index-scheduler/src/index_mapper/index_map.rs

@@ -1,7 +1,5 @@
 use std::collections::BTreeMap;
-use std::env::VarError;
 use std::path::Path;
-use std::str::FromStr;
 use std::time::Duration;
 
 use meilisearch_types::heed::{EnvClosingEvent, EnvFlags, EnvOpenOptions};
@@ -104,7 +102,7 @@ impl ReopenableIndex {
                 return Ok(());
             }
             map.unavailable.remove(&self.uuid);
-            map.create(&self.uuid, path, None, self.enable_mdb_writemap, self.map_size, false)?;
+            map.create(&self.uuid, path, None, self.enable_mdb_writemap, self.map_size)?;
         }
         Ok(())
     }
@@ -173,12 +171,11 @@ impl IndexMap {
         date: Option<(OffsetDateTime, OffsetDateTime)>,
         enable_mdb_writemap: bool,
         map_size: usize,
-        creation: bool,
     ) -> Result<Index> {
         if !matches!(self.get_unavailable(uuid), Missing) {
             panic!("Attempt to open an index that was unavailable");
         }
-        let index = create_or_open_index(path, date, enable_mdb_writemap, map_size, creation)?;
+        let index = create_or_open_index(path, date, enable_mdb_writemap, map_size)?;
         match self.available.insert(*uuid, index.clone()) {
             InsertionOutcome::InsertedNew => (),
             InsertionOutcome::Evicted(evicted_uuid, evicted_index) => {
@@ -302,31 +299,18 @@ fn create_or_open_index(
     date: Option<(OffsetDateTime, OffsetDateTime)>,
     enable_mdb_writemap: bool,
     map_size: usize,
-    creation: bool,
 ) -> Result<Index> {
-    let options = EnvOpenOptions::new();
+    let mut options = EnvOpenOptions::new();
-    let mut options = options.read_txn_without_tls();
     options.map_size(clamp_to_page_size(map_size));
-
+    options.max_readers(1024);
-    // You can find more details about this experimental
-    // environment variable on the following GitHub discussion:
-    // <https://github.com/orgs/meilisearch/discussions/806>
-    let max_readers = match std::env::var("MEILI_EXPERIMENTAL_INDEX_MAX_READERS") {
-        Ok(value) => u32::from_str(&value).unwrap(),
-        Err(VarError::NotPresent) => 1024,
-        Err(VarError::NotUnicode(value)) => panic!(
-            "Invalid unicode for the `MEILI_EXPERIMENTAL_INDEX_MAX_READERS` env var: {value:?}"
-        ),
-    };
-    options.max_readers(max_readers);
     if enable_mdb_writemap {
         unsafe { options.flags(EnvFlags::WRITE_MAP) };
     }
 
     if let Some((created, updated)) = date {
-        Ok(Index::new_with_creation_dates(options, path, created, updated, creation)?)
+        Ok(Index::new_with_creation_dates(options, path, created, updated)?)
     } else {
-        Ok(Index::new(options, path, creation)?)
+        Ok(Index::new(options, path)?)
     }
 }
 
@@ -334,7 +318,7 @@ fn create_or_open_index(
 #[cfg(test)]
 mod tests {
 
-    use meilisearch_types::heed::{Env, WithoutTls};
+    use meilisearch_types::heed::Env;
     use meilisearch_types::Index;
     use uuid::Uuid;
 
@@ -344,7 +328,7 @@ mod tests {
     use crate::IndexScheduler;
 
     impl IndexMapper {
-        fn test() -> (Self, Env<WithoutTls>, IndexSchedulerHandle) {
+        fn test() -> (Self, Env, IndexSchedulerHandle) {
             let (index_scheduler, handle) = IndexScheduler::test(true, vec![]);
             (index_scheduler.index_mapper, index_scheduler.env, handle)
         }

crates/index-scheduler/src/index_mapper/mod.rs

@@ -4,10 +4,8 @@ use std::time::Duration;
 use std::{fs, thread};
 
 use meilisearch_types::heed::types::{SerdeJson, Str};
-use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn, WithoutTls};
+use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn};
 use meilisearch_types::milli;
-use meilisearch_types::milli::database_stats::DatabaseStats;
-use meilisearch_types::milli::index::RollbackOutcome;
 use meilisearch_types::milli::update::IndexerConfig;
 use meilisearch_types::milli::{FieldDistribution, Index};
 use serde::{Deserialize, Serialize};
@@ -22,13 +20,8 @@ use crate::{Error, IndexBudget, IndexSchedulerOptions, Result};
 
 mod index_map;
 
-/// The number of database used by index mapper
+const INDEX_MAPPING: &str = "index-mapping";
-const NUMBER_OF_DATABASES: u32 = 2;
+const INDEX_STATS: &str = "index-stats";
-/// Database const names for the `IndexMapper`.
-mod db_name {
-    pub const INDEX_MAPPING: &str = "index-mapping";
-    pub const INDEX_STATS: &str = "index-stats";
-}
 
 /// Structure managing meilisearch's indexes.
 ///
@@ -100,25 +93,14 @@ pub enum IndexStatus {
 /// The statistics that can be computed from an `Index` object.
 #[derive(Serialize, Deserialize, Debug)]
 pub struct IndexStats {
-    /// Stats of the documents database.
+    /// Number of documents in the index.
-    #[serde(default)]
+    pub number_of_documents: u64,
-    pub documents_database_stats: DatabaseStats,
-
-    #[serde(default, skip_serializing)]
-    pub number_of_documents: Option<u64>,
-
     /// Size taken up by the index' DB, in bytes.
     ///
     /// This includes the size taken by both the used and free pages of the DB, and as the free pages
     /// are not returned to the disk after a deletion, this number is typically larger than
     /// `used_database_size` that only includes the size of the used pages.
     pub database_size: u64,
-    /// Number of embeddings in the index.
-    /// Option: retrocompatible with the stats of the pre-v1.13.0 versions of meilisearch
-    pub number_of_embeddings: Option<u64>,
-    /// Number of embedded documents in the index.
-    /// Option: retrocompatible with the stats of the pre-v1.13.0 versions of meilisearch
-    pub number_of_embedded_documents: Option<u64>,
     /// Size taken by the used pages of the index' DB, in bytes.
     ///
     /// As the DB backend does not return to the disk the pages that are not currently used by the DB,
@@ -143,12 +125,8 @@ impl IndexStats {
     ///
     /// - rtxn: a RO transaction for the index, obtained from `Index::read_txn()`.
     pub fn new(index: &Index, rtxn: &RoTxn) -> milli::Result<Self> {
-        let arroy_stats = index.arroy_stats(rtxn)?;
         Ok(IndexStats {
-            number_of_embeddings: Some(arroy_stats.number_of_embeddings),
+            number_of_documents: index.number_of_documents(rtxn)?,
-            number_of_embedded_documents: Some(arroy_stats.documents.len()),
-            documents_database_stats: index.documents_stats(rtxn)?.unwrap_or_default(),
-            number_of_documents: None,
             database_size: index.on_disk_size()?,
             used_database_size: index.used_size()?,
             primary_key: index.primary_key(rtxn)?.map(|s| s.to_string()),
@@ -160,20 +138,16 @@ impl IndexStats {
 }
 
 impl IndexMapper {
-    pub(crate) const fn nb_db() -> u32 {
-        NUMBER_OF_DATABASES
-    }
-
     pub fn new(
-        env: &Env<WithoutTls>,
+        env: &Env,
         wtxn: &mut RwTxn,
         options: &IndexSchedulerOptions,
         budget: IndexBudget,
     ) -> Result<Self> {
         Ok(Self {
             index_map: Arc::new(RwLock::new(IndexMap::new(budget.index_count))),
-            index_mapping: env.create_database(wtxn, Some(db_name::INDEX_MAPPING))?,
+            index_mapping: env.create_database(wtxn, Some(INDEX_MAPPING))?,
-            index_stats: env.create_database(wtxn, Some(db_name::INDEX_STATS))?,
+            index_stats: env.create_database(wtxn, Some(INDEX_STATS))?,
             base_path: options.indexes_path.clone(),
             index_base_map_size: budget.map_size,
             index_growth_amount: options.index_growth_amount,
@@ -215,7 +189,6 @@ impl IndexMapper {
                         date,
                         self.enable_mdb_writemap,
                         self.index_base_map_size,
-                        true,
                     )
                     .map_err(|e| Error::from_milli(e, Some(uuid.to_string())))?;
                 let index_rtxn = index.read_txn()?;
@@ -414,7 +387,6 @@ impl IndexMapper {
                                     None,
                                     self.enable_mdb_writemap,
                                     self.index_base_map_size,
-                                    false,
                                 )
                                 .map_err(|e| Error::from_milli(e, Some(uuid.to_string())))?;
                         }
@@ -432,51 +404,6 @@ impl IndexMapper {
         Ok(index)
     }
 
-    pub fn rollback_index(
-        &self,
-        rtxn: &RoTxn,
-        name: &str,
-        to: (u32, u32, u32),
-    ) -> Result<RollbackOutcome> {
-        // remove any currently updating index to make sure that we aren't keeping a reference to the index somewhere
-        drop(self.currently_updating_index.write().unwrap().take());
-
-        let uuid = self
-            .index_mapping
-            .get(rtxn, name)?
-            .ok_or_else(|| Error::IndexNotFound(name.to_string()))?;
-
-        // take the lock to make sure noone is messing with the indexes while we rollback
-        // this will block any search or other operation, but we are rollbacking so this is probably acceptable.
-        let mut index_map = self.index_map.write().unwrap();
-
-        'close_index: loop {
-            match index_map.get(&uuid) {
-                Available(_) => {
-                    index_map.close_for_resize(&uuid, self.enable_mdb_writemap, 0);
-                    // index should now be `Closing`; try again
-                    continue;
-                }
-                // index already closed
-                Missing => break 'close_index,
-                // closing requested by this thread or another one; wait for closing to complete, then exit
-                Closing(closing_index) => {
-                    if closing_index.wait_timeout(Duration::from_secs(100)).is_none() {
-                        // release the lock so it doesn't get poisoned
-                        drop(index_map);
-                        panic!("cannot close index")
-                    }
-                    break;
-                }
-                BeingDeleted => return Err(Error::IndexNotFound(name.to_string())),
-            };
-        }
-
-        let index_path = self.base_path.join(uuid.to_string());
-        Index::rollback(milli::heed::EnvOpenOptions::new().read_txn_without_tls(), index_path, to)
-            .map_err(|err| crate::Error::from_milli(err, Some(name.to_string())))
-    }
-
     /// Attempts `f` for each index that exists in the index mapper.
     ///
     /// It is preferable to use this function rather than a loop that opens all indexes, as a way to avoid having all indexes opened,

crates/index-scheduler/src/insta_snapshot.rs

@@ -1,12 +1,11 @@
 use std::collections::BTreeSet;
 use std::fmt::Write;
 
-use meilisearch_types::batches::{Batch, BatchEnqueuedAt, BatchStats};
+use meilisearch_types::batches::Batch;
 use meilisearch_types::heed::types::{SerdeBincode, SerdeJson, Str};
 use meilisearch_types::heed::{Database, RoTxn};
 use meilisearch_types::milli::{CboRoaringBitmapCodec, RoaringBitmapCodec, BEU32};
 use meilisearch_types::tasks::{Details, Kind, Status, Task};
-use meilisearch_types::versioning;
 use roaring::RoaringBitmap;
 
 use crate::index_mapper::IndexMapper;
@@ -22,7 +21,6 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
         cleanup_enabled: _,
         processing_tasks,
         env,
-        version,
         queue,
         scheduler,
 
@@ -34,20 +32,12 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
         planned_failures: _,
         run_loop_iteration: _,
         embedders: _,
-        chat_settings: _,
     } = scheduler;
 
     let rtxn = env.read_txn().unwrap();
 
     let mut snap = String::new();
 
-    let indx_sched_version = version.get_version(&rtxn).unwrap();
-    let latest_version =
-        (versioning::VERSION_MAJOR, versioning::VERSION_MINOR, versioning::VERSION_PATCH);
-    if indx_sched_version != Some(latest_version) {
-        snap.push_str(&format!("index scheduler running on version {indx_sched_version:?}\n"));
-    }
-
     let processing = processing_tasks.read().unwrap().clone();
     snap.push_str(&format!("### Autobatching Enabled = {}\n", scheduler.autobatching_enabled));
     snap.push_str(&format!(
@@ -289,12 +279,6 @@ fn snapshot_details(d: &Details) -> String {
         Details::IndexSwap { swaps } => {
             format!("{{ swaps: {swaps:?} }}")
         }
-        Details::Export { url, api_key, payload_size, indexes } => {
-            format!("{{ url: {url:?}, api_key: {api_key:?}, payload_size: {payload_size:?}, indexes: {indexes:?} }}")
-        }
-        Details::UpgradeDatabase { from, to } => {
-            format!("{{ from: {from:?}, to: {to:?} }}")
-        }
     }
 }
 
@@ -342,41 +326,14 @@ pub fn snapshot_canceled_by(rtxn: &RoTxn, db: Database<BEU32, RoaringBitmapCodec
 
 pub fn snapshot_batch(batch: &Batch) -> String {
     let mut snap = String::new();
-    let Batch {
+    let Batch { uid, details, stats, started_at, finished_at, progress: _ } = batch;
-        uid,
-        details,
-        stats,
-        embedder_stats,
-        started_at,
-        finished_at,
-        progress: _,
-        enqueued_at,
-        stop_reason,
-    } = batch;
-    let stats = BatchStats {
-        progress_trace: Default::default(),
-        internal_database_sizes: Default::default(),
-        write_channel_congestion: None,
-        ..stats.clone()
-    };
     if let Some(finished_at) = finished_at {
         assert!(finished_at > started_at);
     }
-    let BatchEnqueuedAt { earliest, oldest } = enqueued_at.unwrap();
-    assert!(*started_at > earliest);
-    assert!(earliest >= oldest);
-
     snap.push('{');
     snap.push_str(&format!("uid: {uid}, "));
     snap.push_str(&format!("details: {}, ", serde_json::to_string(details).unwrap()));
-    snap.push_str(&format!("stats: {}, ", serde_json::to_string(&stats).unwrap()));
+    snap.push_str(&format!("stats: {}, ", serde_json::to_string(stats).unwrap()));
-    if !embedder_stats.skip_serializing() {
-        snap.push_str(&format!(
-            "embedder stats: {}, ",
-            serde_json::to_string(&embedder_stats).unwrap()
-        ));
-    }
-    snap.push_str(&format!("stop reason: {}, ", serde_json::to_string(&stop_reason).unwrap()));
     snap.push('}');
     snap
 }
@@ -389,8 +346,7 @@ pub fn snapshot_index_mapper(rtxn: &RoTxn, mapper: &IndexMapper) -> String {
         let stats = mapper.stats_of(rtxn, &name).unwrap();
         s.push_str(&format!(
             "{name}: {{ number_of_documents: {}, field_distribution: {:?} }}\n",
-            stats.documents_database_stats.number_of_entries(),
+            stats.number_of_documents, stats.field_distribution
-            stats.field_distribution
         ));
     }
 

crates/index-scheduler/src/lib.rs

@@ -30,10 +30,8 @@ mod queue;
 mod scheduler;
 #[cfg(test)]
 mod test_utils;
-pub mod upgrade;
 mod utils;
 pub mod uuid_codec;
-pub mod versioning;
 
 pub type Result<T, E = Error> = std::result::Result<T, E>;
 pub type TaskId = u32;
@@ -51,37 +49,28 @@ pub use features::RoFeatures;
 use flate2::bufread::GzEncoder;
 use flate2::Compression;
 use meilisearch_types::batches::Batch;
-use meilisearch_types::features::{
+use meilisearch_types::features::{InstanceTogglableFeatures, RuntimeTogglableFeatures};
-    ChatCompletionSettings, InstanceTogglableFeatures, Network, RuntimeTogglableFeatures,
-};
 use meilisearch_types::heed::byteorder::BE;
-use meilisearch_types::heed::types::{DecodeIgnore, SerdeJson, Str, I128};
+use meilisearch_types::heed::types::I128;
-use meilisearch_types::heed::{self, Database, Env, RoTxn, WithoutTls};
+use meilisearch_types::heed::{self, Env, RoTxn};
+use meilisearch_types::milli::index::IndexEmbeddingConfig;
 use meilisearch_types::milli::update::IndexerConfig;
-use meilisearch_types::milli::vector::json_template::JsonTemplate;
+use meilisearch_types::milli::vector::{Embedder, EmbedderOptions, EmbeddingConfigs};
-use meilisearch_types::milli::vector::{
-    Embedder, EmbedderOptions, RuntimeEmbedder, RuntimeEmbedders, RuntimeFragment,
-};
 use meilisearch_types::milli::{self, Index};
 use meilisearch_types::task_view::TaskView;
 use meilisearch_types::tasks::{KindWithContent, Task};
-use milli::vector::db::IndexEmbeddingConfig;
 use processing::ProcessingTasks;
 pub use queue::Query;
 use queue::Queue;
 use roaring::RoaringBitmap;
 use scheduler::Scheduler;
 use time::OffsetDateTime;
-use versioning::Versioning;
 
 use crate::index_mapper::IndexMapper;
 use crate::utils::clamp_to_page_size;
 
 pub(crate) type BEI128 = I128<BE>;
 
-const TASK_SCHEDULER_SIZE_THRESHOLD_PERCENT_INT: u64 = 40;
-const CHAT_SETTINGS_DB_NAME: &str = "chat-settings";
-
 #[derive(Debug)]
 pub struct IndexSchedulerOptions {
     /// The path to the version file of Meilisearch.
@@ -131,40 +120,28 @@ pub struct IndexSchedulerOptions {
     pub batched_tasks_size_limit: u64,
     /// The experimental features enabled for this instance.
     pub instance_features: InstanceTogglableFeatures,
-    /// The experimental features enabled for this instance.
-    pub auto_upgrade: bool,
-    /// The maximal number of entries in the search query cache of an embedder.
-    ///
-    /// 0 disables the cache.
-    pub embedding_cache_cap: usize,
-    /// Snapshot compaction status.
-    pub experimental_no_snapshot_compaction: bool,
 }
 
 /// Structure which holds meilisearch's indexes and schedules the tasks
 /// to be performed on them.
 pub struct IndexScheduler {
     /// The LMDB environment which the DBs are associated with.
-    pub(crate) env: Env<WithoutTls>,
+    pub(crate) env: Env,
 
     /// The list of tasks currently processing
     pub(crate) processing_tasks: Arc<RwLock<ProcessingTasks>>,
 
-    /// A database containing only the version of the index-scheduler
-    pub version: versioning::Versioning,
     /// The queue containing both the tasks and the batches.
     pub queue: queue::Queue,
+
+    pub scheduler: scheduler::Scheduler,
+
     /// In charge of creating, opening, storing and returning indexes.
     pub(crate) index_mapper: IndexMapper,
+
     /// In charge of fetching and setting the status of experimental features.
     features: features::FeatureData,
 
-    /// Stores the custom chat prompts and other settings of the indexes.
-    pub(crate) chat_settings: Database<Str, SerdeJson<ChatCompletionSettings>>,
-
-    /// Everything related to the processing of the tasks
-    pub scheduler: scheduler::Scheduler,
-
     /// Whether we should automatically cleanup the task queue or not.
     pub(crate) cleanup_enabled: bool,
 
@@ -173,11 +150,6 @@ pub struct IndexScheduler {
     /// The Authorization header to send to the webhook URL.
     pub(crate) webhook_authorization_header: Option<String>,
 
-    /// A map to retrieve the runtime representation of an embedder depending on its configuration.
-    ///
-    /// This map may return the same embedder object for two different indexes or embedder settings,
-    /// but it will only do this if the embedder configuration options are the same, leading
-    /// to the same embeddings for the same input text.
     embedders: Arc<RwLock<HashMap<EmbedderOptions, Arc<Embedder>>>>,
 
     // ================= test
@@ -204,7 +176,6 @@ impl IndexScheduler {
         IndexScheduler {
             env: self.env.clone(),
             processing_tasks: self.processing_tasks.clone(),
-            version: self.version.clone(),
             queue: self.queue.private_clone(),
             scheduler: self.scheduler.private_clone(),
 
@@ -220,24 +191,13 @@ impl IndexScheduler {
             #[cfg(test)]
             run_loop_iteration: self.run_loop_iteration.clone(),
             features: self.features.clone(),
-            chat_settings: self.chat_settings,
         }
     }
 
-    pub(crate) const fn nb_db() -> u32 {
-        Versioning::nb_db()
-            + Queue::nb_db()
-            + IndexMapper::nb_db()
-            + features::FeatureData::nb_db()
-            + 1 // chat-prompts
-    }
-
     /// Create an index scheduler and start its run loop.
     #[allow(private_interfaces)] // because test_utils is private
     pub fn new(
         options: IndexSchedulerOptions,
-        auth_env: Env<WithoutTls>,
-        from_db_version: (u32, u32, u32),
         #[cfg(test)] test_breakpoint_sdr: crossbeam_channel::Sender<(test_utils::Breakpoint, bool)>,
         #[cfg(test)] planned_failures: Vec<(usize, test_utils::FailureLocation)>,
     ) -> Result<Self> {
@@ -268,30 +228,24 @@ impl IndexScheduler {
         };
 
         let env = unsafe {
-            let env_options = heed::EnvOpenOptions::new();
+            heed::EnvOpenOptions::new()
-            let mut env_options = env_options.read_txn_without_tls();
+                .max_dbs(19)
-            env_options
-                .max_dbs(Self::nb_db())
                 .map_size(budget.task_db_size)
                 .open(&options.tasks_path)
         }?;
 
-        // We **must** starts by upgrading the version because it'll also upgrade the required database before we can open them
+        let features = features::FeatureData::new(&env, options.instance_features)?;
-        let version = versioning::Versioning::new(&env, from_db_version)?;
 
         let mut wtxn = env.write_txn()?;
-        let features = features::FeatureData::new(&env, &mut wtxn, options.instance_features)?;
         let queue = Queue::new(&env, &mut wtxn, &options)?;
         let index_mapper = IndexMapper::new(&env, &mut wtxn, &options, budget)?;
-        let chat_settings = env.create_database(&mut wtxn, Some(CHAT_SETTINGS_DB_NAME))?;
         wtxn.commit()?;
 
         // allow unreachable_code to get rids of the warning in the case of a test build.
         let this = Self {
             processing_tasks: Arc::new(RwLock::new(ProcessingTasks::new())),
-            version,
             queue,
-            scheduler: Scheduler::new(&options, auth_env),
+            scheduler: Scheduler::new(&options),
 
             index_mapper,
             env,
@@ -307,17 +261,12 @@ impl IndexScheduler {
             #[cfg(test)]
             run_loop_iteration: Arc::new(RwLock::new(0)),
             features,
-            chat_settings,
         };
 
         this.run();
         Ok(this)
     }
 
-    fn read_txn(&self) -> Result<RoTxn<WithoutTls>> {
-        self.env.read_txn().map_err(|e| e.into())
-    }
-
     /// Return `Ok(())` if the index scheduler is able to access one of its database.
     pub fn health(&self) -> Result<()> {
         let rtxn = self.env.read_txn()?;
@@ -394,16 +343,15 @@ impl IndexScheduler {
         }
     }
 
+    pub fn read_txn(&self) -> Result<RoTxn> {
+        self.env.read_txn().map_err(|e| e.into())
+    }
+
     /// Start the run loop for the given index scheduler.
     ///
     /// This function will execute in a different thread and must be called
     /// only once per index scheduler.
     fn run(&self) {
-        // If the number of batched tasks is 0, we don't need to run the scheduler at all.
-        // It will never be able to process any tasks.
-        if self.scheduler.max_number_of_batched_tasks == 0 {
-            return;
-        }
         let run = self.private_clone();
         std::thread::Builder::new()
             .name(String::from("scheduler"))
@@ -418,12 +366,11 @@ impl IndexScheduler {
                     match ret {
                         Ok(Ok(TickOutcome::TickAgain(_))) => (),
                         Ok(Ok(TickOutcome::WaitForSignal)) => run.scheduler.wake_up.wait(),
-                        Ok(Ok(TickOutcome::StopProcessingForever)) => break,
                         Ok(Err(e)) => {
                             tracing::error!("{e}");
-                            // Wait when an irrecoverable error occurs.
+                            // Wait one second when an irrecoverable error occurs.
                             if !e.is_recoverable() {
-                                std::thread::sleep(Duration::from_secs(10));
+                                std::thread::sleep(Duration::from_secs(1));
                             }
                         }
                         Err(_panic) => {
@@ -450,17 +397,6 @@ impl IndexScheduler {
         Ok(self.env.non_free_pages_size()?)
     }
 
-    /// Return the maximum possible database size
-    pub fn max_size(&self) -> Result<u64> {
-        Ok(self.env.info().map_size as u64)
-    }
-
-    /// Return the max size of task allowed until the task queue stop receiving.
-    pub fn remaining_size_until_task_queue_stop(&self) -> Result<u64> {
-        Ok((self.env.info().map_size as u64 * TASK_SCHEDULER_SIZE_THRESHOLD_PERCENT_INT / 100)
-            .saturating_sub(self.used_size()?))
-    }
-
     /// Return the index corresponding to the name.
     ///
     /// * If the index wasn't opened before, the index will be opened.
@@ -475,14 +411,12 @@ impl IndexScheduler {
     /// If you need to fetch information from or perform an action on all indexes,
     /// see the `try_for_each_index` function.
     pub fn index(&self, name: &str) -> Result<Index> {
-        let rtxn = self.env.read_txn()?;
+        self.index_mapper.index(&self.env.read_txn()?, name)
-        self.index_mapper.index(&rtxn, name)
     }
 
     /// Return the boolean referring if index exists.
     pub fn index_exists(&self, name: &str) -> Result<bool> {
-        let rtxn = self.env.read_txn()?;
+        self.index_mapper.index_exists(&self.env.read_txn()?, name)
-        self.index_mapper.index_exists(&rtxn, name)
     }
 
     /// Return the name of all indexes without opening them.
@@ -511,7 +445,7 @@ impl IndexScheduler {
 
     /// Returns the total number of indexes available for the specified filter.
     /// And a `Vec` of the index_uid + its stats
-    pub fn paginated_indexes_stats(
+    pub fn get_paginated_indexes_stats(
         &self,
         filters: &meilisearch_auth::AuthFilter,
         from: usize,
@@ -552,31 +486,12 @@ impl IndexScheduler {
         ret.map(|ret| (total, ret))
     }
 
-    /// Returns the total number of chat workspaces available ~~for the specified filter~~.
-    /// And a `Vec` of the workspace_uids
-    pub fn paginated_chat_workspace_uids(
-        &self,
-        from: usize,
-        limit: usize,
-    ) -> Result<(usize, Vec<String>)> {
-        let rtxn = self.read_txn()?;
-        let total = self.chat_settings.len(&rtxn)?;
-        let mut iter = self.chat_settings.iter(&rtxn)?.skip(from);
-        iter.by_ref()
-            .take(limit)
-            .map(|ret| ret.map_err(Error::from))
-            .map(|ret| ret.map(|(uid, _)| uid.to_string()))
-            .collect::<Result<Vec<_>, Error>>()
-            .map(|ret| (total as usize, ret))
-    }
-
     /// The returned structure contains:
     /// 1. The name of the property being observed can be `statuses`, `types`, or `indexes`.
     /// 2. The name of the specific data related to the property can be `enqueued` for the `statuses`, `settingsUpdate` for the `types`, or the name of the index for the `indexes`, for example.
     /// 3. The number of times the properties appeared.
     pub fn get_stats(&self) -> Result<BTreeMap<String, BTreeMap<String, u64>>> {
-        let rtxn = self.read_txn()?;
+        self.queue.get_stats(&self.read_txn()?, &self.processing_tasks.read().unwrap())
-        self.queue.get_stats(&rtxn, &self.processing_tasks.read().unwrap())
     }
 
     // Return true if there is at least one task that is processing.
@@ -679,10 +594,9 @@ impl IndexScheduler {
         task_id: Option<TaskId>,
         dry_run: bool,
     ) -> Result<Task> {
-        // if the task doesn't delete or cancel anything and 40% of the task queue is full, we must refuse to enqueue the incoming task
+        // if the task doesn't delete anything and 50% of the task queue is full, we must refuse to enqueue the incomming task
-        if !matches!(&kind, KindWithContent::TaskDeletion { tasks, .. } | KindWithContent::TaskCancelation { tasks, .. } if !tasks.is_empty())
+        if !matches!(&kind, KindWithContent::TaskDeletion { tasks, .. } if !tasks.is_empty())
-            && (self.env.non_free_pages_size()? * 100) / self.env.info().map_size as u64
+            && (self.env.non_free_pages_size()? * 100) / self.env.info().map_size as u64 > 40
-                > TASK_SCHEDULER_SIZE_THRESHOLD_PERCENT_INT
         {
             return Err(Error::NoSpaceLeftInTaskQueue);
         }
@@ -751,7 +665,7 @@ impl IndexScheduler {
                 written: usize,
             }
 
-            impl Read for TaskReader<'_, '_> {
+            impl<'a, 'b> Read for TaskReader<'a, 'b> {
                 fn read(&mut self, mut buf: &mut [u8]) -> std::io::Result<usize> {
                     if self.buffer.is_empty() {
                         match self.tasks.next() {
@@ -840,62 +754,40 @@ impl IndexScheduler {
         Ok(())
     }
 
-    pub fn put_network(&self, network: Network) -> Result<()> {
+    // TODO: consider using a type alias or a struct embedder/template
-        let wtxn = self.env.write_txn().map_err(Error::HeedTransaction)?;
-        self.features.put_network(wtxn, network)?;
-        Ok(())
-    }
-
-    pub fn network(&self) -> Network {
-        self.features.network()
-    }
-
     pub fn embedders(
         &self,
         index_uid: String,
         embedding_configs: Vec<IndexEmbeddingConfig>,
-    ) -> Result<RuntimeEmbedders> {
+    ) -> Result<EmbeddingConfigs> {
         let res: Result<_> = embedding_configs
             .into_iter()
             .map(
                 |IndexEmbeddingConfig {
                      name,
                      config: milli::vector::EmbeddingConfig { embedder_options, prompt, quantized },
-                     fragments,
+                     ..
-                 }|
+                 }| {
-                 -> Result<(String, Arc<RuntimeEmbedder>)> {
+                    let prompt = Arc::new(
-                    let document_template = prompt
+                        prompt
-                        .try_into()
+                            .try_into()
-                        .map_err(meilisearch_types::milli::Error::from)
+                            .map_err(meilisearch_types::milli::Error::from)
-                        .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
+                            .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?,
-
+                    );
-                    let fragments = fragments
-                        .into_inner()
-                        .into_iter()
-                        .map(|fragment| {
-                            let value = embedder_options.fragment(&fragment.name).unwrap();
-                            let template = JsonTemplate::new(value.clone()).unwrap();
-                            RuntimeFragment { name: fragment.name, id: fragment.id, template }
-                        })
-                        .collect();
                     // optimistically return existing embedder
                     {
                         let embedders = self.embedders.read().unwrap();
                         if let Some(embedder) = embedders.get(&embedder_options) {
-                            let runtime = Arc::new(RuntimeEmbedder::new(
+                            return Ok((
-                                embedder.clone(),
+                                name,
-                                document_template,
+                                (embedder.clone(), prompt, quantized.unwrap_or_default()),
-                                fragments,
-                                quantized.unwrap_or_default(),
                             ));
-
-                            return Ok((name, runtime));
                         }
                     }
 
                     // add missing embedder
                     let embedder = Arc::new(
-                        Embedder::new(embedder_options.clone(), self.scheduler.embedding_cache_cap)
+                        Embedder::new(embedder_options.clone())
                             .map_err(meilisearch_types::milli::vector::Error::from)
                             .map_err(|err| {
                                 Error::from_milli(err.into(), Some(index_uid.clone()))
@@ -905,44 +797,11 @@ impl IndexScheduler {
                         let mut embedders = self.embedders.write().unwrap();
                         embedders.insert(embedder_options, embedder.clone());
                     }
-
+                    Ok((name, (embedder, prompt, quantized.unwrap_or_default())))
-                    let runtime = Arc::new(RuntimeEmbedder::new(
-                        embedder.clone(),
-                        document_template,
-                        fragments,
-                        quantized.unwrap_or_default(),
-                    ));
-
-                    Ok((name, runtime))
                 },
             )
             .collect();
-        res.map(RuntimeEmbedders::new)
+        res.map(EmbeddingConfigs::new)
-    }
-
-    pub fn chat_settings(&self, uid: &str) -> Result<Option<ChatCompletionSettings>> {
-        let rtxn = self.env.read_txn()?;
-        self.chat_settings.get(&rtxn, uid).map_err(Into::into)
-    }
-
-    /// Return true if chat workspace exists.
-    pub fn chat_workspace_exists(&self, name: &str) -> Result<bool> {
-        let rtxn = self.env.read_txn()?;
-        Ok(self.chat_settings.remap_data_type::<DecodeIgnore>().get(&rtxn, name)?.is_some())
-    }
-
-    pub fn put_chat_settings(&self, uid: &str, settings: &ChatCompletionSettings) -> Result<()> {
-        let mut wtxn = self.env.write_txn()?;
-        self.chat_settings.put(&mut wtxn, uid, settings)?;
-        wtxn.commit()?;
-        Ok(())
-    }
-
-    pub fn delete_chat_settings(&self, uid: &str) -> Result<bool> {
-        let mut wtxn = self.env.write_txn()?;
-        let deleted = self.chat_settings.delete(&mut wtxn, uid)?;
-        wtxn.commit()?;
-        Ok(deleted)
     }
 }
 
@@ -954,8 +813,6 @@ pub enum TickOutcome {
     TickAgain(u64),
     /// The scheduler should wait for an external signal before attempting another `tick`.
     WaitForSignal,
-    /// The scheduler exits the run-loop and will never process tasks again
-    StopProcessingForever,
 }
 
 /// How many indexes we can afford to have open simultaneously.

crates/index-scheduler/src/processing.rs

@@ -1,6 +1,8 @@
+use std::borrow::Cow;
 use std::sync::Arc;
 
-use meilisearch_types::milli::progress::{AtomicSubStep, NamedStep, Progress, ProgressView};
+use enum_iterator::Sequence;
+use meilisearch_types::milli::progress::{AtomicSubStep, NamedStep, Progress, ProgressView, Step};
 use meilisearch_types::milli::{make_atomic_progress, make_enum_progress};
 use roaring::RoaringBitmap;
 
@@ -64,17 +66,9 @@ make_enum_progress! {
     }
 }
 
-make_enum_progress! {
-    pub enum FinalizingIndexStep {
-        Committing,
-        ComputingStats,
-    }
-}
-
 make_enum_progress! {
     pub enum TaskCancelationProgress {
         RetrievingTasks,
-        CancelingUpgrade,
         UpdatingTasks,
     }
 }
@@ -103,9 +97,7 @@ make_enum_progress! {
     pub enum DumpCreationProgress {
         StartTheDumpCreation,
         DumpTheApiKeys,
-        DumpTheChatCompletionSettings,
         DumpTheTasks,
-        DumpTheBatches,
         DumpTheIndexes,
         DumpTheExperimentalFeatures,
         CompressTheDump,
@@ -176,19 +168,36 @@ make_enum_progress! {
     }
 }
 
-make_enum_progress! {
+make_atomic_progress!(Task alias AtomicTaskStep => "task" );
-    pub enum Export {
+make_atomic_progress!(Document alias AtomicDocumentStep => "document" );
-        EnsuringCorrectnessOfTheTarget,
+make_atomic_progress!(Batch alias AtomicBatchStep => "batch" );
-        ExportingTheSettings,
+make_atomic_progress!(UpdateFile alias AtomicUpdateFileStep => "update file" );
-        ExportingTheDocuments,
+
+pub struct VariableNameStep {
+    name: String,
+    current: u32,
+    total: u32,
+}
+
+impl VariableNameStep {
+    pub fn new(name: impl Into<String>, current: u32, total: u32) -> Self {
+        Self { name: name.into(), current, total }
     }
 }
 
-make_atomic_progress!(Task alias AtomicTaskStep => "task" );
+impl Step for VariableNameStep {
-make_atomic_progress!(Document alias AtomicDocumentStep => "document" );
+    fn name(&self) -> Cow<'static, str> {
-make_atomic_progress!(Index alias AtomicIndexStep => "index" );
+        self.name.clone().into()
-make_atomic_progress!(Batch alias AtomicBatchStep => "batch" );
+    }
-make_atomic_progress!(UpdateFile alias AtomicUpdateFileStep => "update file" );
+
+    fn current(&self) -> u32 {
+        self.current
+    }
+
+    fn total(&self) -> u32 {
+        self.total
+    }
+}
 
 #[cfg(test)]
 mod test {

crates/index-scheduler/src/queue/batches.rs

@@ -1,9 +1,8 @@
-use std::collections::HashSet;
 use std::ops::{Bound, RangeBounds};
 
 use meilisearch_types::batches::{Batch, BatchId};
 use meilisearch_types::heed::types::{DecodeIgnore, SerdeBincode, SerdeJson, Str};
-use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn, WithoutTls};
+use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn};
 use meilisearch_types::milli::{CboRoaringBitmapCodec, RoaringBitmapCodec, BEU32};
 use meilisearch_types::tasks::{Kind, Status};
 use roaring::{MultiOps, RoaringBitmap};
@@ -11,14 +10,9 @@ use time::OffsetDateTime;
 
 use super::{Query, Queue};
 use crate::processing::ProcessingTasks;
-use crate::utils::{
+use crate::utils::{insert_task_datetime, keep_ids_within_datetimes, map_bound, ProcessingBatch};
-    insert_task_datetime, keep_ids_within_datetimes, map_bound,
-    remove_n_tasks_datetime_earlier_than, remove_task_datetime, ProcessingBatch,
-};
 use crate::{Error, Result, BEI128};
 
-/// The number of database used by the batch queue
-const NUMBER_OF_DATABASES: u32 = 7;
 /// Database const names for the `IndexScheduler`.
 mod db_name {
     pub const ALL_BATCHES: &str = "all-batches";
@@ -62,11 +56,7 @@ impl BatchQueue {
         }
     }
 
-    pub(crate) const fn nb_db() -> u32 {
+    pub(super) fn new(env: &Env, wtxn: &mut RwTxn) -> Result<Self> {
-        NUMBER_OF_DATABASES
-    }
-
-    pub(super) fn new(env: &Env<WithoutTls>, wtxn: &mut RwTxn) -> Result<Self> {
         Ok(Self {
             all_batches: env.create_database(wtxn, Some(db_name::ALL_BATCHES))?,
             status: env.create_database(wtxn, Some(db_name::BATCH_STATUS))?,
@@ -169,8 +159,6 @@ impl BatchQueue {
     }
 
     pub(crate) fn write_batch(&self, wtxn: &mut RwTxn, batch: ProcessingBatch) -> Result<()> {
-        let old_batch = self.all_batches.get(wtxn, &batch.uid)?;
-
         self.all_batches.put(
             wtxn,
             &batch.uid,
@@ -179,90 +167,34 @@ impl BatchQueue {
                 progress: None,
                 details: batch.details,
                 stats: batch.stats,
-                embedder_stats: batch.embedder_stats.as_ref().into(),
                 started_at: batch.started_at,
                 finished_at: batch.finished_at,
-                enqueued_at: batch.enqueued_at,
-                stop_reason: batch.reason.to_string(),
             },
         )?;
 
-        // Update the statuses
-        if let Some(ref old_batch) = old_batch {
-            for status in old_batch.stats.status.keys() {
-                self.update_status(wtxn, *status, |bitmap| {
-                    bitmap.remove(batch.uid);
-                })?;
-            }
-        }
         for status in batch.statuses {
             self.update_status(wtxn, status, |bitmap| {
                 bitmap.insert(batch.uid);
             })?;
         }
 
-        // Update the kinds / types
-        if let Some(ref old_batch) = old_batch {
-            let kinds: HashSet<_> = old_batch.stats.types.keys().cloned().collect();
-            for kind in kinds.difference(&batch.kinds) {
-                self.update_kind(wtxn, *kind, |bitmap| {
-                    bitmap.remove(batch.uid);
-                })?;
-            }
-        }
         for kind in batch.kinds {
             self.update_kind(wtxn, kind, |bitmap| {
                 bitmap.insert(batch.uid);
             })?;
         }
 
-        // Update the indexes
-        if let Some(ref old_batch) = old_batch {
-            let indexes: HashSet<_> = old_batch.stats.index_uids.keys().cloned().collect();
-            for index in indexes.difference(&batch.indexes) {
-                self.update_index(wtxn, index, |bitmap| {
-                    bitmap.remove(batch.uid);
-                })?;
-            }
-        }
         for index in batch.indexes {
             self.update_index(wtxn, &index, |bitmap| {
                 bitmap.insert(batch.uid);
             })?;
         }
 
-        // Update the enqueued_at: we cannot retrieve the previous enqueued at from the previous batch, and
+        if let Some(enqueued_at) = batch.oldest_enqueued_at {
-        // must instead go through the db looking for it. We cannot look at the task contained in this batch either
+            insert_task_datetime(wtxn, self.enqueued_at, enqueued_at, batch.uid)?;
-        // because they may have been removed.
-        // What we know, though, is that the task date is from before the enqueued_at, and max two timestamps have been written
-        // to the DB per batches.
-        if let Some(ref old_batch) = old_batch {
-            if let Some(enqueued_at) = old_batch.enqueued_at {
-                remove_task_datetime(wtxn, self.enqueued_at, enqueued_at.earliest, old_batch.uid)?;
-                remove_task_datetime(wtxn, self.enqueued_at, enqueued_at.oldest, old_batch.uid)?;
-            } else {
-                // If we don't have the enqueued at in the batch it means the database comes from the v1.12
-                // and we still need to find the date by scrolling the database
-                remove_n_tasks_datetime_earlier_than(
-                    wtxn,
-                    self.enqueued_at,
-                    old_batch.started_at,
-                    old_batch.stats.total_nb_tasks.clamp(1, 2) as usize,
-                    old_batch.uid,
-                )?;
-            }
         }
-        // A finished batch MUST contains at least one task and have an enqueued_at
+        if let Some(enqueued_at) = batch.earliest_enqueued_at {
-        let enqueued_at = batch.enqueued_at.as_ref().unwrap();
+            insert_task_datetime(wtxn, self.enqueued_at, enqueued_at, batch.uid)?;
-        insert_task_datetime(wtxn, self.enqueued_at, enqueued_at.earliest, batch.uid)?;
-        insert_task_datetime(wtxn, self.enqueued_at, enqueued_at.oldest, batch.uid)?;
-
-        // Update the started at and finished at
-        if let Some(ref old_batch) = old_batch {
-            remove_task_datetime(wtxn, self.started_at, old_batch.started_at, old_batch.uid)?;
-            if let Some(finished_at) = old_batch.finished_at {
-                remove_task_datetime(wtxn, self.finished_at, finished_at, old_batch.uid)?;
-            }
         }
         insert_task_datetime(wtxn, self.started_at, batch.started_at, batch.uid)?;
         insert_task_datetime(wtxn, self.finished_at, batch.finished_at.unwrap(), batch.uid)?;

crates/index-scheduler/src/queue/batches_test.rs

@@ -102,34 +102,30 @@ fn query_batches_simple() {
         .unwrap();
     assert_eq!(batches.len(), 1);
     batches[0].started_at = OffsetDateTime::UNIX_EPOCH;
-    assert!(batches[0].enqueued_at.is_some());
-    batches[0].enqueued_at = None;
     // Insta cannot snapshot our batches because the batch stats contains an enum as key: https://github.com/mitsuhiko/insta/issues/689
     let batch = serde_json::to_string_pretty(&batches[0]).unwrap();
-    snapshot!(batch, @r###"
+    snapshot!(batch, @r#"
-    {
+        {
-      "uid": 0,
+          "uid": 0,
-      "details": {
+          "details": {
-        "primaryKey": "mouse"
+            "primaryKey": "mouse"
-      },
+          },
-      "stats": {
+          "stats": {
-        "totalNbTasks": 1,
+            "totalNbTasks": 1,
-        "status": {
+            "status": {
-          "processing": 1
+              "processing": 1
-        },
+            },
-        "types": {
+            "types": {
-          "indexCreation": 1
+              "indexCreation": 1
-        },
+            },
-        "indexUids": {
+            "indexUids": {
-          "catto": 1
+              "catto": 1
+            }
+          },
+          "startedAt": "1970-01-01T00:00:00Z",
+          "finishedAt": null
         }
-      },
+        "#);
-      "startedAt": "1970-01-01T00:00:00Z",
-      "finishedAt": null,
-      "enqueuedAt": null,
-      "stopReason": "created batch containing only task with id 0 of type `indexCreation` that cannot be batched with any other task."
-    }
-    "###);
 
     let query = Query { statuses: Some(vec![Status::Enqueued]), ..Default::default() };
     let (batches, _) = index_scheduler

crates/index-scheduler/src/queue/mod.rs

@@ -8,12 +8,11 @@ mod tasks_test;
 mod test;
 
 use std::collections::BTreeMap;
-use std::fs::File as StdFile;
 use std::time::Duration;
 
 use file_store::FileStore;
 use meilisearch_types::batches::BatchId;
-use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn, WithoutTls};
+use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn};
 use meilisearch_types::milli::{CboRoaringBitmapCodec, BEU32};
 use meilisearch_types::tasks::{Kind, KindWithContent, Status, Task};
 use roaring::RoaringBitmap;
@@ -21,16 +20,14 @@ use time::format_description::well_known::Rfc3339;
 use time::OffsetDateTime;
 use uuid::Uuid;
 
-pub(crate) use self::batches::BatchQueue;
+use self::batches::BatchQueue;
-pub(crate) use self::tasks::TaskQueue;
+use self::tasks::TaskQueue;
 use crate::processing::ProcessingTasks;
 use crate::utils::{
     check_index_swap_validity, filter_out_references_to_newer_tasks, ProcessingBatch,
 };
 use crate::{Error, IndexSchedulerOptions, Result, TaskId};
 
-/// The number of database used by queue itself
-const NUMBER_OF_DATABASES: u32 = 1;
 /// Database const names for the `IndexScheduler`.
 mod db_name {
     pub const BATCH_TO_TASKS_MAPPING: &str = "batch-to-tasks-mapping";
@@ -151,13 +148,9 @@ impl Queue {
         }
     }
 
-    pub(crate) const fn nb_db() -> u32 {
-        tasks::TaskQueue::nb_db() + batches::BatchQueue::nb_db() + NUMBER_OF_DATABASES
-    }
-
     /// Create an index scheduler and start its run loop.
     pub(crate) fn new(
-        env: &Env<WithoutTls>,
+        env: &Env,
         wtxn: &mut RwTxn,
         options: &IndexSchedulerOptions,
     ) -> Result<Self> {
@@ -217,11 +210,6 @@ impl Queue {
         }
     }
 
-    /// Open and returns the task's content File.
-    pub fn update_file(&self, uuid: Uuid) -> file_store::Result<StdFile> {
-        self.file_store.get_update(uuid)
-    }
-
     /// Delete a file from the index scheduler.
     ///
     /// Counterpart to the [`create_update_file`](IndexScheduler::create_update_file) method.
@@ -292,6 +280,8 @@ impl Queue {
             return Ok(task);
         }
 
+        // Get rid of the mutability.
+        let task = task;
         self.tasks.register(wtxn, &task)?;
 
         Ok(task)

crates/index-scheduler/src/queue/snapshots/batches_test.rs/query_batches_canceled_by/start.snap

@@ -1,5 +1,6 @@
 ---
 source: crates/index-scheduler/src/queue/batches_test.rs
+snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -48,8 +49,8 @@ catto: { number_of_documents: 0, field_distribution: {} }
 [timestamp] [1,2,3,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"primaryKey":"mouse"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":1}}, stop reason: "created batch containing only task with id 0 of type `indexCreation` that cannot be batched with any other task.", }
+0 {uid: 0, details: {"primaryKey":"mouse"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":1}}, }
-1 {uid: 1, details: {"primaryKey":"sheep","matchedTasks":3,"canceledTasks":2,"originalFilter":"test_query","swaps":[{"indexes":["catto","doggo"]}]}, stats: {"totalNbTasks":3,"status":{"succeeded":1,"canceled":2},"types":{"indexCreation":1,"indexSwap":1,"taskCancelation":1},"indexUids":{"doggo":1}}, stop reason: "created batch containing only task with id 3 of type `taskCancelation` that cannot be batched with any other task.", }
+1 {uid: 1, details: {"primaryKey":"sheep","matchedTasks":3,"canceledTasks":2,"originalFilter":"test_query","swaps":[{"indexes":["catto","doggo"]}]}, stats: {"totalNbTasks":3,"status":{"succeeded":1,"canceled":2},"types":{"indexCreation":1,"indexSwap":1,"taskCancelation":1},"indexUids":{"doggo":1}}, }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

crates/index-scheduler/src/queue/snapshots/batches_test.rs/query_batches_from_and_limit/processed_all_tasks.snap

@@ -1,5 +1,6 @@
 ---
 source: crates/index-scheduler/src/queue/batches_test.rs
+snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -47,9 +48,9 @@ whalo: { number_of_documents: 0, field_distribution: {} }
 [timestamp] [2,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"primaryKey":"bone"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, stop reason: "created batch containing only task with id 0 of type `indexCreation` that cannot be batched with any other task.", }
+0 {uid: 0, details: {"primaryKey":"bone"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, }
-1 {uid: 1, details: {"primaryKey":"plankton"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"whalo":1}}, stop reason: "created batch containing only task with id 1 of type `indexCreation` that cannot be batched with any other task.", }
+1 {uid: 1, details: {"primaryKey":"plankton"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"whalo":1}}, }
-2 {uid: 2, details: {"primaryKey":"his_own_vomit"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":1}}, stop reason: "created batch containing only task with id 2 of type `indexCreation` that cannot be batched with any other task.", }
+2 {uid: 2, details: {"primaryKey":"his_own_vomit"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":1}}, }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

crates/index-scheduler/src/queue/snapshots/batches_test.rs/query_batches_simple/after-advancing-a-bit.snap

@@ -1,10 +1,11 @@
 ---
 source: crates/index-scheduler/src/queue/batches_test.rs
+snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch Some(1):
 [1,]
-{uid: 1, details: {"primaryKey":"sheep"}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, stop reason: "created batch containing only task with id 1 of type `indexCreation` that cannot be batched with any other task.", }
+{uid: 1, details: {"primaryKey":"sheep"}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, }
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, batch_uid: 0, status: succeeded, details: { primary_key: Some("mouse") }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
@@ -42,7 +43,7 @@ catto: { number_of_documents: 0, field_distribution: {} }
 [timestamp] [0,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"primaryKey":"mouse"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":1}}, stop reason: "created batch containing only task with id 0 of type `indexCreation` that cannot be batched with any other task.", }
+0 {uid: 0, details: {"primaryKey":"mouse"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":1}}, }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

crates/index-scheduler/src/queue/snapshots/batches_test.rs/query_batches_simple/end.snap

@@ -1,5 +1,6 @@
 ---
 source: crates/index-scheduler/src/queue/batches_test.rs
+snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -47,9 +48,9 @@ doggo: { number_of_documents: 0, field_distribution: {} }
 [timestamp] [2,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"primaryKey":"mouse"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":1}}, stop reason: "created batch containing only task with id 0 of type `indexCreation` that cannot be batched with any other task.", }
+0 {uid: 0, details: {"primaryKey":"mouse"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":1}}, }
-1 {uid: 1, details: {"primaryKey":"sheep"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, stop reason: "created batch containing only task with id 1 of type `indexCreation` that cannot be batched with any other task.", }
+1 {uid: 1, details: {"primaryKey":"sheep"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, }
-2 {uid: 2, details: {"primaryKey":"fish"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"indexCreation":1},"indexUids":{"whalo":1}}, stop reason: "created batch containing only task with id 2 of type `indexCreation` that cannot be batched with any other task.", }
+2 {uid: 2, details: {"primaryKey":"fish"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"indexCreation":1},"indexUids":{"whalo":1}}, }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

crates/index-scheduler/src/queue/snapshots/batches_test.rs/query_batches_special_rules/after-processing-everything.snap

@@ -1,5 +1,6 @@
 ---
 source: crates/index-scheduler/src/queue/batches_test.rs
+snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -52,10 +53,10 @@ doggo: { number_of_documents: 0, field_distribution: {} }
 [timestamp] [3,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"primaryKey":"mouse"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":1}}, stop reason: "created batch containing only task with id 0 of type `indexCreation` that cannot be batched with any other task.", }
+0 {uid: 0, details: {"primaryKey":"mouse"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":1}}, }
-1 {uid: 1, details: {"primaryKey":"sheep"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, stop reason: "created batch containing only task with id 1 of type `indexCreation` that cannot be batched with any other task.", }
+1 {uid: 1, details: {"primaryKey":"sheep"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, }
-2 {uid: 2, details: {"swaps":[{"indexes":["catto","doggo"]}]}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"indexSwap":1},"indexUids":{}}, stop reason: "created batch containing only task with id 2 of type `indexSwap` that cannot be batched with any other task.", }
+2 {uid: 2, details: {"swaps":[{"indexes":["catto","doggo"]}]}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"indexSwap":1},"indexUids":{}}, }
-3 {uid: 3, details: {"swaps":[{"indexes":["catto","whalo"]}]}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"indexSwap":1},"indexUids":{}}, stop reason: "created batch containing only task with id 3 of type `indexSwap` that cannot be batched with any other task.", }
+3 {uid: 3, details: {"swaps":[{"indexes":["catto","whalo"]}]}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"indexSwap":1},"indexUids":{}}, }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

crates/index-scheduler/src/queue/snapshots/tasks_test.rs/query_tasks_canceled_by/start.snap

@@ -1,5 +1,6 @@
 ---
 source: crates/index-scheduler/src/queue/tasks_test.rs
+snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -48,8 +49,8 @@ catto: { number_of_documents: 0, field_distribution: {} }
 [timestamp] [1,2,3,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"primaryKey":"mouse"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":1}}, stop reason: "created batch containing only task with id 0 of type `indexCreation` that cannot be batched with any other task.", }
+0 {uid: 0, details: {"primaryKey":"mouse"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":1}}, }
-1 {uid: 1, details: {"primaryKey":"sheep","matchedTasks":3,"canceledTasks":2,"originalFilter":"test_query","swaps":[{"indexes":["catto","doggo"]}]}, stats: {"totalNbTasks":3,"status":{"succeeded":1,"canceled":2},"types":{"indexCreation":1,"indexSwap":1,"taskCancelation":1},"indexUids":{"doggo":1}}, stop reason: "created batch containing only task with id 3 of type `taskCancelation` that cannot be batched with any other task.", }
+1 {uid: 1, details: {"primaryKey":"sheep","matchedTasks":3,"canceledTasks":2,"originalFilter":"test_query","swaps":[{"indexes":["catto","doggo"]}]}, stats: {"totalNbTasks":3,"status":{"succeeded":1,"canceled":2},"types":{"indexCreation":1,"indexSwap":1,"taskCancelation":1},"indexUids":{"doggo":1}}, }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

crates/index-scheduler/src/queue/snapshots/tasks_test.rs/query_tasks_from_and_limit/processed_all_tasks.snap

@@ -1,5 +1,6 @@
 ---
 source: crates/index-scheduler/src/queue/tasks_test.rs
+snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -47,9 +48,9 @@ whalo: { number_of_documents: 0, field_distribution: {} }
 [timestamp] [2,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"primaryKey":"bone"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, stop reason: "created batch containing only task with id 0 of type `indexCreation` that cannot be batched with any other task.", }
+0 {uid: 0, details: {"primaryKey":"bone"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, }
-1 {uid: 1, details: {"primaryKey":"plankton"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"whalo":1}}, stop reason: "created batch containing only task with id 1 of type `indexCreation` that cannot be batched with any other task.", }
+1 {uid: 1, details: {"primaryKey":"plankton"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"whalo":1}}, }
-2 {uid: 2, details: {"primaryKey":"his_own_vomit"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":1}}, stop reason: "created batch containing only task with id 2 of type `indexCreation` that cannot be batched with any other task.", }
+2 {uid: 2, details: {"primaryKey":"his_own_vomit"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":1}}, }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

crates/index-scheduler/src/queue/snapshots/tasks_test.rs/query_tasks_simple/end.snap

@@ -1,5 +1,6 @@
 ---
 source: crates/index-scheduler/src/queue/tasks_test.rs
+snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -47,9 +48,9 @@ doggo: { number_of_documents: 0, field_distribution: {} }
 [timestamp] [2,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"primaryKey":"mouse"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":1}}, stop reason: "created batch containing only task with id 0 of type `indexCreation` that cannot be batched with any other task.", }
+0 {uid: 0, details: {"primaryKey":"mouse"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":1}}, }
-1 {uid: 1, details: {"primaryKey":"sheep"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, stop reason: "created batch containing only task with id 1 of type `indexCreation` that cannot be batched with any other task.", }
+1 {uid: 1, details: {"primaryKey":"sheep"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, }
-2 {uid: 2, details: {"primaryKey":"fish"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"indexCreation":1},"indexUids":{"whalo":1}}, stop reason: "created batch containing only task with id 2 of type `indexCreation` that cannot be batched with any other task.", }
+2 {uid: 2, details: {"primaryKey":"fish"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"indexCreation":1},"indexUids":{"whalo":1}}, }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

crates/index-scheduler/src/queue/tasks.rs

@@ -1,7 +1,7 @@
 use std::ops::{Bound, RangeBounds};
 
 use meilisearch_types::heed::types::{DecodeIgnore, SerdeBincode, SerdeJson, Str};
-use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn, WithoutTls};
+use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn};
 use meilisearch_types::milli::{CboRoaringBitmapCodec, RoaringBitmapCodec, BEU32};
 use meilisearch_types::tasks::{Kind, Status, Task};
 use roaring::{MultiOps, RoaringBitmap};
@@ -9,17 +9,12 @@ use time::OffsetDateTime;
 
 use super::{Query, Queue};
 use crate::processing::ProcessingTasks;
-use crate::utils::{
+use crate::utils::{self, insert_task_datetime, keep_ids_within_datetimes, map_bound};
-    self, insert_task_datetime, keep_ids_within_datetimes, map_bound, remove_task_datetime,
-};
 use crate::{Error, Result, TaskId, BEI128};
 
-/// The number of database used by the task queue
-const NUMBER_OF_DATABASES: u32 = 8;
 /// Database const names for the `IndexScheduler`.
 mod db_name {
     pub const ALL_TASKS: &str = "all-tasks";
-
     pub const STATUS: &str = "status";
     pub const KIND: &str = "kind";
     pub const INDEX_TASKS: &str = "index-tasks";
@@ -64,11 +59,7 @@ impl TaskQueue {
         }
     }
 
-    pub(crate) const fn nb_db() -> u32 {
+    pub(super) fn new(env: &Env, wtxn: &mut RwTxn) -> Result<Self> {
-        NUMBER_OF_DATABASES
-    }
-
-    pub(crate) fn new(env: &Env<WithoutTls>, wtxn: &mut RwTxn) -> Result<Self> {
         Ok(Self {
             all_tasks: env.create_database(wtxn, Some(db_name::ALL_TASKS))?,
             status: env.create_database(wtxn, Some(db_name::STATUS))?,
@@ -99,14 +90,12 @@ impl TaskQueue {
 
     pub(crate) fn update_task(&self, wtxn: &mut RwTxn, task: &Task) -> Result<()> {
         let old_task = self.get_task(wtxn, task.uid)?.ok_or(Error::CorruptedTaskQueue)?;
-        let reprocessing = old_task.status != Status::Enqueued;
 
         debug_assert!(old_task != *task);
         debug_assert_eq!(old_task.uid, task.uid);
-
+        debug_assert!(old_task.batch_uid.is_none() && task.batch_uid.is_some());
-        // If we're processing a task that failed it may already contains a batch_uid
         debug_assert!(
-            reprocessing || (old_task.batch_uid.is_none() && task.batch_uid.is_some()),
+            old_task.batch_uid.is_none() && task.batch_uid.is_some(),
             "\n==> old: {old_task:?}\n==> new: {task:?}"
         );
 
@@ -133,25 +122,13 @@ impl TaskQueue {
             "Cannot update a task's enqueued_at time"
         );
         if old_task.started_at != task.started_at {
-            assert!(
+            assert!(old_task.started_at.is_none(), "Cannot update a task's started_at time");
-                reprocessing || old_task.started_at.is_none(),
-                "Cannot update a task's started_at time"
-            );
-            if let Some(started_at) = old_task.started_at {
-                remove_task_datetime(wtxn, self.started_at, started_at, task.uid)?;
-            }
             if let Some(started_at) = task.started_at {
                 insert_task_datetime(wtxn, self.started_at, started_at, task.uid)?;
             }
         }
         if old_task.finished_at != task.finished_at {
-            assert!(
+            assert!(old_task.finished_at.is_none(), "Cannot update a task's finished_at time");
-                reprocessing || old_task.finished_at.is_none(),
-                "Cannot update a task's finished_at time"
-            );
-            if let Some(finished_at) = old_task.finished_at {
-                remove_task_datetime(wtxn, self.finished_at, finished_at, task.uid)?;
-            }
             if let Some(finished_at) = task.finished_at {
                 insert_task_datetime(wtxn, self.finished_at, finished_at, task.uid)?;
             }
@@ -315,7 +292,7 @@ impl Queue {
         if let Some(batch_uids) = batch_uids {
             let mut batch_tasks = RoaringBitmap::new();
             for batch_uid in batch_uids {
-                if processing_batch.as_ref().is_some_and(|batch| batch.uid == *batch_uid) {
+                if processing_batch.as_ref().map_or(false, |batch| batch.uid == *batch_uid) {
                     batch_tasks |= &**processing_tasks;
                 } else {
                     batch_tasks |= self.tasks_in_batch(rtxn, *batch_uid)?;

crates/index-scheduler/src/queue/test.rs

@@ -165,7 +165,6 @@ fn test_disable_auto_deletion_of_tasks() {
     let (index_scheduler, mut handle) = IndexScheduler::test_with_custom_config(vec![], |config| {
         config.cleanup_enabled = false;
         config.max_number_of_tasks = 2;
-        None
     });
 
     index_scheduler
@@ -229,7 +228,6 @@ fn test_disable_auto_deletion_of_tasks() {
 fn test_auto_deletion_of_tasks() {
     let (index_scheduler, mut handle) = IndexScheduler::test_with_custom_config(vec![], |config| {
         config.max_number_of_tasks = 2;
-        None
     });
 
     index_scheduler
@@ -326,8 +324,7 @@ fn test_auto_deletion_of_tasks() {
 fn test_task_queue_is_full() {
     let (index_scheduler, mut handle) = IndexScheduler::test_with_custom_config(vec![], |config| {
         // that's the minimum map size possible
-        config.task_db_size = 1048576 * 3;
+        config.task_db_size = 1048576;
-        None
     });
 
     index_scheduler
@@ -364,7 +361,7 @@ fn test_task_queue_is_full() {
     // we won't be able to test this error in an integration test thus as a best effort test I still ensure the error return the expected error code
     snapshot!(format!("{:?}", result.error_code()), @"NoSpaceLeftOnDevice");
 
-    // Even the task deletion and cancelation that don't delete anything should be refused
+    // Even the task deletion that doesn't delete anything shouldn't be accepted
     let result = index_scheduler
         .register(
             KindWithContent::TaskDeletion { query: S("test"), tasks: RoaringBitmap::new() },
@@ -373,39 +370,10 @@ fn test_task_queue_is_full() {
         )
         .unwrap_err();
     snapshot!(result, @"Meilisearch cannot receive write operations because the limit of the task database has been reached. Please delete tasks to continue performing write operations.");
-    let result = index_scheduler
-        .register(
-            KindWithContent::TaskCancelation { query: S("test"), tasks: RoaringBitmap::new() },
-            None,
-            false,
-        )
-        .unwrap_err();
-    snapshot!(result, @"Meilisearch cannot receive write operations because the limit of the task database has been reached. Please delete tasks to continue performing write operations.");
-
     // we won't be able to test this error in an integration test thus as a best effort test I still ensure the error return the expected error code
     snapshot!(format!("{:?}", result.error_code()), @"NoSpaceLeftOnDevice");
 
-    // But a task cancelation that cancel something should work
+    // But a task deletion that delete something should works
-    index_scheduler
-        .register(
-            KindWithContent::TaskCancelation { query: S("test"), tasks: (0..100).collect() },
-            None,
-            false,
-        )
-        .unwrap();
-    handle.advance_one_successful_batch();
-
-    // But we should still be forbidden from enqueuing new tasks
-    let result = index_scheduler
-        .register(
-            KindWithContent::IndexCreation { index_uid: S("doggo"), primary_key: None },
-            None,
-            false,
-        )
-        .unwrap_err();
-    snapshot!(result, @"Meilisearch cannot receive write operations because the limit of the task database has been reached. Please delete tasks to continue performing write operations.");
-
-    // And a task deletion that delete something should works
     index_scheduler
         .register(
             KindWithContent::TaskDeletion { query: S("test"), tasks: (0..100).collect() },

crates/index-scheduler/src/scheduler/autobatcher.rs

@@ -7,7 +7,10 @@ The main function of the autobatcher is [`next_autobatch`].
 
 use std::ops::ControlFlow::{self, Break, Continue};
 
-use meilisearch_types::tasks::{BatchStopReason, PrimaryKeyMismatchReason, TaskId};
+use meilisearch_types::milli::update::IndexDocumentsMethod::{
+    self, ReplaceDocuments, UpdateDocuments,
+};
+use meilisearch_types::tasks::TaskId;
 
 use crate::KindWithContent;
 
@@ -16,11 +19,19 @@ use crate::KindWithContent;
 ///
 /// Only the non-prioritised tasks that can be grouped in a batch have a corresponding [`AutobatchKind`]
 enum AutobatchKind {
-    DocumentImport { allow_index_creation: bool, primary_key: Option<String> },
+    DocumentImport {
+        method: IndexDocumentsMethod,
+        allow_index_creation: bool,
+        primary_key: Option<String>,
+    },
     DocumentEdition,
-    DocumentDeletion { by_filter: bool },
+    DocumentDeletion {
+        by_filter: bool,
+    },
     DocumentClear,
-    Settings { allow_index_creation: bool },
+    Settings {
+        allow_index_creation: bool,
+    },
     IndexCreation,
     IndexDeletion,
     IndexUpdate,
@@ -49,8 +60,11 @@ impl From<KindWithContent> for AutobatchKind {
     fn from(kind: KindWithContent) -> Self {
         match kind {
             KindWithContent::DocumentAdditionOrUpdate {
-                allow_index_creation, primary_key, ..
+                method,
-            } => AutobatchKind::DocumentImport { allow_index_creation, primary_key },
+                allow_index_creation,
+                primary_key,
+                ..
+            } => AutobatchKind::DocumentImport { method, allow_index_creation, primary_key },
             KindWithContent::DocumentEdition { .. } => AutobatchKind::DocumentEdition,
             KindWithContent::DocumentDeletion { .. } => {
                 AutobatchKind::DocumentDeletion { by_filter: false }
@@ -71,8 +85,6 @@ impl From<KindWithContent> for AutobatchKind {
             KindWithContent::TaskCancelation { .. }
             | KindWithContent::TaskDeletion { .. }
             | KindWithContent::DumpCreation { .. }
-            | KindWithContent::Export { .. }
-            | KindWithContent::UpgradeDatabase { .. }
             | KindWithContent::SnapshotCreation => {
                 panic!("The autobatcher should never be called with tasks that don't apply to an index.")
             }
@@ -86,6 +98,7 @@ pub enum BatchKind {
         ids: Vec<TaskId>,
     },
     DocumentOperation {
+        method: IndexDocumentsMethod,
         allow_index_creation: bool,
         primary_key: Option<String>,
         operation_ids: Vec<TaskId>,
@@ -147,48 +160,23 @@ impl BatchKind {
     // TODO use an AutoBatchKind as input
     pub fn new(
         task_id: TaskId,
-        kind_with_content: KindWithContent,
+        kind: KindWithContent,
         primary_key: Option<&str>,
-    ) -> (ControlFlow<(BatchKind, BatchStopReason), BatchKind>, bool) {
+    ) -> (ControlFlow<BatchKind, BatchKind>, bool) {
         use AutobatchKind as K;
 
-        let kind = kind_with_content.as_kind();
+        match AutobatchKind::from(kind) {
-
+            K::IndexCreation => (Break(BatchKind::IndexCreation { id: task_id }), true),
-        match AutobatchKind::from(kind_with_content) {
+            K::IndexDeletion => (Break(BatchKind::IndexDeletion { ids: vec![task_id] }), false),
-            K::IndexCreation => (
+            K::IndexUpdate => (Break(BatchKind::IndexUpdate { id: task_id }), false),
-                Break((
+            K::IndexSwap => (Break(BatchKind::IndexSwap { id: task_id }), false),
-                    BatchKind::IndexCreation { id: task_id },
-                    BatchStopReason::TaskCannotBeBatched { kind, id: task_id },
-                )),
-                true,
-            ),
-            K::IndexDeletion => (
-                Break((
-                    BatchKind::IndexDeletion { ids: vec![task_id] },
-                    BatchStopReason::IndexDeletion { id: task_id },
-                )),
-                false,
-            ),
-            K::IndexUpdate => (
-                Break((
-                    BatchKind::IndexUpdate { id: task_id },
-                    BatchStopReason::TaskCannotBeBatched { kind, id: task_id },
-                )),
-                false,
-            ),
-            K::IndexSwap => (
-                Break((
-                    BatchKind::IndexSwap { id: task_id },
-                    BatchStopReason::TaskCannotBeBatched { kind, id: task_id },
-                )),
-                false,
-            ),
             K::DocumentClear => (Continue(BatchKind::DocumentClear { ids: vec![task_id] }), false),
-            K::DocumentImport { allow_index_creation, primary_key: pk }
+            K::DocumentImport { method, allow_index_creation, primary_key: pk }
                 if primary_key.is_none() || pk.is_none() || primary_key == pk.as_deref() =>
             {
                 (
                     Continue(BatchKind::DocumentOperation {
+                        method,
                         allow_index_creation,
                         primary_key: pk,
                         operation_ids: vec![task_id],
@@ -197,28 +185,16 @@ impl BatchKind {
                 )
             }
             // if the primary key set in the task was different than ours we should stop and make this batch fail asap.
-            K::DocumentImport { allow_index_creation, primary_key: pk } => (
+            K::DocumentImport { method, allow_index_creation, primary_key } => (
-                Break((
+                Break(BatchKind::DocumentOperation {
-                    BatchKind::DocumentOperation {
+                    method,
-                        allow_index_creation,
+                    allow_index_creation,
-                        primary_key: pk.clone(),
+                    primary_key,
-                        operation_ids: vec![task_id],
+                    operation_ids: vec![task_id],
-                    },
+                }),
-                    BatchStopReason::PrimaryKeyIndexMismatch {
-                        id: task_id,
-                        in_index: primary_key.unwrap().to_owned(),
-                        in_task: pk.unwrap(),
-                    },
-                )),
                 allow_index_creation,
             ),
-            K::DocumentEdition => (
+            K::DocumentEdition => (Break(BatchKind::DocumentEdition { id: task_id }), false),
-                Break((
-                    BatchKind::DocumentEdition { id: task_id },
-                    BatchStopReason::TaskCannotBeBatched { kind, id: task_id },
-                )),
-                false,
-            ),
             K::DocumentDeletion { by_filter: includes_by_filter } => (
                 Continue(BatchKind::DocumentDeletion {
                     deletion_ids: vec![task_id],
@@ -238,71 +214,54 @@ impl BatchKind {
     /// To ease the writing of the code. `true` can be returned when you don't need to create an index
     /// but false can't be returned if you needs to create an index.
     #[rustfmt::skip]
-    fn accumulate(self, id: TaskId, kind_with_content: KindWithContent, index_already_exists: bool, primary_key: Option<&str>) -> ControlFlow<(BatchKind, BatchStopReason), BatchKind> {
+    fn accumulate(self, id: TaskId, kind: AutobatchKind, index_already_exists: bool, primary_key: Option<&str>) -> ControlFlow<BatchKind, BatchKind> {
         use AutobatchKind as K;
 
-        let kind = kind_with_content.as_kind();
+        match (self, kind) {
-        let autobatch_kind = AutobatchKind::from(kind_with_content);
-
-        let pk: Option<String> = match (self.primary_key(), autobatch_kind.primary_key(), primary_key) {
-            // 1. If incoming task don't interact with primary key -> we can continue
-            (batch_pk, None | Some(None), _) => {
-                batch_pk.flatten().map(ToOwned::to_owned)
-            },
-            // 2.1 If we already have a primary-key ->
-            // 2.1.1 If the task we're trying to accumulate have a pk it must be equal to our primary key
-            (_batch_pk, Some(Some(task_pk)), Some(index_pk)) => if task_pk == index_pk {
-                Some(task_pk.to_owned())
-            } else {
-                return Break((self, BatchStopReason::PrimaryKeyMismatch {
-                    id,
-                    reason: PrimaryKeyMismatchReason::TaskPrimaryKeyDifferFromIndexPrimaryKey {
-                        task_pk: task_pk.to_owned(),
-                        index_pk: index_pk.to_owned(),
-                    },
-                }))
-            },
-            // 2.2 If we don't have a primary-key ->
-            // 2.2.2 If the batch is set to Some(None), the task should be too
-            (Some(None), Some(Some(task_pk)), None) => return Break((self, BatchStopReason::PrimaryKeyMismatch {
-                id,
-                reason: PrimaryKeyMismatchReason::CannotInterfereWithPrimaryKeyGuessing {
-                    task_pk: task_pk.to_owned(),
-                },
-            })),
-            (Some(Some(batch_pk)), Some(Some(task_pk)), None) => if task_pk == batch_pk {
-                Some(task_pk.to_owned())
-            } else {
-                let batch_pk = batch_pk.to_owned();
-                let task_pk = task_pk.to_owned();
-                return Break((self, BatchStopReason::PrimaryKeyMismatch {
-                    id,
-                    reason: PrimaryKeyMismatchReason::TaskPrimaryKeyDifferFromCurrentBatchPrimaryKey {
-                        batch_pk,
-                        task_pk
-                    },
-                }))
-            },
-            (None, Some(Some(task_pk)), None) => Some(task_pk.to_owned())
-        };
-
-        match (self, autobatch_kind) {
             // We don't batch any of these operations
-            (this, K::IndexCreation | K::IndexUpdate | K::IndexSwap | K::DocumentEdition) => Break((this, BatchStopReason::TaskCannotBeBatched { kind, id })),
+            (this, K::IndexCreation | K::IndexUpdate | K::IndexSwap | K::DocumentEdition) => Break(this),
             // We must not batch tasks that don't have the same index creation rights if the index doesn't already exists.
             (this, kind) if !index_already_exists && this.allow_index_creation() == Some(false) && kind.allow_index_creation() == Some(true) => {
-                Break((this, BatchStopReason::IndexCreationMismatch { id }))
+                Break(this)
+            },
+            // NOTE: We need to negate the whole condition since we're checking if we need to break instead of continue.
+            //       I wrote it this way because it's easier to understand than the other way around.
+            (this, kind) if !(
+                // 1. If both task don't interact with primary key -> we can continue
+                (this.primary_key().is_none() && kind.primary_key().is_none()) ||
+                // 2. Else ->
+                (
+                    // 2.1 If we already have a primary-key ->
+                    (
+                        primary_key.is_some() &&
+                        // 2.1.1 If the task we're trying to accumulate have a pk it must be equal to our primary key
+                        // 2.1.2 If the task don't have a primary-key -> we can continue
+                        kind.primary_key().map_or(true, |pk| pk == primary_key)
+                    ) ||
+                    // 2.2 If we don't have a primary-key ->
+                    (
+                        // 2.2.1 If both the batch and the task have a primary key they should be equal
+                        // 2.2.2 If the batch is set to Some(None), the task should be too
+                        // 2.2.3 If the batch is set to None -> we can continue
+                        this.primary_key().zip(kind.primary_key()).map_or(true, |(this, kind)| this == kind)
+                    )
+                )
+
+                ) // closing the negation
+
+            => {
+                Break(this)
             },
             // The index deletion can batch with everything but must stop after
             (
                 BatchKind::DocumentClear { mut ids }
                 | BatchKind::DocumentDeletion { deletion_ids: mut ids, includes_by_filter: _ }
-                | BatchKind::DocumentOperation { allow_index_creation: _, primary_key: _, operation_ids: mut ids }
+                | BatchKind::DocumentOperation { method: _, allow_index_creation: _, primary_key: _, operation_ids: mut ids }
                 | BatchKind::Settings { allow_index_creation: _, settings_ids: mut ids },
                 K::IndexDeletion,
             ) => {
                 ids.push(id);
-                Break((BatchKind::IndexDeletion { ids }, BatchStopReason::IndexDeletion { id }))
+                Break(BatchKind::IndexDeletion { ids })
             }
             (
                 BatchKind::ClearAndSettings { settings_ids: mut ids, allow_index_creation: _, mut other },
@@ -310,7 +269,7 @@ impl BatchKind {
             ) => {
                 ids.push(id);
                 ids.append(&mut other);
-                Break((BatchKind::IndexDeletion { ids }, BatchStopReason::IndexDeletion { id }))
+                Break(BatchKind::IndexDeletion { ids })
             }
 
             (
@@ -323,37 +282,51 @@ impl BatchKind {
             (
                 this @ BatchKind::DocumentClear { .. },
                 K::DocumentImport { .. } | K::Settings { .. },
-            ) => Break((this, BatchStopReason::DocumentOperationWithSettings { id })),
+            ) => Break(this),
             (
-                BatchKind::DocumentOperation { allow_index_creation: _, primary_key: _, mut operation_ids },
+                BatchKind::DocumentOperation { method: _, allow_index_creation: _, primary_key: _, mut operation_ids },
                 K::DocumentClear,
             ) => {
                 operation_ids.push(id);
                 Continue(BatchKind::DocumentClear { ids: operation_ids })
             }
 
-            // we can autobatch different kind of document operations and mix replacements with updates
+            // we can autobatch the same kind of document additions / updates
             (
-                BatchKind::DocumentOperation { allow_index_creation, primary_key: _, mut operation_ids },
+                BatchKind::DocumentOperation { method: ReplaceDocuments, allow_index_creation, primary_key: _, mut operation_ids },
-                K::DocumentImport { primary_key: _, .. },
+                K::DocumentImport { method: ReplaceDocuments, primary_key: pk, .. },
             ) => {
                 operation_ids.push(id);
                 Continue(BatchKind::DocumentOperation {
+                    method: ReplaceDocuments,
                     allow_index_creation,
                     operation_ids,
                     primary_key: pk,
                 })
             }
             (
-                BatchKind::DocumentOperation { allow_index_creation, primary_key: _, mut operation_ids },
+                BatchKind::DocumentOperation { method: UpdateDocuments, allow_index_creation, primary_key: _, mut operation_ids },
+                K::DocumentImport { method: UpdateDocuments, primary_key: pk, .. },
+            ) => {
+                operation_ids.push(id);
+                Continue(BatchKind::DocumentOperation {
+                    method: UpdateDocuments,
+                    allow_index_creation,
+                    primary_key: pk,
+                    operation_ids,
+                })
+            }
+            (
+                BatchKind::DocumentOperation { method, allow_index_creation, primary_key, mut operation_ids },
                 K::DocumentDeletion { by_filter: false },
             ) => {
                 operation_ids.push(id);
 
                 Continue(BatchKind::DocumentOperation {
+                    method,
                     allow_index_creation,
+                    primary_key,
                     operation_ids,
-                    primary_key: pk,
                 })
             }
             // We can't batch a document operation with a delete by filter
@@ -361,12 +334,19 @@ impl BatchKind {
                 this @ BatchKind::DocumentOperation { .. },
                 K::DocumentDeletion { by_filter: true },
             ) => {
-                Break((this, BatchStopReason::DocumentOperationWithDeletionByFilter { id }))
+                Break(this)
             }
+            // but we can't autobatch documents if it's not the same kind
+            // this match branch MUST be AFTER the previous one
+            (
+                this @ BatchKind::DocumentOperation { .. },
+                K::DocumentImport { .. },
+            ) => Break(this),
+
             (
                 this @ BatchKind::DocumentOperation { .. },
                 K::Settings { .. },
-            ) => Break((this, BatchStopReason::DocumentOperationWithSettings { id })),
+            ) => Break(this),
 
             (BatchKind::DocumentDeletion { mut deletion_ids, includes_by_filter: _ }, K::DocumentClear) => {
                 deletion_ids.push(id);
@@ -376,15 +356,16 @@ impl BatchKind {
             (
                 this @ BatchKind::DocumentDeletion { deletion_ids: _, includes_by_filter: true },
                 K::DocumentImport { .. }
-            ) => Break((this, BatchStopReason::DeletionByFilterWithDocumentOperation { id })),
+            ) => Break(this),
             // we can autobatch the deletion and import if the index already exists
             (
                 BatchKind::DocumentDeletion { mut deletion_ids, includes_by_filter: false },
-                K::DocumentImport { allow_index_creation, primary_key }
+                K::DocumentImport { method, allow_index_creation, primary_key }
             ) if index_already_exists => {
                 deletion_ids.push(id);
 
                 Continue(BatchKind::DocumentOperation {
+                    method,
                     allow_index_creation,
                     primary_key,
                     operation_ids: deletion_ids,
@@ -393,28 +374,29 @@ impl BatchKind {
             // we can autobatch the deletion and import if both can't create an index
             (
                 BatchKind::DocumentDeletion { mut deletion_ids, includes_by_filter: false },
-                K::DocumentImport { allow_index_creation, primary_key }
+                K::DocumentImport { method, allow_index_creation, primary_key }
             ) if !allow_index_creation => {
                 deletion_ids.push(id);
 
                 Continue(BatchKind::DocumentOperation {
+                    method,
                     allow_index_creation,
                     primary_key,
                     operation_ids: deletion_ids,
                 })
             }
-            // we can't autobatch a deletion and an import if the index does not exist but would be created by an addition
+            // we can't autobatch a deletion and an import if the index does not exists but would be created by an addition
             (
                 this @ BatchKind::DocumentDeletion { .. },
                 K::DocumentImport { .. }
             ) => {
-                Break((this, BatchStopReason::IndexCreationMismatch { id }))
+                Break(this)
             }
             (BatchKind::DocumentDeletion { mut deletion_ids, includes_by_filter }, K::DocumentDeletion { by_filter }) => {
                 deletion_ids.push(id);
                 Continue(BatchKind::DocumentDeletion { deletion_ids, includes_by_filter: includes_by_filter | by_filter })
             }
-            (this @ BatchKind::DocumentDeletion { .. }, K::Settings { .. }) => Break((this, BatchStopReason::DocumentOperationWithSettings { id })),
+            (this @ BatchKind::DocumentDeletion { .. }, K::Settings { .. }) => Break(this),
 
             (
                 BatchKind::Settings { settings_ids, allow_index_creation },
@@ -427,7 +409,7 @@ impl BatchKind {
             (
                 this @ BatchKind::Settings { .. },
                 K::DocumentImport { .. } | K::DocumentDeletion { .. },
-            ) => Break((this, BatchStopReason::SettingsWithDocumentOperation { id })),
+            ) => Break(this),
             (
                 BatchKind::Settings { mut settings_ids, allow_index_creation },
                 K::Settings { .. },
@@ -450,7 +432,7 @@ impl BatchKind {
                     allow_index_creation,
                 })
             }
-            (this @ BatchKind::ClearAndSettings { .. }, K::DocumentImport { .. }) => Break((this, BatchStopReason::SettingsWithDocumentOperation { id })),
+            (this @ BatchKind::ClearAndSettings { .. }, K::DocumentImport { .. }) => Break(this),
             (
                 BatchKind::ClearAndSettings {
                     mut other,
@@ -506,7 +488,7 @@ pub fn autobatch(
     enqueued: Vec<(TaskId, KindWithContent)>,
     index_already_exists: bool,
     primary_key: Option<&str>,
-) -> Option<(BatchKind, bool, Option<BatchStopReason>)> {
+) -> Option<(BatchKind, bool)> {
     let mut enqueued = enqueued.into_iter();
     let (id, kind) = enqueued.next()?;
 
@@ -515,22 +497,18 @@ pub fn autobatch(
 
     let (mut acc, must_create_index) = match BatchKind::new(id, kind, primary_key) {
         (Continue(acc), create) => (acc, create),
-        (Break((acc, batch_stop_reason)), create) => {
+        (Break(acc), create) => return Some((acc, create)),
-            return Some((acc, create, Some(batch_stop_reason)))
-        }
     };
 
     // if an index has been created in the previous step we can consider it as existing.
     index_exist |= must_create_index;
 
-    for (id, kind_with_content) in enqueued {
+    for (id, kind) in enqueued {
-        acc = match acc.accumulate(id, kind_with_content, index_exist, primary_key) {
+        acc = match acc.accumulate(id, kind.into(), index_exist, primary_key) {
             Continue(acc) => acc,
-            Break((acc, batch_stop_reason)) => {
+            Break(acc) => return Some((acc, must_create_index)),
-                return Some((acc, must_create_index, Some(batch_stop_reason)))
-            }
         };
     }
 
-    Some((acc, must_create_index, None))
+    Some((acc, must_create_index))
 }

crates/index-scheduler/src/scheduler/autobatcher_test.rs

@@ -1,7 +1,7 @@
 use meilisearch_types::milli::update::IndexDocumentsMethod::{
     self, ReplaceDocuments, UpdateDocuments,
 };
-use meilisearch_types::tasks::{BatchStopReason, IndexSwap, KindWithContent};
+use meilisearch_types::tasks::{IndexSwap, KindWithContent};
 use uuid::Uuid;
 
 use self::autobatcher::{autobatch, BatchKind};
@@ -20,7 +20,7 @@ fn autobatch_from(
     index_already_exists: bool,
     primary_key: Option<&str>,
     input: impl IntoIterator<Item = KindWithContent>,
-) -> Option<(BatchKind, bool, Option<BatchStopReason>)> {
+) -> Option<(BatchKind, bool)> {
     autobatch(
         input.into_iter().enumerate().map(|(id, kind)| (id as TaskId, kind)).collect(),
         index_already_exists,
@@ -92,304 +92,304 @@ fn idx_swap() -> KindWithContent {
 fn autobatch_simple_operation_together() {
     // we can autobatch one or multiple `ReplaceDocuments` together.
     // if the index exists.
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0] }, false, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp( ReplaceDocuments, true , None), doc_imp(ReplaceDocuments, true , None)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0, 1, 2] }, true, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp( ReplaceDocuments, true , None), doc_imp(ReplaceDocuments, true , None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1, 2] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_imp( ReplaceDocuments, false , None), doc_imp(ReplaceDocuments, false , None)]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0, 1, 2] }, false, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_imp( ReplaceDocuments, false , None), doc_imp(ReplaceDocuments, false , None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1, 2] }, false))");
 
     // if it doesn't exists.
-    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, None))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0] }, false, None))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None), doc_imp( ReplaceDocuments, true , None), doc_imp(ReplaceDocuments, true , None)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0, 1, 2] }, true, None))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None), doc_imp( ReplaceDocuments, true , None), doc_imp(ReplaceDocuments, true , None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1, 2] }, true))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None), doc_imp( ReplaceDocuments, true , None), doc_imp(ReplaceDocuments, true , None)]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0] }, false, Some(IndexCreationMismatch { id: 1 })))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None), doc_imp( ReplaceDocuments, true , None), doc_imp(ReplaceDocuments, true , None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
 
     // we can autobatch one or multiple `UpdateDocuments` together.
     // if the index exists.
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0, 1, 2] }, true, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1, 2] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0] }, false, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), doc_imp(UpdateDocuments, false, None), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0, 1, 2] }, false, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), doc_imp(UpdateDocuments, false, None), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1, 2] }, false))");
 
     // if it doesn't exists.
-    debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, None))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0, 1, 2] }, true, None))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1, 2] }, true))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0] }, false, None))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None), doc_imp(UpdateDocuments, false, None), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0, 1, 2] }, false, None))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None), doc_imp(UpdateDocuments, false, None), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1, 2] }, false))");
 
     // we can autobatch one or multiple DocumentDeletion together
-    debug_snapshot!(autobatch_from(true, None, [doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2], includes_by_filter: false }, false, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2], includes_by_filter: false }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false, None))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_del(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2], includes_by_filter: false }, false, None))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_del(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2], includes_by_filter: false }, false))");
 
     // we can autobatch one or multiple DocumentDeletionByFilter together
-    debug_snapshot!(autobatch_from(true, None, [doc_del_fil()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del_fil()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_del_fil(), doc_del_fil()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2], includes_by_filter: true }, false, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_del_fil(), doc_del_fil()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2], includes_by_filter: true }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_del_fil()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, None))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_del_fil()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_del_fil(), doc_del_fil(), doc_del_fil()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2], includes_by_filter: true }, false, None))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_del_fil(), doc_del_fil(), doc_del_fil()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2], includes_by_filter: true }, false))");
 
     // we can autobatch one or multiple Settings together
-    debug_snapshot!(autobatch_from(true, None, [settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0] }, true, None))");
+    debug_snapshot!(autobatch_from(true, None, [settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [settings(true), settings(true), settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0, 1, 2] }, true, None))");
+    debug_snapshot!(autobatch_from(true, None, [settings(true), settings(true), settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0, 1, 2] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0] }, false, None))");
+    debug_snapshot!(autobatch_from(true, None, [settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [settings(false), settings(false), settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0, 1, 2] }, false, None))");
+    debug_snapshot!(autobatch_from(true, None, [settings(false), settings(false), settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0, 1, 2] }, false))");
 
-    debug_snapshot!(autobatch_from(false,None,  [settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0] }, true, None))");
+    debug_snapshot!(autobatch_from(false,None,  [settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(false,None,  [settings(true), settings(true), settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0, 1, 2] }, true, None))");
+    debug_snapshot!(autobatch_from(false,None,  [settings(true), settings(true), settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0, 1, 2] }, true))");
-    debug_snapshot!(autobatch_from(false,None,  [settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0] }, false, None))");
+    debug_snapshot!(autobatch_from(false,None,  [settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [settings(false), settings(false), settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0, 1, 2] }, false, None))");
+    debug_snapshot!(autobatch_from(false,None,  [settings(false), settings(false), settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0, 1, 2] }, false))");
 
     // We can autobatch document addition with document deletion
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true, None))"###);
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true))"###);
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true, None))"###);
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true))"###);
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false, None))"###);
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false, None))"###);
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-    debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true, None))");
+    debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
-    debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true, None))");
+    debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
-    debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false, None))");
+    debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false, None))");
+    debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, None), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true, None))"###);
+    debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true))"###);
-    debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true, None))"###);
+    debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, true))"###);
-    debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false, None))"###);
+    debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-    debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false, None))"###);
+    debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
     // And the other way around
-    debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, false, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, false, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, false, None))"###);
+    debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-    debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, Some("catto"))]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, false, None))"###);
+    debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, true, Some("catto"))]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-    debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false, None))"###);
+    debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-    debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false, None))"###);
+    debug_snapshot!(autobatch_from(true, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-    debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false, None))");
+    debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false, None))");
+    debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false, None))"###);
+    debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
-    debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false, None))"###);
+    debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false))"###);
 
     // But we can't autobatch document addition with document deletion by filter
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithDeletionByFilter { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithDeletionByFilter { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_del_fil()]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0] }, false, Some(DocumentOperationWithDeletionByFilter { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_del_fil()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), doc_del_fil()]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0] }, false, Some(DocumentOperationWithDeletionByFilter { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), doc_del_fil()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true, Some(DocumentOperationWithDeletionByFilter { id: 1 })))"###);
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true, Some(DocumentOperationWithDeletionByFilter { id: 1 })))"###);
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false, Some(DocumentOperationWithDeletionByFilter { id: 1 })))"###);
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false, Some(DocumentOperationWithDeletionByFilter { id: 1 })))"###);
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
-    debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithDeletionByFilter { id: 1 })))");
+    debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithDeletionByFilter { id: 1 })))");
+    debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, None), doc_del_fil()]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0] }, false, Some(DocumentOperationWithDeletionByFilter { id: 1 })))");
+    debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, None), doc_del_fil()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, None), doc_del_fil()]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0] }, false, Some(DocumentOperationWithDeletionByFilter { id: 1 })))");
+    debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, None), doc_del_fil()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true, Some(DocumentOperationWithDeletionByFilter { id: 1 })))"###);
+    debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, true, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
-    debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true, Some(DocumentOperationWithDeletionByFilter { id: 1 })))"###);
+    debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, true, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: Some("catto"), operation_ids: [0] }, true))"###);
-    debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false, Some(DocumentOperationWithDeletionByFilter { id: 1 })))"###);
+    debug_snapshot!(autobatch_from(false, None, [doc_imp(ReplaceDocuments, false, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
-    debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false, Some(DocumentOperationWithDeletionByFilter { id: 1 })))"###);
+    debug_snapshot!(autobatch_from(false, None, [doc_imp(UpdateDocuments, false, Some("catto")), doc_del_fil()]), @r###"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0] }, false))"###);
     // And the other way around
-    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, Some(DeletionByFilterWithDocumentOperation { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, Some(DeletionByFilterWithDocumentOperation { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, Some(DeletionByFilterWithDocumentOperation { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, Some(DeletionByFilterWithDocumentOperation { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, Some(DeletionByFilterWithDocumentOperation { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(UpdateDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, Some(DeletionByFilterWithDocumentOperation { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(UpdateDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, Some(DeletionByFilterWithDocumentOperation { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(UpdateDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, Some(DeletionByFilterWithDocumentOperation { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(UpdateDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
-    debug_snapshot!(autobatch_from(false, None, [doc_del_fil(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, Some(DeletionByFilterWithDocumentOperation { id: 1 })))");
+    debug_snapshot!(autobatch_from(false, None, [doc_del_fil(), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
-    debug_snapshot!(autobatch_from(false, None, [doc_del_fil(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, Some(DeletionByFilterWithDocumentOperation { id: 1 })))");
+    debug_snapshot!(autobatch_from(false, None, [doc_del_fil(), doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
-    debug_snapshot!(autobatch_from(false, None, [doc_del_fil(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, Some(DeletionByFilterWithDocumentOperation { id: 1 })))");
+    debug_snapshot!(autobatch_from(false, None, [doc_del_fil(), doc_imp(ReplaceDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
-    debug_snapshot!(autobatch_from(false, None, [doc_del_fil(), doc_imp(UpdateDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, Some(DeletionByFilterWithDocumentOperation { id: 1 })))");
+    debug_snapshot!(autobatch_from(false, None, [doc_del_fil(), doc_imp(UpdateDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
 }
 
 #[test]
-fn simple_different_document_operations_autobatch_together() {
+fn simple_document_operation_dont_autobatch_with_other() {
-    // addition and updates with deletion by filter can't batch together
+    // addition, updates and deletion by filter can't batch together
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithDeletionByFilter { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithDeletionByFilter { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_del_fil()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, Some(DeletionByFilterWithDocumentOperation { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, Some(DeletionByFilterWithDocumentOperation { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
 
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_create()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(TaskCannotBeBatched { kind: IndexCreation, id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_create()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_create()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(TaskCannotBeBatched { kind: IndexCreation, id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_create()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_create()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false, Some(TaskCannotBeBatched { kind: IndexCreation, id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_create()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), idx_create()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, Some(TaskCannotBeBatched { kind: IndexCreation, id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), idx_create()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
 
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_update()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(TaskCannotBeBatched { kind: IndexUpdate, id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_update()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_update()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(TaskCannotBeBatched { kind: IndexUpdate, id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_update()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_update()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false, Some(TaskCannotBeBatched { kind: IndexUpdate, id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_update()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), idx_update()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, Some(TaskCannotBeBatched { kind: IndexUpdate, id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), idx_update()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
 
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_swap()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(TaskCannotBeBatched { kind: IndexSwap, id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_swap()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_swap()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(TaskCannotBeBatched { kind: IndexSwap, id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_swap()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_swap()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false, Some(TaskCannotBeBatched { kind: IndexSwap, id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_swap()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), idx_swap()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, Some(TaskCannotBeBatched { kind: IndexSwap, id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), idx_swap()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false))");
 }
 
 #[test]
 fn document_addition_doesnt_batch_with_settings() {
     // simple case
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
 
     // multiple settings and doc addition
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None), settings(true), settings(true)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true, Some(DocumentOperationWithSettings { id: 2 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None), settings(true), settings(true)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None), settings(true), settings(true)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true, Some(DocumentOperationWithSettings { id: 2 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None), settings(true), settings(true)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
 
     // addition and setting unordered
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), doc_imp(ReplaceDocuments, true, None), settings(true)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), doc_imp(ReplaceDocuments, true, None), settings(true)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), doc_imp(UpdateDocuments, true, None), settings(true)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), doc_imp(UpdateDocuments, true, None), settings(true)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
 
     // Doesn't batch with other forbidden operations
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), doc_del()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), doc_del()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), doc_del()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), doc_del()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), idx_create()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), idx_create()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), idx_create()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), idx_create()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), idx_update()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), idx_update()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), idx_update()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), idx_update()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), idx_swap()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), idx_swap()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), idx_swap()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), idx_swap()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
 }
 
 #[test]
 fn clear_and_additions() {
     // these two doesn't need to batch
-    debug_snapshot!(autobatch_from(true, None, [doc_clr(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentClear { ids: [0] }, false, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_clr(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentClear { ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_clr(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentClear { ids: [0] }, false, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_clr(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentClear { ids: [0] }, false))");
 
     // Basic use case
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None), doc_clr()]), @"Some((DocumentClear { ids: [0, 1, 2] }, true, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None), doc_clr()]), @"Some((DocumentClear { ids: [0, 1, 2] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None), doc_clr()]), @"Some((DocumentClear { ids: [0, 1, 2] }, true, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None), doc_clr()]), @"Some((DocumentClear { ids: [0, 1, 2] }, true))");
 
     // This batch kind doesn't mix with other document addition
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None), doc_clr(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentClear { ids: [0, 1, 2] }, true, Some(DocumentOperationWithSettings { id: 3 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None), doc_clr(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentClear { ids: [0, 1, 2] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None), doc_clr(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentClear { ids: [0, 1, 2] }, true, Some(DocumentOperationWithSettings { id: 3 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None), doc_clr(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentClear { ids: [0, 1, 2] }, true))");
 
     // But you can batch multiple clear together
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None), doc_clr(), doc_clr(), doc_clr()]), @"Some((DocumentClear { ids: [0, 1, 2, 3, 4] }, true, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None), doc_clr(), doc_clr(), doc_clr()]), @"Some((DocumentClear { ids: [0, 1, 2, 3, 4] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None), doc_clr(), doc_clr(), doc_clr()]), @"Some((DocumentClear { ids: [0, 1, 2, 3, 4] }, true, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None), doc_clr(), doc_clr(), doc_clr()]), @"Some((DocumentClear { ids: [0, 1, 2, 3, 4] }, true))");
 }
 
 #[test]
 fn clear_and_additions_and_settings() {
     // A clear don't need to autobatch the settings that happens AFTER there is no documents
-    debug_snapshot!(autobatch_from(true, None, [doc_clr(), settings(true)]), @"Some((DocumentClear { ids: [0] }, false, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_clr(), settings(true)]), @"Some((DocumentClear { ids: [0] }, false))");
 
-    debug_snapshot!(autobatch_from(true, None, [settings(true), doc_clr(), settings(true)]), @"Some((ClearAndSettings { other: [1], allow_index_creation: true, settings_ids: [0, 2] }, true, None))");
+    debug_snapshot!(autobatch_from(true, None, [settings(true), doc_clr(), settings(true)]), @"Some((ClearAndSettings { other: [1], allow_index_creation: true, settings_ids: [0, 2] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), doc_clr()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true), doc_clr()]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), doc_clr()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), settings(true), doc_clr()]), @"Some((DocumentOperation { method: UpdateDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
 }
 
 #[test]
 fn anything_and_index_deletion() {
     // The `IndexDeletion` doesn't batch with anything that happens AFTER.
-    debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
+    debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
+    debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
+    debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
+    debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_del()]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
+    debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_del()]), @"Some((IndexDeletion { ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_del_fil()]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
+    debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_del_fil()]), @"Some((IndexDeletion { ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_clr()]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
+    debug_snapshot!(autobatch_from(true, None, [idx_del(), doc_clr()]), @"Some((IndexDeletion { ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [idx_del(), settings(true)]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
+    debug_snapshot!(autobatch_from(true, None, [idx_del(), settings(true)]), @"Some((IndexDeletion { ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [idx_del(), settings(false)]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
+    debug_snapshot!(autobatch_from(true, None, [idx_del(), settings(false)]), @"Some((IndexDeletion { ids: [0] }, false))");
 
-    debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
+    debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
+    debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
+    debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_imp(ReplaceDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
+    debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_imp(UpdateDocuments, false, None)]), @"Some((IndexDeletion { ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_del()]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
+    debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_del()]), @"Some((IndexDeletion { ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_del_fil()]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
+    debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_del_fil()]), @"Some((IndexDeletion { ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_clr()]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
+    debug_snapshot!(autobatch_from(false,None,  [idx_del(), doc_clr()]), @"Some((IndexDeletion { ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [idx_del(), settings(true)]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
+    debug_snapshot!(autobatch_from(false,None,  [idx_del(), settings(true)]), @"Some((IndexDeletion { ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [idx_del(), settings(false)]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
+    debug_snapshot!(autobatch_from(false,None,  [idx_del(), settings(false)]), @"Some((IndexDeletion { ids: [0] }, false))");
 
     // The index deletion can accept almost any type of `BatchKind` and transform it to an `IndexDeletion`.
     // First, the basic cases
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true, Some(IndexDeletion { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true, Some(IndexDeletion { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, true, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false, Some(IndexDeletion { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false, Some(IndexDeletion { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false, Some(IndexDeletion { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false, Some(IndexDeletion { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_del_fil(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false, Some(IndexDeletion { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true, Some(IndexDeletion { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false, Some(IndexDeletion { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
 
-    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true, Some(IndexDeletion { id: 1 })))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, true, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true, Some(IndexDeletion { id: 1 })))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, true, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false, Some(IndexDeletion { id: 1 })))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false, Some(IndexDeletion { id: 1 })))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_del(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false, Some(IndexDeletion { id: 1 })))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_del(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_del_fil(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false, Some(IndexDeletion { id: 1 })))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_del_fil(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false, Some(IndexDeletion { id: 1 })))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_clr(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true, Some(IndexDeletion { id: 1 })))");
+    debug_snapshot!(autobatch_from(false,None,  [settings(true), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true))");
-    debug_snapshot!(autobatch_from(false,None,  [settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false, Some(IndexDeletion { id: 1 })))");
+    debug_snapshot!(autobatch_from(false,None,  [settings(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false))");
 }
 
 #[test]
 fn allowed_and_disallowed_index_creation() {
     // `DocumentImport` can't be mixed with those disallowed to do so except if the index already exists.
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), settings(true)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), settings(true)]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0] }, false, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None), settings(true)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
 
-    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0] }, false, Some(IndexCreationMismatch { id: 1 })))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true, None))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false, None))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None), doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0, 1] }, false))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None), settings(true)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, true, None), settings(true)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None), settings(true)]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0] }, false, Some(IndexCreationMismatch { id: 1 })))");
+    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None), settings(true)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: false, primary_key: None, operation_ids: [0] }, false))");
 
     // batch deletion and addition
-    debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false, Some(IndexCreationMismatch { id: 1 })))");
+    debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))");
-    debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false, Some(IndexCreationMismatch { id: 1 })))");
+    debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, true, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))");
-    debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false, Some(IndexCreationMismatch { id: 1 })))");
+    debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))");
-    debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false, Some(IndexCreationMismatch { id: 1 })))");
+    debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))");
 }
 
 #[test]
 fn autobatch_primary_key() {
     // ==> If I have a pk
     // With a single update
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, None))");
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("id"), operation_ids: [0] }, true, None))"###);
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0] }, true))"###);
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other"))]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true, Some(PrimaryKeyIndexMismatch { id: 0, in_index: "id", in_task: "other" })))"###);
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true))"###);
 
     // With a multiple updates
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true, None))");
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("id"), operation_ids: [0, 1] }, true, None))"###);
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0, 1] }, true))"###);
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("id"), operation_ids: [0, 1, 2] }, true, None))"###);
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0, 1] }, true))"###);
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, Some("other"))]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(PrimaryKeyMismatch { id: 1, reason: TaskPrimaryKeyDifferFromIndexPrimaryKey { task_pk: "other", index_pk: "id" } })))"###);
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, Some("other"))]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(PrimaryKeyMismatch { id: 1, reason: TaskPrimaryKeyDifferFromIndexPrimaryKey { task_pk: "other", index_pk: "id" } })))"###);
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(PrimaryKeyMismatch { id: 1, reason: TaskPrimaryKeyDifferFromIndexPrimaryKey { task_pk: "other", index_pk: "id" } })))"###);
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("id"))]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
 
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("id"), operation_ids: [0, 1] }, true, None))"###);
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0] }, true))"###);
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("id"), operation_ids: [0, 1] }, true, None))"###);
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0, 1] }, true))"###);
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("id"), operation_ids: [0, 1, 2] }, true, None))"###);
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0, 1] }, true))"###);
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, Some("other"))]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("id"), operation_ids: [0] }, true, Some(PrimaryKeyMismatch { id: 1, reason: TaskPrimaryKeyDifferFromIndexPrimaryKey { task_pk: "other", index_pk: "id" } })))"###);
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, Some("other"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0] }, true))"###);
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("id"), operation_ids: [0] }, true, Some(PrimaryKeyMismatch { id: 1, reason: TaskPrimaryKeyDifferFromIndexPrimaryKey { task_pk: "other", index_pk: "id" } })))"###);
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0] }, true))"###);
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("id"), operation_ids: [0] }, true, Some(PrimaryKeyMismatch { id: 1, reason: TaskPrimaryKeyDifferFromIndexPrimaryKey { task_pk: "other", index_pk: "id" } })))"###);
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0] }, true))"###);
 
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true, Some(PrimaryKeyIndexMismatch { id: 0, in_index: "id", in_task: "other" })))"###);
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true))"###);
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true, Some(PrimaryKeyIndexMismatch { id: 0, in_index: "id", in_task: "other" })))"###);
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true))"###);
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true, Some(PrimaryKeyIndexMismatch { id: 0, in_index: "id", in_task: "other" })))"###);
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true))"###);
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("other"))]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true, Some(PrimaryKeyIndexMismatch { id: 0, in_index: "id", in_task: "other" })))"###);
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("other"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true))"###);
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true, Some(PrimaryKeyIndexMismatch { id: 0, in_index: "id", in_task: "other" })))"###);
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true))"###);
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true, Some(PrimaryKeyIndexMismatch { id: 0, in_index: "id", in_task: "other" })))"###);
+    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("other")), doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true))"###);
 
     // ==> If I don't have a pk
     // With a single update
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("id"), operation_ids: [0] }, true, None))"###);
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0] }, true))"###);
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("other"))]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true, None))"###);
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("other"))]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true))"###);
 
     // With a multiple updates
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true, None))");
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, None)]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, Some("id"))]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(PrimaryKeyMismatch { id: 1, reason: CannotInterfereWithPrimaryKeyGuessing { task_pk: "id" } })))"###);
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, Some("id"))]), @"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: None, operation_ids: [0] }, true))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("id"), operation_ids: [0, 1] }, true, None))"###);
+    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, Some("id")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { method: ReplaceDocuments, allow_index_creation: true, primary_key: Some("id"), operation_ids: [0] }, true))"###);
 }

crates/index-scheduler/src/scheduler/create_batch.rs

@@ -1,10 +1,9 @@
 use std::fmt;
-use std::io::ErrorKind;
 
 use meilisearch_types::heed::RoTxn;
 use meilisearch_types::milli::update::IndexDocumentsMethod;
 use meilisearch_types::settings::{Settings, Unchecked};
-use meilisearch_types::tasks::{BatchStopReason, Kind, KindWithContent, Status, Task};
+use meilisearch_types::tasks::{Kind, KindWithContent, Status, Task};
 use roaring::RoaringBitmap;
 use uuid::Uuid;
 
@@ -48,18 +47,11 @@ pub(crate) enum Batch {
     IndexSwap {
         task: Task,
     },
-    Export {
-        task: Task,
-    },
-    UpgradeDatabase {
-        tasks: Vec<Task>,
-    },
 }
 
 #[derive(Debug)]
 pub(crate) enum DocumentOperation {
-    Replace(Uuid),
+    Add(Uuid),
-    Update(Uuid),
     Delete(Vec<String>),
 }
 
@@ -69,6 +61,7 @@ pub(crate) enum IndexOperation {
     DocumentOperation {
         index_uid: String,
         primary_key: Option<String>,
+        method: IndexDocumentsMethod,
         operations: Vec<DocumentOperation>,
         tasks: Vec<Task>,
     },
@@ -107,13 +100,11 @@ impl Batch {
             Batch::TaskCancelation { task, .. }
             | Batch::Dump(task)
             | Batch::IndexCreation { task, .. }
-            | Batch::Export { task }
             | Batch::IndexUpdate { task, .. } => {
                 RoaringBitmap::from_sorted_iter(std::iter::once(task.uid)).unwrap()
             }
             Batch::SnapshotCreation(tasks)
             | Batch::TaskDeletions(tasks)
-            | Batch::UpgradeDatabase { tasks }
             | Batch::IndexDeletion { tasks, .. } => {
                 RoaringBitmap::from_iter(tasks.iter().map(|task| task.uid))
             }
@@ -147,8 +138,6 @@ impl Batch {
             | TaskDeletions(_)
             | SnapshotCreation(_)
             | Dump(_)
-            | Export { .. }
-            | UpgradeDatabase { .. }
             | IndexSwap { .. } => None,
             IndexOperation { op, .. } => Some(op.index_uid()),
             IndexCreation { index_uid, .. }
@@ -173,8 +162,6 @@ impl fmt::Display for Batch {
             Batch::IndexUpdate { .. } => f.write_str("IndexUpdate")?,
             Batch::IndexDeletion { .. } => f.write_str("IndexDeletion")?,
             Batch::IndexSwap { .. } => f.write_str("IndexSwap")?,
-            Batch::Export { .. } => f.write_str("Export")?,
-            Batch::UpgradeDatabase { .. } => f.write_str("UpgradeDatabase")?,
         };
         match index_uid {
             Some(name) => f.write_fmt(format_args!(" on {name:?} from tasks: {tasks:?}")),
@@ -261,7 +248,7 @@ impl IndexScheduler {
                     _ => unreachable!(),
                 }
             }
-            BatchKind::DocumentOperation { operation_ids, .. } => {
+            BatchKind::DocumentOperation { method, operation_ids, .. } => {
                 let tasks = self.queue.get_existing_tasks_for_processing_batch(
                     rtxn,
                     current_batch,
@@ -283,17 +270,9 @@ impl IndexScheduler {
 
                 for task in tasks.iter() {
                     match task.kind {
-                        KindWithContent::DocumentAdditionOrUpdate {
+                        KindWithContent::DocumentAdditionOrUpdate { content_file, .. } => {
-                            content_file, method, ..
+                            operations.push(DocumentOperation::Add(content_file));
-                        } => match method {
+                        }
-                            IndexDocumentsMethod::ReplaceDocuments => {
-                                operations.push(DocumentOperation::Replace(content_file))
-                            }
-                            IndexDocumentsMethod::UpdateDocuments => {
-                                operations.push(DocumentOperation::Update(content_file))
-                            }
-                            _ => unreachable!("Unknown document merging method"),
-                        },
                         KindWithContent::DocumentDeletion { ref documents_ids, .. } => {
                             operations.push(DocumentOperation::Delete(documents_ids.clone()));
                         }
@@ -305,6 +284,7 @@ impl IndexScheduler {
                     op: IndexOperation::DocumentOperation {
                         index_uid,
                         primary_key,
+                        method,
                         operations,
                         tasks,
                     },
@@ -430,13 +410,11 @@ impl IndexScheduler {
     }
 
     /// Create the next batch to be processed;
-    /// 0. We get the *last* task to cancel.
+    /// 1. We get the *last* task to cancel.
-    /// 1. We get the tasks to upgrade.
     /// 2. We get the *next* task to delete.
-    /// 3. We get the *next* export to process.
+    /// 3. We get the *next* snapshot to process.
-    /// 4. We get the *next* snapshot to process.
+    /// 4. We get the *next* dump to process.
-    /// 5. We get the *next* dump to process.
+    /// 5. We get the *next* tasks to process for a specific index.
-    /// 6. We get the *next* tasks to process for a specific index.
     #[tracing::instrument(level = "trace", skip(self, rtxn), target = "indexing::scheduler")]
     pub(crate) fn create_next_batch(
         &self,
@@ -449,99 +427,42 @@ impl IndexScheduler {
         let mut current_batch = ProcessingBatch::new(batch_id);
 
         let enqueued = &self.queue.tasks.get_status(rtxn, Status::Enqueued)?;
-        let count_total_enqueued = enqueued.len();
-        let failed = &self.queue.tasks.get_status(rtxn, Status::Failed)?;
-
-        // 0. we get the last task to cancel.
         let to_cancel = self.queue.tasks.get_kind(rtxn, Kind::TaskCancelation)? & enqueued;
+
+        // 1. we get the last task to cancel.
         if let Some(task_id) = to_cancel.max() {
             let mut task =
                 self.queue.tasks.get_task(rtxn, task_id)?.ok_or(Error::CorruptedTaskQueue)?;
             current_batch.processing(Some(&mut task));
-            current_batch.reason(BatchStopReason::TaskCannotBeBatched {
-                kind: Kind::TaskCancelation,
-                id: task_id,
-            });
             return Ok(Some((Batch::TaskCancelation { task }, current_batch)));
         }
 
-        // 1. We upgrade the instance
-        // There shouldn't be multiple upgrade tasks but just in case we're going to batch all of them at the same time
-        let upgrade = self.queue.tasks.get_kind(rtxn, Kind::UpgradeDatabase)? & (enqueued | failed);
-        if !upgrade.is_empty() {
-            let mut tasks = self.queue.tasks.get_existing_tasks(rtxn, upgrade)?;
-            // In the case of an upgrade database batch, we want to find back the original batch that tried processing it
-            // and re-use its id
-            if let Some(batch_uid) = tasks.last().unwrap().batch_uid {
-                current_batch.uid = batch_uid;
-            }
-            current_batch.processing(&mut tasks);
-            current_batch
-                .reason(BatchStopReason::TaskKindCannotBeBatched { kind: Kind::UpgradeDatabase });
-            return Ok(Some((Batch::UpgradeDatabase { tasks }, current_batch)));
-        }
-
-        // check the version of the scheduler here.
-        // if the version is not the current, refuse to batch any additional task.
-        let version = self.version.get_version(rtxn)?;
-        let package_version = (
-            meilisearch_types::versioning::VERSION_MAJOR,
-            meilisearch_types::versioning::VERSION_MINOR,
-            meilisearch_types::versioning::VERSION_PATCH,
-        );
-        if version != Some(package_version) {
-            return Err(Error::UnrecoverableError(Box::new(
-                Error::IndexSchedulerVersionMismatch {
-                    index_scheduler_version: version.unwrap_or((1, 12, 0)),
-                    package_version,
-                },
-            )));
-        }
-
         // 2. we get the next task to delete
         let to_delete = self.queue.tasks.get_kind(rtxn, Kind::TaskDeletion)? & enqueued;
         if !to_delete.is_empty() {
             let mut tasks = self.queue.tasks.get_existing_tasks(rtxn, to_delete)?;
             current_batch.processing(&mut tasks);
-            current_batch
-                .reason(BatchStopReason::TaskKindCannotBeBatched { kind: Kind::TaskDeletion });
             return Ok(Some((Batch::TaskDeletions(tasks), current_batch)));
         }
 
-        // 3. we batch the export.
+        // 3. we batch the snapshot.
-        let to_export = self.queue.tasks.get_kind(rtxn, Kind::Export)? & enqueued;
-        if !to_export.is_empty() {
-            let task_id = to_export.iter().next().expect("There must be at least one export task");
-            let mut task = self.queue.tasks.get_task(rtxn, task_id)?.unwrap();
-            current_batch.processing([&mut task]);
-            current_batch.reason(BatchStopReason::TaskKindCannotBeBatched { kind: Kind::Export });
-            return Ok(Some((Batch::Export { task }, current_batch)));
-        }
-
-        // 4. we batch the snapshot.
         let to_snapshot = self.queue.tasks.get_kind(rtxn, Kind::SnapshotCreation)? & enqueued;
         if !to_snapshot.is_empty() {
             let mut tasks = self.queue.tasks.get_existing_tasks(rtxn, to_snapshot)?;
             current_batch.processing(&mut tasks);
-            current_batch
-                .reason(BatchStopReason::TaskKindCannotBeBatched { kind: Kind::SnapshotCreation });
             return Ok(Some((Batch::SnapshotCreation(tasks), current_batch)));
         }
 
-        // 5. we batch the dumps.
+        // 4. we batch the dumps.
         let to_dump = self.queue.tasks.get_kind(rtxn, Kind::DumpCreation)? & enqueued;
         if let Some(to_dump) = to_dump.min() {
             let mut task =
                 self.queue.tasks.get_task(rtxn, to_dump)?.ok_or(Error::CorruptedTaskQueue)?;
             current_batch.processing(Some(&mut task));
-            current_batch.reason(BatchStopReason::TaskCannotBeBatched {
-                kind: Kind::DumpCreation,
-                id: task.uid,
-            });
             return Ok(Some((Batch::Dump(task), current_batch)));
         }
 
-        // 6. We make a batch from the unprioritised tasks. Start by taking the next enqueued task.
+        // 5. We make a batch from the unprioritised tasks. Start by taking the next enqueued task.
         let task_id = if let Some(task_id) = enqueued.min() { task_id } else { return Ok(None) };
         let mut task =
             self.queue.tasks.get_task(rtxn, task_id)?.ok_or(Error::CorruptedTaskQueue)?;
@@ -555,10 +476,6 @@ impl IndexScheduler {
         } else {
             assert!(matches!(&task.kind, KindWithContent::IndexSwap { swaps } if swaps.is_empty()));
             current_batch.processing(Some(&mut task));
-            current_batch.reason(BatchStopReason::TaskCannotBeBatched {
-                kind: Kind::IndexSwap,
-                id: task.uid,
-            });
             return Ok(Some((Batch::IndexSwap { task }, current_batch)));
         };
 
@@ -580,14 +497,9 @@ impl IndexScheduler {
             1
         };
 
-        let mut stop_reason = BatchStopReason::default();
         let mut enqueued = Vec::new();
         let mut total_size: u64 = 0;
-        for task_id in index_tasks.into_iter() {
+        for task_id in index_tasks.into_iter().take(tasks_limit) {
-            if enqueued.len() >= tasks_limit {
-                stop_reason = BatchStopReason::ReachedTaskLimit { task_limit: tasks_limit };
-                break;
-            }
             let task = self
                 .queue
                 .tasks
@@ -595,35 +507,20 @@ impl IndexScheduler {
                 .and_then(|task| task.ok_or(Error::CorruptedTaskQueue))?;
 
             if let Some(uuid) = task.content_uuid() {
-                let content_size = match self.queue.file_store.compute_size(uuid) {
+                let content_size = self.queue.file_store.compute_size(uuid)?;
-                    Ok(content_size) => content_size,
-                    Err(file_store::Error::IoError(err)) if err.kind() == ErrorKind::NotFound => 0,
-                    Err(otherwise) => return Err(otherwise.into()),
-                };
                 total_size = total_size.saturating_add(content_size);
             }
 
-            let size_limit = self.scheduler.batched_tasks_size_limit;
+            if total_size > self.scheduler.batched_tasks_size_limit && !enqueued.is_empty() {
-            if total_size > size_limit && !enqueued.is_empty() {
-                stop_reason = BatchStopReason::ReachedSizeLimit { size_limit, size: total_size };
                 break;
             }
 
             enqueued.push((task.uid, task.kind));
         }
 
-        stop_reason.replace_unspecified({
+        if let Some((batchkind, create_index)) =
-            if enqueued.len() == count_total_enqueued as usize {
-                BatchStopReason::ExhaustedEnqueuedTasks
-            } else {
-                BatchStopReason::ExhaustedEnqueuedTasksForIndex { index: index_name.to_owned() }
-            }
-        });
-
-        if let Some((batchkind, create_index, autobatch_stop_reason)) =
             autobatcher::autobatch(enqueued, index_already_exists, primary_key.as_deref())
         {
-            current_batch.reason(autobatch_stop_reason.unwrap_or(stop_reason));
             return Ok(self
                 .create_next_batch_index(
                     rtxn,

crates/index-scheduler/src/scheduler/mod.rs

@@ -4,10 +4,8 @@ mod autobatcher_test;
 mod create_batch;
 mod process_batch;
 mod process_dump_creation;
-mod process_export;
 mod process_index_operation;
 mod process_snapshot_creation;
-mod process_upgrade;
 #[cfg(test)]
 mod test;
 #[cfg(test)]
@@ -21,12 +19,9 @@ use std::path::PathBuf;
 use std::sync::atomic::{AtomicBool, AtomicU32, Ordering};
 use std::sync::Arc;
 
-use convert_case::{Case, Casing as _};
 use meilisearch_types::error::ResponseError;
-use meilisearch_types::heed::{Env, WithoutTls};
 use meilisearch_types::milli;
 use meilisearch_types::tasks::Status;
-use process_batch::ProcessBatchInfo;
 use rayon::current_num_threads;
 use rayon::iter::{IntoParallelIterator, ParallelIterator};
 use roaring::RoaringBitmap;
@@ -75,18 +70,10 @@ pub struct Scheduler {
     pub(crate) snapshots_path: PathBuf,
 
     /// The path to the folder containing the auth LMDB env.
-    pub(crate) auth_env: Env<WithoutTls>,
+    pub(crate) auth_path: PathBuf,
 
     /// The path to the version file of Meilisearch.
     pub(crate) version_file_path: PathBuf,
-
-    /// The maximal number of entries in the search query cache of an embedder.
-    ///
-    /// 0 disables the cache.
-    pub(crate) embedding_cache_cap: usize,
-
-    /// Snapshot compaction status.
-    pub(crate) experimental_no_snapshot_compaction: bool,
 }
 
 impl Scheduler {
@@ -99,14 +86,12 @@ impl Scheduler {
             batched_tasks_size_limit: self.batched_tasks_size_limit,
             dumps_path: self.dumps_path.clone(),
             snapshots_path: self.snapshots_path.clone(),
-            auth_env: self.auth_env.clone(),
+            auth_path: self.auth_path.clone(),
             version_file_path: self.version_file_path.clone(),
-            embedding_cache_cap: self.embedding_cache_cap,
-            experimental_no_snapshot_compaction: self.experimental_no_snapshot_compaction,
         }
     }
 
-    pub fn new(options: &IndexSchedulerOptions, auth_env: Env<WithoutTls>) -> Scheduler {
+    pub fn new(options: &IndexSchedulerOptions) -> Scheduler {
         Scheduler {
             must_stop_processing: MustStopProcessing::default(),
             // we want to start the loop right away in case meilisearch was ctrl+Ced while processing things
@@ -116,10 +101,8 @@ impl Scheduler {
             batched_tasks_size_limit: options.batched_tasks_size_limit,
             dumps_path: options.dumps_path.clone(),
             snapshots_path: options.snapshots_path.clone(),
-            auth_env,
+            auth_path: options.auth_path.clone(),
             version_file_path: options.version_file_path.clone(),
-            embedding_cache_cap: options.embedding_cache_cap,
-            experimental_no_snapshot_compaction: options.experimental_no_snapshot_compaction,
         }
     }
 }
@@ -182,41 +165,13 @@ impl IndexScheduler {
             let processing_batch = &mut processing_batch;
             let progress = progress.clone();
             std::thread::scope(|s| {
-                let p = progress.clone();
                 let handle = std::thread::Builder::new()
                     .name(String::from("batch-operation"))
                     .spawn_scoped(s, move || {
-                        cloned_index_scheduler.process_batch(batch, processing_batch, p)
+                        cloned_index_scheduler.process_batch(batch, processing_batch, progress)
                     })
                     .unwrap();
-
+                handle.join().unwrap_or(Err(Error::ProcessBatchPanicked))
-                match handle.join() {
-                    Ok(ret) => {
-                        if ret.is_err() {
-                            if let Ok(progress_view) =
-                                serde_json::to_string(&progress.as_progress_view())
-                            {
-                                tracing::warn!("Batch failed while doing: {progress_view}")
-                            }
-                        }
-                        ret
-                    }
-                    Err(panic) => {
-                        if let Ok(progress_view) =
-                            serde_json::to_string(&progress.as_progress_view())
-                        {
-                            tracing::warn!("Batch failed while doing: {progress_view}")
-                        }
-                        let msg = match panic.downcast_ref::<&'static str>() {
-                            Some(s) => *s,
-                            None => match panic.downcast_ref::<String>() {
-                                Some(s) => &s[..],
-                                None => "Box<dyn Any>",
-                            },
-                        };
-                        Err(Error::ProcessBatchPanicked(msg.to_string()))
-                    }
-                }
             })
         };
 
@@ -228,19 +183,16 @@ impl IndexScheduler {
 
         progress.update_progress(BatchProgress::WritingTasksToDisk);
         processing_batch.finished();
-        let mut stop_scheduler_forever = false;
         let mut wtxn = self.env.write_txn().map_err(Error::HeedTransaction)?;
         let mut canceled = RoaringBitmap::new();
-        let mut process_batch_info = ProcessBatchInfo::default();
 
         match res {
-            Ok((tasks, info)) => {
+            Ok(tasks) => {
                 #[cfg(test)]
                 self.breakpoint(crate::test_utils::Breakpoint::ProcessBatchSucceeded);
 
                 let (task_progress, task_progress_obj) = AtomicTaskStep::new(tasks.len() as u32);
                 progress.update_progress(task_progress_obj);
-                process_batch_info = info;
                 let mut success = 0;
                 let mut failure = 0;
                 let mut canceled_by = None;
@@ -269,7 +221,7 @@ impl IndexScheduler {
                     self.queue
                         .tasks
                         .update_task(&mut wtxn, &task)
-                        .map_err(|e| Error::UnrecoverableError(Box::new(e)))?;
+                        .map_err(|e| Error::TaskDatabaseUpdate(Box::new(e)))?;
                 }
                 if let Some(canceled_by) = canceled_by {
                     self.queue.tasks.canceled_by.put(&mut wtxn, &canceled_by, &canceled)?;
@@ -320,12 +272,6 @@ impl IndexScheduler {
                 let (task_progress, task_progress_obj) = AtomicTaskStep::new(ids.len() as u32);
                 progress.update_progress(task_progress_obj);
 
-                if matches!(err, Error::DatabaseUpgrade(_)) {
-                    tracing::error!(
-                        "Upgrade task failed, tasks won't be processed until the following issue is fixed: {err}"
-                    );
-                    stop_scheduler_forever = true;
-                }
                 let error: ResponseError = err.into();
                 for id in ids.iter() {
                     task_progress.fetch_add(1, Ordering::Relaxed);
@@ -333,7 +279,7 @@ impl IndexScheduler {
                         .queue
                         .tasks
                         .get_task(&wtxn, id)
-                        .map_err(|e| Error::UnrecoverableError(Box::new(e)))?
+                        .map_err(|e| Error::TaskDatabaseUpdate(Box::new(e)))?
                         .ok_or(Error::CorruptedTaskQueue)?;
                     task.status = Status::Failed;
                     task.error = Some(error.clone());
@@ -350,67 +296,13 @@ impl IndexScheduler {
                     self.queue
                         .tasks
                         .update_task(&mut wtxn, &task)
-                        .map_err(|e| Error::UnrecoverableError(Box::new(e)))?;
+                        .map_err(|e| Error::TaskDatabaseUpdate(Box::new(e)))?;
                 }
             }
         }
 
         // We must re-add the canceled task so they're part of the same batch.
         ids |= canceled;
-
-        let ProcessBatchInfo { congestion, pre_commit_dabases_sizes, post_commit_dabases_sizes } =
-            process_batch_info;
-
-        processing_batch.stats.progress_trace =
-            progress.accumulated_durations().into_iter().map(|(k, v)| (k, v.into())).collect();
-        processing_batch.stats.write_channel_congestion = congestion.map(|congestion| {
-            let mut congestion_info = serde_json::Map::new();
-            congestion_info.insert("attempts".into(), congestion.attempts.into());
-            congestion_info.insert("blocking_attempts".into(), congestion.blocking_attempts.into());
-            congestion_info.insert("blocking_ratio".into(), congestion.congestion_ratio().into());
-            congestion_info
-        });
-        processing_batch.stats.internal_database_sizes = pre_commit_dabases_sizes
-            .iter()
-            .flat_map(|(dbname, pre_size)| {
-                post_commit_dabases_sizes
-                    .get(dbname)
-                    .map(|post_size| {
-                        use std::cmp::Ordering::{Equal, Greater, Less};
-
-                        use byte_unit::Byte;
-                        use byte_unit::UnitType::Binary;
-
-                        let post = Byte::from_u64(*post_size as u64).get_appropriate_unit(Binary);
-                        let diff_size = post_size.abs_diff(*pre_size) as u64;
-                        let diff = Byte::from_u64(diff_size).get_appropriate_unit(Binary);
-                        let sign = match post_size.cmp(pre_size) {
-                            Equal => return None,
-                            Greater => "+",
-                            Less => "-",
-                        };
-
-                        Some((
-                            dbname.to_case(Case::Camel),
-                            format!("{post:#.2} ({sign}{diff:#.2})").into(),
-                        ))
-                    })
-                    .into_iter()
-                    .flatten()
-            })
-            .collect();
-
-        if let Some(congestion) = congestion {
-            tracing::debug!(
-                "Channel congestion metrics - Attempts: {}, Blocked attempts: {}  ({:.1}% congestion)",
-                congestion.attempts,
-                congestion.blocking_attempts,
-                congestion.congestion_ratio(),
-            );
-        }
-
-        tracing::debug!("call trace: {:?}", progress.accumulated_durations());
-
         self.queue.write_batch(&mut wtxn, processing_batch, &ids)?;
 
         #[cfg(test)]
@@ -434,7 +326,7 @@ impl IndexScheduler {
                     .queue
                     .tasks
                     .get_task(&rtxn, id)
-                    .map_err(|e| Error::UnrecoverableError(Box::new(e)))?
+                    .map_err(|e| Error::TaskDatabaseUpdate(Box::new(e)))?
                     .ok_or(Error::CorruptedTaskQueue)?;
                 if let Err(e) = self.queue.delete_persisted_task_data(&task) {
                     tracing::error!(
@@ -452,10 +344,6 @@ impl IndexScheduler {
         #[cfg(test)]
         self.breakpoint(crate::test_utils::Breakpoint::AfterProcessing);
 
-        if stop_scheduler_forever {
+        Ok(TickOutcome::TickAgain(processed_tasks))
-            Ok(TickOutcome::StopProcessingForever)
-        } else {
-            Ok(TickOutcome::TickAgain(processed_tasks))
-        }
     }
 }

crates/index-scheduler/src/scheduler/process_batch.rs

@@ -1,38 +1,23 @@
 use std::collections::{BTreeSet, HashMap, HashSet};
-use std::panic::{catch_unwind, AssertUnwindSafe};
 use std::sync::atomic::Ordering;
 
-use meilisearch_types::batches::{BatchEnqueuedAt, BatchId};
+use meilisearch_types::batches::BatchId;
 use meilisearch_types::heed::{RoTxn, RwTxn};
-use meilisearch_types::milli::progress::{Progress, VariableNameStep};
+use meilisearch_types::milli::progress::Progress;
-use meilisearch_types::milli::{self, ChannelCongestion};
+use meilisearch_types::milli::{self};
-use meilisearch_types::tasks::{Details, IndexSwap, Kind, KindWithContent, Status, Task};
+use meilisearch_types::tasks::{Details, IndexSwap, KindWithContent, Status, Task};
-use meilisearch_types::versioning::{VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH};
 use milli::update::Settings as MilliSettings;
 use roaring::RoaringBitmap;
 
 use super::create_batch::Batch;
 use crate::processing::{
-    AtomicBatchStep, AtomicTaskStep, CreateIndexProgress, DeleteIndexProgress, FinalizingIndexStep,
+    AtomicBatchStep, AtomicTaskStep, CreateIndexProgress, DeleteIndexProgress,
     InnerSwappingTwoIndexes, SwappingTheIndexes, TaskCancelationProgress, TaskDeletionProgress,
-    UpdateIndexProgress,
+    UpdateIndexProgress, VariableNameStep,
-};
-use crate::utils::{
-    self, remove_n_tasks_datetime_earlier_than, remove_task_datetime, swap_index_uid_in_task,
-    ProcessingBatch,
 };
+use crate::utils::{self, swap_index_uid_in_task, ProcessingBatch};
 use crate::{Error, IndexScheduler, Result, TaskId};
 
-#[derive(Debug, Default)]
-pub struct ProcessBatchInfo {
-    /// The write channel congestion. None when unavailable: settings update.
-    pub congestion: Option<ChannelCongestion>,
-    /// The sizes of the different databases before starting the indexation.
-    pub pre_commit_dabases_sizes: indexmap::IndexMap<&'static str, usize>,
-    /// The sizes of the different databases after commiting the indexation.
-    pub post_commit_dabases_sizes: indexmap::IndexMap<&'static str, usize>,
-}
-
 impl IndexScheduler {
     /// Apply the operation associated with the given batch.
     ///
@@ -46,7 +31,7 @@ impl IndexScheduler {
         batch: Batch,
         current_batch: &mut ProcessingBatch,
         progress: Progress,
-    ) -> Result<(Vec<Task>, ProcessBatchInfo)> {
+    ) -> Result<Vec<Task>> {
         #[cfg(test)]
         {
             self.maybe_fail(crate::test_utils::FailureLocation::InsideProcessBatch)?;
@@ -87,7 +72,7 @@ impl IndexScheduler {
 
                 canceled_tasks.push(task);
 
-                Ok((canceled_tasks, ProcessBatchInfo::default()))
+                Ok(canceled_tasks)
             }
             Batch::TaskDeletions(mut tasks) => {
                 // 1. Retrieve the tasks that matched the query at enqueue-time.
@@ -126,14 +111,10 @@ impl IndexScheduler {
                         _ => unreachable!(),
                     }
                 }
-                Ok((tasks, ProcessBatchInfo::default()))
+                Ok(tasks)
             }
-            Batch::SnapshotCreation(tasks) => self
+            Batch::SnapshotCreation(tasks) => self.process_snapshot(progress, tasks),
-                .process_snapshot(progress, tasks)
+            Batch::Dump(task) => self.process_dump_creation(progress, task),
-                .map(|tasks| (tasks, ProcessBatchInfo::default())),
-            Batch::Dump(task) => self
-                .process_dump_creation(progress, task)
-                .map(|tasks| (tasks, ProcessBatchInfo::default())),
             Batch::IndexOperation { op, must_create_index } => {
                 let index_uid = op.index_uid().to_string();
                 let index = if must_create_index {
@@ -145,33 +126,14 @@ impl IndexScheduler {
                     self.index_mapper.index(&rtxn, &index_uid)?
                 };
 
-                let mut index_wtxn = index.write_txn()?;
-
-                let index_version = index.get_version(&index_wtxn)?.unwrap_or((1, 12, 0));
-                let package_version = (VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH);
-                if index_version != package_version {
-                    return Err(Error::IndexVersionMismatch {
-                        index: index_uid,
-                        index_version,
-                        package_version,
-                    });
-                }
-
                 // the index operation can take a long time, so save this handle to make it available to the search for the duration of the tick
                 self.index_mapper
                     .set_currently_updating_index(Some((index_uid.clone(), index.clone())));
 
-                let pre_commit_dabases_sizes = index.database_sizes(&index_wtxn)?;
+                let mut index_wtxn = index.write_txn()?;
-                let (tasks, congestion) = self.apply_index_operation(
+                let tasks = self.apply_index_operation(&mut index_wtxn, &index, op, progress)?;
-                    &mut index_wtxn,
-                    &index,
-                    op,
-                    &progress,
-                    current_batch.embedder_stats.clone(),
-                )?;
 
                 {
-                    progress.update_progress(FinalizingIndexStep::Committing);
                     let span = tracing::trace_span!(target: "indexing::scheduler", "commit");
                     let _entered = span.enter();
 
@@ -182,15 +144,12 @@ impl IndexScheduler {
                 // stats of the index. Since the tasks have already been processed and
                 // this is a non-critical operation. If it fails, we should not fail
                 // the entire batch.
-                let mut post_commit_dabases_sizes = None;
                 let res = || -> Result<()> {
-                    progress.update_progress(FinalizingIndexStep::ComputingStats);
                     let index_rtxn = index.read_txn()?;
                     let stats = crate::index_mapper::IndexStats::new(&index, &index_rtxn)
                         .map_err(|e| Error::from_milli(e, Some(index_uid.to_string())))?;
                     let mut wtxn = self.env.write_txn()?;
                     self.index_mapper.store_stats_of(&mut wtxn, &index_uid, &stats)?;
-                    post_commit_dabases_sizes = Some(index.database_sizes(&index_rtxn)?);
                     wtxn.commit()?;
                     Ok(())
                 }();
@@ -203,16 +162,7 @@ impl IndexScheduler {
                     ),
                 }
 
-                let info = ProcessBatchInfo {
+                Ok(tasks)
-                    congestion,
-                    // In case we fail to the get post-commit sizes we decide
-                    // that nothing changed and use the pre-commit sizes.
-                    post_commit_dabases_sizes: post_commit_dabases_sizes
-                        .unwrap_or_else(|| pre_commit_dabases_sizes.clone()),
-                    pre_commit_dabases_sizes,
-                };
-
-                Ok((tasks, info))
             }
             Batch::IndexCreation { index_uid, primary_key, task } => {
                 progress.update_progress(CreateIndexProgress::CreatingTheIndex);
@@ -243,12 +193,10 @@ impl IndexScheduler {
                     );
                     builder.set_primary_key(primary_key);
                     let must_stop_processing = self.scheduler.must_stop_processing.clone();
-
                     builder
                         .execute(
-                            &|| must_stop_processing.get(),
+                            |indexing_step| tracing::debug!(update = ?indexing_step),
-                            &progress,
+                            || must_stop_processing.get(),
-                            current_batch.embedder_stats.clone(),
                         )
                         .map_err(|e| Error::from_milli(e, Some(index_uid.to_string())))?;
                     index_wtxn.commit()?;
@@ -282,7 +230,7 @@ impl IndexScheduler {
                     ),
                 }
 
-                Ok((vec![task], ProcessBatchInfo::default()))
+                Ok(vec![task])
             }
             Batch::IndexDeletion { index_uid, index_has_been_created, mut tasks } => {
                 progress.update_progress(DeleteIndexProgress::DeletingTheIndex);
@@ -316,9 +264,7 @@ impl IndexScheduler {
                     };
                 }
 
-                // Here we could also show that all the internal database sizes goes to 0
+                Ok(tasks)
-                // but it would mean opening the index and that's costly.
-                Ok((tasks, ProcessBatchInfo::default()))
             }
             Batch::IndexSwap { mut task } => {
                 progress.update_progress(SwappingTheIndexes::EnsuringCorrectnessOfTheSwap);
@@ -351,7 +297,7 @@ impl IndexScheduler {
                 }
                 progress.update_progress(SwappingTheIndexes::SwappingTheIndexes);
                 for (step, swap) in swaps.iter().enumerate() {
-                    progress.update_progress(VariableNameStep::<SwappingTheIndexes>::new(
+                    progress.update_progress(VariableNameStep::new(
                         format!("swapping index {} and {}", swap.indexes.0, swap.indexes.1),
                         step as u32,
                         swaps.len() as u32,
@@ -366,79 +312,7 @@ impl IndexScheduler {
                 }
                 wtxn.commit()?;
                 task.status = Status::Succeeded;
-                Ok((vec![task], ProcessBatchInfo::default()))
+                Ok(vec![task])
-            }
-            Batch::Export { mut task } => {
-                let KindWithContent::Export { url, api_key, payload_size, indexes } = &task.kind
-                else {
-                    unreachable!()
-                };
-
-                let ret = catch_unwind(AssertUnwindSafe(|| {
-                    self.process_export(
-                        url,
-                        api_key.as_deref(),
-                        payload_size.as_ref(),
-                        indexes,
-                        progress,
-                    )
-                }));
-
-                let stats = match ret {
-                    Ok(Ok(stats)) => stats,
-                    Ok(Err(Error::AbortedTask)) => return Err(Error::AbortedTask),
-                    Ok(Err(e)) => return Err(Error::Export(Box::new(e))),
-                    Err(e) => {
-                        let msg = match e.downcast_ref::<&'static str>() {
-                            Some(s) => *s,
-                            None => match e.downcast_ref::<String>() {
-                                Some(s) => &s[..],
-                                None => "Box<dyn Any>",
-                            },
-                        };
-                        return Err(Error::Export(Box::new(Error::ProcessBatchPanicked(
-                            msg.to_string(),
-                        ))));
-                    }
-                };
-
-                task.status = Status::Succeeded;
-                if let Some(Details::Export { indexes, .. }) = task.details.as_mut() {
-                    *indexes = stats;
-                }
-                Ok((vec![task], ProcessBatchInfo::default()))
-            }
-            Batch::UpgradeDatabase { mut tasks } => {
-                let KindWithContent::UpgradeDatabase { from } = tasks.last().unwrap().kind else {
-                    unreachable!();
-                };
-
-                let ret = catch_unwind(AssertUnwindSafe(|| self.process_upgrade(from, progress)));
-                match ret {
-                    Ok(Ok(())) => (),
-                    Ok(Err(Error::AbortedTask)) => return Err(Error::AbortedTask),
-                    Ok(Err(e)) => return Err(Error::DatabaseUpgrade(Box::new(e))),
-                    Err(e) => {
-                        let msg = match e.downcast_ref::<&'static str>() {
-                            Some(s) => *s,
-                            None => match e.downcast_ref::<String>() {
-                                Some(s) => &s[..],
-                                None => "Box<dyn Any>",
-                            },
-                        };
-                        return Err(Error::DatabaseUpgrade(Box::new(Error::ProcessBatchPanicked(
-                            msg.to_string(),
-                        ))));
-                    }
-                }
-
-                for task in tasks.iter_mut() {
-                    task.status = Status::Succeeded;
-                    // Since this task can be retried we must reset its error status
-                    task.error = None;
-                }
-
-                Ok((tasks, ProcessBatchInfo::default()))
             }
         }
     }
@@ -522,6 +396,7 @@ impl IndexScheduler {
         to_delete_tasks -= &enqueued_tasks;
 
         // 2. We now have a list of tasks to delete, delete them
+
         let mut affected_indexes = HashSet::new();
         let mut affected_statuses = HashSet::new();
         let mut affected_kinds = HashSet::new();
@@ -618,51 +493,9 @@ impl IndexScheduler {
                 tasks -= &to_delete_tasks;
                 // We must remove the batch entirely
                 if tasks.is_empty() {
-                    if let Some(batch) = self.queue.batches.get_batch(wtxn, batch_id)? {
+                    self.queue.batches.all_batches.delete(wtxn, &batch_id)?;
-                        if let Some(BatchEnqueuedAt { earliest, oldest }) = batch.enqueued_at {
+                    self.queue.batch_to_tasks_mapping.delete(wtxn, &batch_id)?;
-                            remove_task_datetime(
-                                wtxn,
-                                self.queue.batches.enqueued_at,
-                                earliest,
-                                batch_id,
-                            )?;
-                            remove_task_datetime(
-                                wtxn,
-                                self.queue.batches.enqueued_at,
-                                oldest,
-                                batch_id,
-                            )?;
-                        } else {
-                            // If we don't have the enqueued at in the batch it means the database comes from the v1.12
-                            // and we still need to find the date by scrolling the database
-                            remove_n_tasks_datetime_earlier_than(
-                                wtxn,
-                                self.queue.batches.enqueued_at,
-                                batch.started_at,
-                                batch.stats.total_nb_tasks.clamp(1, 2) as usize,
-                                batch_id,
-                            )?;
-                        }
-                        remove_task_datetime(
-                            wtxn,
-                            self.queue.batches.started_at,
-                            batch.started_at,
-                            batch_id,
-                        )?;
-                        if let Some(finished_at) = batch.finished_at {
-                            remove_task_datetime(
-                                wtxn,
-                                self.queue.batches.finished_at,
-                                finished_at,
-                                batch_id,
-                            )?;
-                        }
-
-                        self.queue.batches.all_batches.delete(wtxn, &batch_id)?;
-                        self.queue.batch_to_tasks_mapping.delete(wtxn, &batch_id)?;
-                    }
                 }
-
                 // Anyway, we must remove the batch from all its reverse indexes.
                 // The only way to do that is to check
 
@@ -714,81 +547,17 @@ impl IndexScheduler {
         progress: &Progress,
     ) -> Result<Vec<Task>> {
         progress.update_progress(TaskCancelationProgress::RetrievingTasks);
-        let mut tasks_to_cancel = RoaringBitmap::new();
 
-        let enqueued_tasks = &self.queue.tasks.get_status(rtxn, Status::Enqueued)?;
-
-        // 0. Check if any upgrade task was matched.
-        //    If so, we cancel all the failed or enqueued upgrade tasks.
-        let upgrade_tasks = &self.queue.tasks.get_kind(rtxn, Kind::UpgradeDatabase)?;
-        let is_canceling_upgrade = !matched_tasks.is_disjoint(upgrade_tasks);
-        if is_canceling_upgrade {
-            let failed_tasks = self.queue.tasks.get_status(rtxn, Status::Failed)?;
-            tasks_to_cancel |= upgrade_tasks & (enqueued_tasks | failed_tasks);
-        }
         // 1. Remove from this list the tasks that we are not allowed to cancel
         //    Notice that only the _enqueued_ ones are cancelable and we should
         //    have already aborted the indexation of the _processing_ ones
-        tasks_to_cancel |= enqueued_tasks & matched_tasks;
+        let cancelable_tasks = self.queue.tasks.get_status(rtxn, Status::Enqueued)?;
+        let tasks_to_cancel = cancelable_tasks & matched_tasks;
 
-        // 2. If we're canceling an upgrade, attempt the rollback
-        if let Some(latest_upgrade_task) = (&tasks_to_cancel & upgrade_tasks).max() {
-            progress.update_progress(TaskCancelationProgress::CancelingUpgrade);
-
-            let task = self.queue.tasks.get_task(rtxn, latest_upgrade_task)?.unwrap();
-            let Some(Details::UpgradeDatabase { from, to }) = task.details else {
-                unreachable!("wrong details for upgrade task {latest_upgrade_task}")
-            };
-
-            // check that we are rollbacking an upgrade to the current Meilisearch
-            let bin_major: u32 = meilisearch_types::versioning::VERSION_MAJOR;
-            let bin_minor: u32 = meilisearch_types::versioning::VERSION_MINOR;
-            let bin_patch: u32 = meilisearch_types::versioning::VERSION_PATCH;
-
-            if to == (bin_major, bin_minor, bin_patch) {
-                tracing::warn!(
-                    "Rollbacking from v{}.{}.{} to v{}.{}.{}",
-                    to.0,
-                    to.1,
-                    to.2,
-                    from.0,
-                    from.1,
-                    from.2
-                );
-                let ret = catch_unwind(std::panic::AssertUnwindSafe(|| {
-                    self.process_rollback(from, progress)
-                }));
-
-                match ret {
-                    Ok(Ok(())) => {}
-                    Ok(Err(err)) => return Err(Error::DatabaseUpgrade(Box::new(err))),
-                    Err(e) => {
-                        let msg = match e.downcast_ref::<&'static str>() {
-                            Some(s) => *s,
-                            None => match e.downcast_ref::<String>() {
-                                Some(s) => &s[..],
-                                None => "Box<dyn Any>",
-                            },
-                        };
-                        return Err(Error::DatabaseUpgrade(Box::new(Error::ProcessBatchPanicked(
-                            msg.to_string(),
-                        ))));
-                    }
-                }
-            } else {
-                tracing::debug!(
-                    "Not rollbacking an upgrade targetting the earlier version v{}.{}.{}",
-                    bin_major,
-                    bin_minor,
-                    bin_patch
-                )
-            }
-        }
-
-        // 3. We now have a list of tasks to cancel, cancel them
         let (task_progress, progress_obj) = AtomicTaskStep::new(tasks_to_cancel.len() as u32);
         progress.update_progress(progress_obj);
 
+        // 2. We now have a list of tasks to cancel, cancel them
         let mut tasks = self.queue.tasks.get_existing_tasks(
             rtxn,
             tasks_to_cancel.iter().inspect(|_| {

crates/index-scheduler/src/scheduler/process_dump_creation.rs

@@ -1,12 +1,11 @@
-use std::collections::BTreeMap;
 use std::fs::File;
 use std::io::BufWriter;
 use std::sync::atomic::Ordering;
 
 use dump::IndexMetadata;
 use meilisearch_types::milli::constants::RESERVED_VECTORS_FIELD_NAME;
-use meilisearch_types::milli::index::EmbeddingsWithMetadata;
+use meilisearch_types::milli::documents::{obkv_to_object, DocumentsBatchReader};
-use meilisearch_types::milli::progress::{Progress, VariableNameStep};
+use meilisearch_types::milli::progress::Progress;
 use meilisearch_types::milli::vector::parsed_vectors::{ExplicitVectors, VectorOrArrayOfVectors};
 use meilisearch_types::milli::{self};
 use meilisearch_types::tasks::{Details, KindWithContent, Status, Task};
@@ -14,7 +13,7 @@ use time::macros::format_description;
 use time::OffsetDateTime;
 
 use crate::processing::{
-    AtomicBatchStep, AtomicDocumentStep, AtomicTaskStep, DumpCreationProgress,
+    AtomicDocumentStep, AtomicTaskStep, DumpCreationProgress, VariableNameStep,
 };
 use crate::{Error, IndexScheduler, Result};
 
@@ -44,16 +43,7 @@ impl IndexScheduler {
 
         let rtxn = self.env.read_txn()?;
 
-        // 2. dump the chat completion settings
+        // 2. dump the tasks
-        // TODO should I skip the export if the chat completion has been disabled?
-        progress.update_progress(DumpCreationProgress::DumpTheChatCompletionSettings);
-        let mut dump_chat_completion_settings = dump.create_chat_completions_settings()?;
-        for result in self.chat_settings.iter(&rtxn)? {
-            let (name, chat_settings) = result?;
-            dump_chat_completion_settings.push_settings(name, &chat_settings)?;
-        }
-
-        // 3. dump the tasks
         progress.update_progress(DumpCreationProgress::DumpTheTasks);
         let mut dump_tasks = dump.create_tasks_queue()?;
 
@@ -82,16 +72,9 @@ impl IndexScheduler {
                 t.started_at = Some(started_at);
                 t.finished_at = Some(finished_at);
             }
-
-            // Patch the task to remove the batch uid, because as of v1.12.5 batches are not persisted.
-            // This prevent from referencing *future* batches not actually associated with the task.
-            //
-            // See <https://github.com/meilisearch/meilisearch/issues/5247> for details.
-            t.batch_uid = None;
-
             let mut dump_content_file = dump_tasks.push_task(&t.into())?;
 
-            // 3.1. Dump the `content_file` associated with the task if there is one and the task is not finished yet.
+            // 2.1. Dump the `content_file` associated with the task if there is one and the task is not finished yet.
             if let Some(content_file) = content_file {
                 if self.scheduler.must_stop_processing.get() {
                     return Err(Error::AbortedTask);
@@ -99,15 +82,19 @@ impl IndexScheduler {
                 if status == Status::Enqueued {
                     let content_file = self.queue.file_store.get_update(content_file)?;
 
-                    for document in
+                    let reader = DocumentsBatchReader::from_reader(content_file)
-                        serde_json::de::Deserializer::from_reader(content_file).into_iter()
+                        .map_err(|e| Error::from_milli(e.into(), None))?;
-                    {
-                        let document = document.map_err(|e| {
-                            Error::from_milli(milli::InternalError::SerdeJson(e).into(), None)
-                        })?;
-                        dump_content_file.push_document(&document)?;
-                    }
 
+                    let (mut cursor, documents_batch_index) = reader.into_cursor_and_fields_index();
+
+                    while let Some(doc) =
+                        cursor.next_document().map_err(|e| Error::from_milli(e.into(), None))?
+                    {
+                        dump_content_file.push_document(
+                            &obkv_to_object(doc, &documents_batch_index)
+                                .map_err(|e| Error::from_milli(e, None))?,
+                        )?;
+                    }
                     dump_content_file.flush()?;
                 }
             }
@@ -115,49 +102,12 @@ impl IndexScheduler {
         }
         dump_tasks.flush()?;
 
-        // 4. dump the batches
+        // 3. Dump the indexes
-        progress.update_progress(DumpCreationProgress::DumpTheBatches);
-        let mut dump_batches = dump.create_batches_queue()?;
-
-        let (atomic_batch_progress, update_batch_progress) =
-            AtomicBatchStep::new(self.queue.batches.all_batches.len(&rtxn)? as u32);
-        progress.update_progress(update_batch_progress);
-
-        for ret in self.queue.batches.all_batches.iter(&rtxn)? {
-            if self.scheduler.must_stop_processing.get() {
-                return Err(Error::AbortedTask);
-            }
-
-            let (_, mut b) = ret?;
-            // In the case we're dumping ourselves we want to be marked as finished
-            // to not loop over ourselves indefinitely.
-            if b.uid == task.uid {
-                let finished_at = OffsetDateTime::now_utc();
-
-                // We're going to fake the date because we don't know if everything is going to go well.
-                // But we need to dump the task as finished and successful.
-                // If something fail everything will be set appropriately in the end.
-                let mut statuses = BTreeMap::new();
-                statuses.insert(Status::Succeeded, b.stats.total_nb_tasks);
-                b.stats.status = statuses;
-                b.finished_at = Some(finished_at);
-            }
-
-            dump_batches.push_batch(&b)?;
-            atomic_batch_progress.fetch_add(1, Ordering::Relaxed);
-        }
-        dump_batches.flush()?;
-
-        // 5. Dump the indexes
         progress.update_progress(DumpCreationProgress::DumpTheIndexes);
         let nb_indexes = self.index_mapper.index_mapping.len(&rtxn)? as u32;
         let mut count = 0;
         let () = self.index_mapper.try_for_each_index(&rtxn, |uid, index| -> Result<()> {
-            progress.update_progress(VariableNameStep::<DumpCreationProgress>::new(
+            progress.update_progress(VariableNameStep::new(uid.to_string(), count, nb_indexes));
-                uid.to_string(),
-                count,
-                nb_indexes,
-            ));
             count += 1;
 
             let rtxn = index.read_txn()?;
@@ -175,6 +125,10 @@ impl IndexScheduler {
 
             let fields_ids_map = index.fields_ids_map(&rtxn)?;
             let all_fields: Vec<_> = fields_ids_map.iter().map(|(id, _)| id).collect();
+            let embedding_configs = index
+                .embedding_configs(&rtxn)
+                .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
+            let decompression_dictionary = index.document_decompression_dictionary(&rtxn)?;
 
             let nb_documents = index
                 .number_of_documents(&rtxn)
@@ -182,16 +136,21 @@ impl IndexScheduler {
                 as u32;
             let (atomic, update_document_progress) = AtomicDocumentStep::new(nb_documents);
             progress.update_progress(update_document_progress);
+            let doc_alloc = bumpalo::Bump::new();
             let documents = index
-                .all_documents(&rtxn)
+                .all_compressed_documents(&rtxn)
                 .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
-            // 5.1. Dump the documents
+            // 3.1. Dump the documents
             for ret in documents {
                 if self.scheduler.must_stop_processing.get() {
                     return Err(Error::AbortedTask);
                 }
 
                 let (id, doc) = ret.map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
+                let doc = match decompression_dictionary.as_ref() {
+                    Some(dict) => doc.decompress_into_bump(&doc_alloc, dict)?,
+                    None => doc.as_non_compressed(),
+                };
 
                 let mut document = milli::obkv_to_json(&all_fields, &fields_ids_map, doc)
                     .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
@@ -228,21 +187,16 @@ impl IndexScheduler {
                         return Err(Error::from_milli(user_err, Some(uid.to_string())));
                     };
 
-                    for (
+                    for (embedder_name, embeddings) in embeddings {
-                        embedder_name,
+                        let user_provided = embedding_configs
-                        EmbeddingsWithMetadata { embeddings, regenerate, has_fragments },
+                            .iter()
-                    ) in embeddings
+                            .find(|conf| conf.name == embedder_name)
-                    {
+                            .is_some_and(|conf| conf.user_provided.contains(id));
                         let embeddings = ExplicitVectors {
                             embeddings: Some(VectorOrArrayOfVectors::from_array_of_vectors(
                                 embeddings,
                             )),
-                            regenerate: regenerate &&
+                            regenerate: !user_provided,
-                            // Meilisearch does not handle well dumps with fragments, because as the fragments
-                            // are marked as user-provided,
-                            // all embeddings would be regenerated on any settings change or document update.
-                            // To prevent this, we mark embeddings has non regenerate in this case.
-                            !has_fragments,
                         };
                         vectors.insert(embedder_name, serde_json::to_value(embeddings).unwrap());
                     }
@@ -252,7 +206,7 @@ impl IndexScheduler {
                 atomic.fetch_add(1, Ordering::Relaxed);
             }
 
-            // 5.2. Dump the settings
+            // 3.2. Dump the settings
             let settings = meilisearch_types::settings::settings(
                 index,
                 &rtxn,
@@ -263,12 +217,10 @@ impl IndexScheduler {
             Ok(())
         })?;
 
-        // 6. Dump experimental feature settings
+        // 4. Dump experimental feature settings
         progress.update_progress(DumpCreationProgress::DumpTheExperimentalFeatures);
         let features = self.features().runtime_features();
         dump.create_experimental_features(features)?;
-        let network = self.network();
-        dump.create_network(network)?;
 
         let dump_uid = started_at.format(format_description!(
                     "[year repr:full][month repr:numerical][day padding:zero]-[hour padding:zero][minute padding:zero][second padding:zero][subsecond digits:3]"

crates/index-scheduler/src/scheduler/process_export.rs

@@ -1,377 +0,0 @@
-use std::collections::BTreeMap;
-use std::io::{self, Write as _};
-use std::sync::atomic;
-use std::time::Duration;
-
-use backoff::ExponentialBackoff;
-use byte_unit::Byte;
-use flate2::write::GzEncoder;
-use flate2::Compression;
-use meilisearch_types::index_uid_pattern::IndexUidPattern;
-use meilisearch_types::milli::constants::RESERVED_VECTORS_FIELD_NAME;
-use meilisearch_types::milli::index::EmbeddingsWithMetadata;
-use meilisearch_types::milli::progress::{Progress, VariableNameStep};
-use meilisearch_types::milli::update::{request_threads, Setting};
-use meilisearch_types::milli::vector::parsed_vectors::{ExplicitVectors, VectorOrArrayOfVectors};
-use meilisearch_types::milli::{self, obkv_to_json, Filter, InternalError};
-use meilisearch_types::settings::{self, SecretPolicy};
-use meilisearch_types::tasks::{DetailsExportIndexSettings, ExportIndexSettings};
-use serde::Deserialize;
-use ureq::{json, Response};
-
-use super::MustStopProcessing;
-use crate::processing::AtomicDocumentStep;
-use crate::{Error, IndexScheduler, Result};
-
-impl IndexScheduler {
-    pub(super) fn process_export(
-        &self,
-        base_url: &str,
-        api_key: Option<&str>,
-        payload_size: Option<&Byte>,
-        indexes: &BTreeMap<IndexUidPattern, ExportIndexSettings>,
-        progress: Progress,
-    ) -> Result<BTreeMap<IndexUidPattern, DetailsExportIndexSettings>> {
-        #[cfg(test)]
-        self.maybe_fail(crate::test_utils::FailureLocation::ProcessExport)?;
-
-        let indexes: Vec<_> = self
-            .index_names()?
-            .into_iter()
-            .flat_map(|uid| {
-                indexes
-                    .iter()
-                    .find(|(pattern, _)| pattern.matches_str(&uid))
-                    .map(|(pattern, settings)| (pattern, uid, settings))
-            })
-            .collect();
-
-        let mut output = BTreeMap::new();
-        let agent = ureq::AgentBuilder::new().timeout(Duration::from_secs(5)).build();
-        let must_stop_processing = self.scheduler.must_stop_processing.clone();
-        for (i, (_pattern, uid, export_settings)) in indexes.iter().enumerate() {
-            if must_stop_processing.get() {
-                return Err(Error::AbortedTask);
-            }
-
-            progress.update_progress(VariableNameStep::<ExportIndex>::new(
-                format!("Exporting index `{uid}`"),
-                i as u32,
-                indexes.len() as u32,
-            ));
-
-            let ExportIndexSettings { filter, override_settings } = export_settings;
-            let index = self.index(uid)?;
-            let index_rtxn = index.read_txn()?;
-            let bearer = api_key.map(|api_key| format!("Bearer {api_key}"));
-
-            // First, check if the index already exists
-            let url = format!("{base_url}/indexes/{uid}");
-            let response = retry(&must_stop_processing, || {
-                let mut request = agent.get(&url);
-                if let Some(bearer) = &bearer {
-                    request = request.set("Authorization", bearer);
-                }
-
-                request.send_bytes(Default::default()).map_err(into_backoff_error)
-            });
-            let index_exists = match response {
-                Ok(response) => response.status() == 200,
-                Err(Error::FromRemoteWhenExporting { code, .. }) if code == "index_not_found" => {
-                    false
-                }
-                Err(e) => return Err(e),
-            };
-
-            let primary_key = index
-                .primary_key(&index_rtxn)
-                .map_err(|e| Error::from_milli(e.into(), Some(uid.to_string())))?;
-
-            // Create the index
-            if !index_exists {
-                let url = format!("{base_url}/indexes");
-                retry(&must_stop_processing, || {
-                    let mut request = agent.post(&url);
-                    if let Some(bearer) = &bearer {
-                        request = request.set("Authorization", bearer);
-                    }
-                    let index_param = json!({ "uid": uid, "primaryKey": primary_key });
-                    request.send_json(&index_param).map_err(into_backoff_error)
-                })?;
-            }
-
-            // Patch the index primary key
-            if index_exists && *override_settings {
-                let url = format!("{base_url}/indexes/{uid}");
-                retry(&must_stop_processing, || {
-                    let mut request = agent.patch(&url);
-                    if let Some(bearer) = &bearer {
-                        request = request.set("Authorization", bearer);
-                    }
-                    let index_param = json!({ "primaryKey": primary_key });
-                    request.send_json(&index_param).map_err(into_backoff_error)
-                })?;
-            }
-
-            // Send the index settings
-            if !index_exists || *override_settings {
-                let mut settings =
-                    settings::settings(&index, &index_rtxn, SecretPolicy::RevealSecrets)
-                        .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
-                // Remove the experimental chat setting if not enabled
-                if self.features().check_chat_completions("exporting chat settings").is_err() {
-                    settings.chat = Setting::NotSet;
-                }
-                // Retry logic for sending settings
-                let url = format!("{base_url}/indexes/{uid}/settings");
-                retry(&must_stop_processing, || {
-                    let mut request = agent.patch(&url);
-                    if let Some(bearer) = bearer.as_ref() {
-                        request = request.set("Authorization", bearer);
-                    }
-                    request.send_json(settings.clone()).map_err(into_backoff_error)
-                })?;
-            }
-
-            let filter = filter
-                .as_ref()
-                .map(Filter::from_json)
-                .transpose()
-                .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?
-                .flatten();
-
-            let filter_universe = filter
-                .map(|f| f.evaluate(&index_rtxn, &index))
-                .transpose()
-                .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
-            let whole_universe = index
-                .documents_ids(&index_rtxn)
-                .map_err(|e| Error::from_milli(e.into(), Some(uid.to_string())))?;
-            let universe = filter_universe.unwrap_or(whole_universe);
-
-            let fields_ids_map = index.fields_ids_map(&index_rtxn)?;
-            let all_fields: Vec<_> = fields_ids_map.iter().map(|(id, _)| id).collect();
-
-            // We don't need to keep this one alive as we will
-            // spawn many threads to process the documents
-            drop(index_rtxn);
-
-            let total_documents = universe.len() as u32;
-            let (step, progress_step) = AtomicDocumentStep::new(total_documents);
-            progress.update_progress(progress_step);
-
-            output.insert(
-                IndexUidPattern::new_unchecked(uid.clone()),
-                DetailsExportIndexSettings {
-                    settings: (*export_settings).clone(),
-                    matched_documents: Some(total_documents as u64),
-                },
-            );
-
-            let limit = payload_size.map(|ps| ps.as_u64() as usize).unwrap_or(20 * 1024 * 1024); // defaults to 20 MiB
-            let documents_url = format!("{base_url}/indexes/{uid}/documents");
-
-            let results = request_threads()
-                .broadcast(|ctx| {
-                    let index_rtxn = index
-                        .read_txn()
-                        .map_err(|e| Error::from_milli(e.into(), Some(uid.to_string())))?;
-
-                    let mut buffer = Vec::new();
-                    let mut tmp_buffer = Vec::new();
-                    let mut compressed_buffer = Vec::new();
-                    for (i, docid) in universe.iter().enumerate() {
-                        if i % ctx.num_threads() != ctx.index() {
-                            continue;
-                        }
-
-                        let document = index
-                            .document(&index_rtxn, docid)
-                            .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
-
-                        let mut document = obkv_to_json(&all_fields, &fields_ids_map, document)
-                            .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
-
-                        // TODO definitely factorize this code
-                        'inject_vectors: {
-                            let embeddings = index
-                                .embeddings(&index_rtxn, docid)
-                                .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
-
-                            if embeddings.is_empty() {
-                                break 'inject_vectors;
-                            }
-
-                            let vectors = document
-                                .entry(RESERVED_VECTORS_FIELD_NAME)
-                                .or_insert(serde_json::Value::Object(Default::default()));
-
-                            let serde_json::Value::Object(vectors) = vectors else {
-                                return Err(Error::from_milli(
-                                    milli::Error::UserError(
-                                        milli::UserError::InvalidVectorsMapType {
-                                            document_id: {
-                                                if let Ok(Some(Ok(index))) = index
-                                                    .external_id_of(
-                                                        &index_rtxn,
-                                                        std::iter::once(docid),
-                                                    )
-                                                    .map(|it| it.into_iter().next())
-                                                {
-                                                    index
-                                                } else {
-                                                    format!("internal docid={docid}")
-                                                }
-                                            },
-                                            value: vectors.clone(),
-                                        },
-                                    ),
-                                    Some(uid.to_string()),
-                                ));
-                            };
-
-                            for (
-                                embedder_name,
-                                EmbeddingsWithMetadata { embeddings, regenerate, has_fragments },
-                            ) in embeddings
-                            {
-                                let embeddings = ExplicitVectors {
-                                    embeddings: Some(
-                                        VectorOrArrayOfVectors::from_array_of_vectors(embeddings),
-                                    ),
-                                    regenerate: regenerate &&
-                                    // Meilisearch does not handle well dumps with fragments, because as the fragments
-                                    // are marked as user-provided,
-                                    // all embeddings would be regenerated on any settings change or document update.
-                                    // To prevent this, we mark embeddings has non regenerate in this case.
-                                    !has_fragments,
-                                };
-                                vectors.insert(
-                                    embedder_name,
-                                    serde_json::to_value(embeddings).unwrap(),
-                                );
-                            }
-                        }
-
-                        tmp_buffer.clear();
-                        serde_json::to_writer(&mut tmp_buffer, &document)
-                            .map_err(milli::InternalError::from)
-                            .map_err(|e| Error::from_milli(e.into(), Some(uid.to_string())))?;
-
-                        // Make sure we put at least one document in the buffer even
-                        // though we might go above the buffer limit before sending
-                        if !buffer.is_empty() && buffer.len() + tmp_buffer.len() > limit {
-                            // We compress the documents before sending them
-                            let mut encoder =
-                                GzEncoder::new(&mut compressed_buffer, Compression::default());
-                            encoder
-                                .write_all(&buffer)
-                                .map_err(|e| Error::from_milli(e.into(), Some(uid.clone())))?;
-                            encoder
-                                .finish()
-                                .map_err(|e| Error::from_milli(e.into(), Some(uid.clone())))?;
-
-                            retry(&must_stop_processing, || {
-                                let mut request = agent.post(&documents_url);
-                                request = request.set("Content-Type", "application/x-ndjson");
-                                request = request.set("Content-Encoding", "gzip");
-                                if let Some(bearer) = &bearer {
-                                    request = request.set("Authorization", bearer);
-                                }
-                                request.send_bytes(&compressed_buffer).map_err(into_backoff_error)
-                            })?;
-                            buffer.clear();
-                            compressed_buffer.clear();
-                        }
-                        buffer.extend_from_slice(&tmp_buffer);
-
-                        if i > 0 && i % 100 == 0 {
-                            step.fetch_add(100, atomic::Ordering::Relaxed);
-                        }
-                    }
-
-                    retry(&must_stop_processing, || {
-                        let mut request = agent.post(&documents_url);
-                        request = request.set("Content-Type", "application/x-ndjson");
-                        if let Some(bearer) = &bearer {
-                            request = request.set("Authorization", bearer);
-                        }
-                        request.send_bytes(&buffer).map_err(into_backoff_error)
-                    })?;
-
-                    Ok(())
-                })
-                .map_err(|e| {
-                    Error::from_milli(
-                        milli::Error::InternalError(InternalError::PanicInThreadPool(e)),
-                        Some(uid.to_string()),
-                    )
-                })?;
-            for result in results {
-                result?;
-            }
-
-            step.store(total_documents, atomic::Ordering::Relaxed);
-        }
-
-        Ok(output)
-    }
-}
-
-fn retry<F>(must_stop_processing: &MustStopProcessing, send_request: F) -> Result<ureq::Response>
-where
-    F: Fn() -> Result<ureq::Response, backoff::Error<ureq::Error>>,
-{
-    match backoff::retry(ExponentialBackoff::default(), || {
-        if must_stop_processing.get() {
-            return Err(backoff::Error::Permanent(ureq::Error::Status(
-                u16::MAX,
-                // 444: Connection Closed Without Response
-                Response::new(444, "Abort", "Aborted task").unwrap(),
-            )));
-        }
-        send_request()
-    }) {
-        Ok(response) => Ok(response),
-        Err(backoff::Error::Permanent(e)) => Err(ureq_error_into_error(e)),
-        Err(backoff::Error::Transient { err, retry_after: _ }) => Err(ureq_error_into_error(err)),
-    }
-}
-
-fn into_backoff_error(err: ureq::Error) -> backoff::Error<ureq::Error> {
-    match err {
-        // Those code status must trigger an automatic retry
-        // <https://www.restapitutorial.com/advanced/responses/retries>
-        ureq::Error::Status(408 | 429 | 500 | 502 | 503 | 504, _) => {
-            backoff::Error::Transient { err, retry_after: None }
-        }
-        ureq::Error::Status(_, _) => backoff::Error::Permanent(err),
-        ureq::Error::Transport(_) => backoff::Error::Transient { err, retry_after: None },
-    }
-}
-
-/// Converts a `ureq::Error` into an `Error`.
-fn ureq_error_into_error(error: ureq::Error) -> Error {
-    #[derive(Deserialize)]
-    struct MeiliError {
-        message: String,
-        code: String,
-        r#type: String,
-        link: String,
-    }
-
-    match error {
-        // This is a workaround to handle task abortion - the error propagation path
-        // makes it difficult to cleanly surface the abortion at this level.
-        ureq::Error::Status(u16::MAX, _) => Error::AbortedTask,
-        ureq::Error::Status(_, response) => match response.into_json() {
-            Ok(MeiliError { message, code, r#type, link }) => {
-                Error::FromRemoteWhenExporting { message, code, r#type, link }
-            }
-            Err(e) => e.into(),
-        },
-        ureq::Error::Transport(transport) => io::Error::new(io::ErrorKind::Other, transport).into(),
-    }
-}
-
-enum ExportIndex {}

crates/index-scheduler/src/scheduler/process_index_operation.rs

@@ -1,13 +1,11 @@
-use std::sync::Arc;
-
 use bumpalo::collections::CollectIn;
 use bumpalo::Bump;
 use meilisearch_types::heed::RwTxn;
 use meilisearch_types::milli::documents::PrimaryKey;
-use meilisearch_types::milli::progress::{EmbedderStats, Progress};
+use meilisearch_types::milli::progress::Progress;
 use meilisearch_types::milli::update::new::indexer::{self, UpdateByFunction};
 use meilisearch_types::milli::update::DocumentAdditionResult;
-use meilisearch_types::milli::{self, ChannelCongestion, Filter};
+use meilisearch_types::milli::{self, Filter, ThreadPoolNoAbortBuilder};
 use meilisearch_types::settings::apply_settings_to_builder;
 use meilisearch_types::tasks::{Details, KindWithContent, Status, Task};
 use meilisearch_types::Index;
@@ -26,7 +24,7 @@ impl IndexScheduler {
     /// The list of processed tasks.
     #[tracing::instrument(
         level = "trace",
-        skip(self, index_wtxn, index, progress, embedder_stats),
+        skip(self, index_wtxn, index, progress),
         target = "indexing::scheduler"
     )]
     pub(crate) fn apply_index_operation<'i>(
@@ -34,10 +32,10 @@ impl IndexScheduler {
         index_wtxn: &mut RwTxn<'i>,
         index: &'i Index,
         operation: IndexOperation,
-        progress: &Progress,
+        progress: Progress,
-        embedder_stats: Arc<EmbedderStats>,
+    ) -> Result<Vec<Task>> {
-    ) -> Result<(Vec<Task>, Option<ChannelCongestion>)> {
         let indexer_alloc = Bump::new();
+
         let started_processing_at = std::time::Instant::now();
         let must_stop_processing = self.scheduler.must_stop_processing.clone();
 
@@ -62,23 +60,25 @@ impl IndexScheduler {
                     };
                 }
 
-                Ok((tasks, None))
+                Ok(tasks)
             }
-            IndexOperation::DocumentOperation { index_uid, primary_key, operations, mut tasks } => {
+            IndexOperation::DocumentOperation {
+                index_uid,
+                primary_key,
+                method,
+                operations,
+                mut tasks,
+            } => {
                 progress.update_progress(DocumentOperationProgress::RetrievingConfig);
                 // TODO: at some point, for better efficiency we might want to reuse the bumpalo for successive batches.
                 // this is made difficult by the fact we're doing private clones of the index scheduler and sending it
                 // to a fresh thread.
                 let mut content_files = Vec::new();
                 for operation in &operations {
-                    match operation {
+                    if let DocumentOperation::Add(content_uuid) = operation {
-                        DocumentOperation::Replace(content_uuid)
+                        let content_file = self.queue.file_store.get_update(*content_uuid)?;
-                        | DocumentOperation::Update(content_uuid) => {
+                        let mmap = unsafe { memmap2::Mmap::map(&content_file)? };
-                            let content_file = self.queue.file_store.get_update(*content_uuid)?;
+                        content_files.push(mmap);
-                            let mmap = unsafe { memmap2::Mmap::map(&content_file)? };
-                            content_files.push(mmap);
-                        }
-                        _ => (),
                     }
                 }
 
@@ -87,24 +87,17 @@ impl IndexScheduler {
                 let mut new_fields_ids_map = db_fields_ids_map.clone();
 
                 let mut content_files_iter = content_files.iter();
-                let mut indexer = indexer::DocumentOperation::new();
+                let mut indexer = indexer::DocumentOperation::new(method);
                 let embedders = index
-                    .embedding_configs()
                     .embedding_configs(index_wtxn)
-                    .map_err(|e| Error::from_milli(e.into(), Some(index_uid.clone())))?;
+                    .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
                 let embedders = self.embedders(index_uid.clone(), embedders)?;
                 for operation in operations {
                     match operation {
-                        DocumentOperation::Replace(_content_uuid) => {
+                        DocumentOperation::Add(_content_uuid) => {
                             let mmap = content_files_iter.next().unwrap();
                             indexer
-                                .replace_documents(mmap)
+                                .add_documents(mmap)
-                                .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
-                        }
-                        DocumentOperation::Update(_content_uuid) => {
-                            let mmap = content_files_iter.next().unwrap();
-                            indexer
-                                .update_documents(mmap)
                                 .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
                         }
                         DocumentOperation::Delete(document_ids) => {
@@ -117,8 +110,18 @@ impl IndexScheduler {
                     }
                 }
 
+                let local_pool;
                 let indexer_config = self.index_mapper.indexer_config();
-                let pool = &indexer_config.thread_pool;
+                let pool = match &indexer_config.thread_pool {
+                    Some(pool) => pool,
+                    None => {
+                        local_pool = ThreadPoolNoAbortBuilder::new()
+                            .thread_name(|i| format!("indexing-thread-{i}"))
+                            .build()
+                            .unwrap();
+                        &local_pool
+                    }
+                };
 
                 progress.update_progress(DocumentOperationProgress::ComputingDocumentChanges);
                 let (document_changes, operation_stats, primary_key) = indexer
@@ -166,25 +169,21 @@ impl IndexScheduler {
                 }
 
                 progress.update_progress(DocumentOperationProgress::Indexing);
-                let mut congestion = None;
                 if tasks.iter().any(|res| res.error.is_none()) {
-                    congestion = Some(
+                    indexer::index(
-                        indexer::index(
+                        index_wtxn,
-                            index_wtxn,
+                        index,
-                            index,
+                        pool,
-                            pool,
+                        indexer_config.grenad_parameters(),
-                            indexer_config.grenad_parameters(),
+                        &db_fields_ids_map,
-                            &db_fields_ids_map,
+                        new_fields_ids_map,
-                            new_fields_ids_map,
+                        primary_key,
-                            primary_key,
+                        &document_changes,
-                            &document_changes,
+                        embedders,
-                            embedders,
+                        &|| must_stop_processing.get(),
-                            &|| must_stop_processing.get(),
+                        &progress,
-                            progress,
+                    )
-                            &embedder_stats,
+                    .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
-                        )
-                        .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?,
-                    );
 
                     let addition = DocumentAdditionResult {
                         indexed_documents: candidates_count,
@@ -196,7 +195,7 @@ impl IndexScheduler {
                     tracing::info!(indexing_result = ?addition, processed_in = ?started_processing_at.elapsed(), "document indexing done");
                 }
 
-                Ok((tasks, congestion))
+                Ok(tasks)
             }
             IndexOperation::DocumentEdition { index_uid, mut task } => {
                 progress.update_progress(DocumentEditionProgress::RetrievingConfig);
@@ -244,7 +243,7 @@ impl IndexScheduler {
                         edited_documents: Some(0),
                     });
 
-                    return Ok((vec![task], None));
+                    return Ok(vec![task]);
                 }
 
                 let rtxn = index.read_txn()?;
@@ -259,10 +258,19 @@ impl IndexScheduler {
 
                 let result_count = Ok((candidates.len(), candidates.len())) as Result<_>;
 
-                let mut congestion = None;
                 if task.error.is_none() {
+                    let local_pool;
                     let indexer_config = self.index_mapper.indexer_config();
-                    let pool = &indexer_config.thread_pool;
+                    let pool = match &indexer_config.thread_pool {
+                        Some(pool) => pool,
+                        None => {
+                            local_pool = ThreadPoolNoAbortBuilder::new()
+                                .thread_name(|i| format!("indexing-thread-{i}"))
+                                .build()
+                                .unwrap();
+                            &local_pool
+                        }
+                    };
 
                     let candidates_count = candidates.len();
                     progress.update_progress(DocumentEditionProgress::ComputingDocumentChanges);
@@ -275,29 +283,25 @@ impl IndexScheduler {
                         })
                         .unwrap()?;
                     let embedders = index
-                        .embedding_configs()
                         .embedding_configs(index_wtxn)
-                        .map_err(|err| Error::from_milli(err.into(), Some(index_uid.clone())))?;
+                        .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
                     let embedders = self.embedders(index_uid.clone(), embedders)?;
 
                     progress.update_progress(DocumentEditionProgress::Indexing);
-                    congestion = Some(
+                    indexer::index(
-                        indexer::index(
+                        index_wtxn,
-                            index_wtxn,
+                        index,
-                            index,
+                        pool,
-                            pool,
+                        indexer_config.grenad_parameters(),
-                            indexer_config.grenad_parameters(),
+                        &db_fields_ids_map,
-                            &db_fields_ids_map,
+                        new_fields_ids_map,
-                            new_fields_ids_map,
+                        None, // cannot change primary key in DocumentEdition
-                            None, // cannot change primary key in DocumentEdition
+                        &document_changes,
-                            &document_changes,
+                        embedders,
-                            embedders,
+                        &|| must_stop_processing.get(),
-                            &|| must_stop_processing.get(),
+                        &progress,
-                            progress,
+                    )
-                            &embedder_stats,
+                    .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
-                        )
-                        .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?,
-                    );
 
                     let addition = DocumentAdditionResult {
                         indexed_documents: candidates_count,
@@ -333,7 +337,7 @@ impl IndexScheduler {
                     }
                 }
 
-                Ok((vec![task], congestion))
+                Ok(vec![task])
             }
             IndexOperation::DocumentDeletion { mut tasks, index_uid } => {
                 progress.update_progress(DocumentDeletionProgress::RetrievingConfig);
@@ -400,7 +404,7 @@ impl IndexScheduler {
                 }
 
                 if to_delete.is_empty() {
-                    return Ok((tasks, None));
+                    return Ok(tasks);
                 }
 
                 let rtxn = index.read_txn()?;
@@ -414,10 +418,19 @@ impl IndexScheduler {
                     PrimaryKey::new_or_insert(primary_key, &mut new_fields_ids_map)
                         .map_err(|err| Error::from_milli(err.into(), Some(index_uid.clone())))?;
 
-                let mut congestion = None;
                 if !tasks.iter().all(|res| res.error.is_some()) {
+                    let local_pool;
                     let indexer_config = self.index_mapper.indexer_config();
-                    let pool = &indexer_config.thread_pool;
+                    let pool = match &indexer_config.thread_pool {
+                        Some(pool) => pool,
+                        None => {
+                            local_pool = ThreadPoolNoAbortBuilder::new()
+                                .thread_name(|i| format!("indexing-thread-{i}"))
+                                .build()
+                                .unwrap();
+                            &local_pool
+                        }
+                    };
 
                     progress.update_progress(DocumentDeletionProgress::DeleteDocuments);
                     let mut indexer = indexer::DocumentDeletion::new();
@@ -425,29 +438,25 @@ impl IndexScheduler {
                     indexer.delete_documents_by_docids(to_delete);
                     let document_changes = indexer.into_changes(&indexer_alloc, primary_key);
                     let embedders = index
-                        .embedding_configs()
                         .embedding_configs(index_wtxn)
-                        .map_err(|err| Error::from_milli(err.into(), Some(index_uid.clone())))?;
+                        .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
                     let embedders = self.embedders(index_uid.clone(), embedders)?;
 
                     progress.update_progress(DocumentDeletionProgress::Indexing);
-                    congestion = Some(
+                    indexer::index(
-                        indexer::index(
+                        index_wtxn,
-                            index_wtxn,
+                        index,
-                            index,
+                        pool,
-                            pool,
+                        indexer_config.grenad_parameters(),
-                            indexer_config.grenad_parameters(),
+                        &db_fields_ids_map,
-                            &db_fields_ids_map,
+                        new_fields_ids_map,
-                            new_fields_ids_map,
+                        None, // document deletion never changes primary key
-                            None, // document deletion never changes primary key
+                        &document_changes,
-                            &document_changes,
+                        embedders,
-                            embedders,
+                        &|| must_stop_processing.get(),
-                            &|| must_stop_processing.get(),
+                        &progress,
-                            progress,
+                    )
-                            &embedder_stats,
+                    .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
-                        )
-                        .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?,
-                    );
 
                     let addition = DocumentAdditionResult {
                         indexed_documents: candidates_count,
@@ -459,7 +468,7 @@ impl IndexScheduler {
                     tracing::info!(indexing_result = ?addition, processed_in = ?started_processing_at.elapsed(), "document indexing done");
                 }
 
-                Ok((tasks, congestion))
+                Ok(tasks)
             }
             IndexOperation::Settings { index_uid, settings, mut tasks } => {
                 progress.update_progress(SettingsProgress::RetrievingAndMergingTheSettings);
@@ -477,11 +486,14 @@ impl IndexScheduler {
                 }
 
                 progress.update_progress(SettingsProgress::ApplyTheSettings);
-                let congestion = builder
+                builder
-                    .execute(&|| must_stop_processing.get(), progress, embedder_stats)
+                    .execute(
+                        |indexing_step| tracing::debug!(update = ?indexing_step),
+                        || must_stop_processing.get(),
+                    )
                     .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
 
-                Ok((tasks, congestion))
+                Ok(tasks)
             }
             IndexOperation::DocumentClearAndSetting {
                 index_uid,
@@ -489,28 +501,26 @@ impl IndexScheduler {
                 settings,
                 settings_tasks,
             } => {
-                let (mut import_tasks, _congestion) = self.apply_index_operation(
+                let mut import_tasks = self.apply_index_operation(
                     index_wtxn,
                     index,
                     IndexOperation::DocumentClear {
                         index_uid: index_uid.clone(),
                         tasks: cleared_tasks,
                     },
-                    progress,
+                    progress.clone(),
-                    embedder_stats.clone(),
                 )?;
 
-                let (settings_tasks, _congestion) = self.apply_index_operation(
+                let settings_tasks = self.apply_index_operation(
                     index_wtxn,
                     index,
                     IndexOperation::Settings { index_uid, settings, tasks: settings_tasks },
                     progress,
-                    embedder_stats,
                 )?;
 
                 let mut tasks = settings_tasks;
                 tasks.append(&mut import_tasks);
-                Ok((tasks, None))
+                Ok(tasks)
             }
         }
     }

crates/index-scheduler/src/scheduler/process_snapshot_creation.rs

@@ -3,11 +3,12 @@ use std::fs;
 use std::sync::atomic::Ordering;
 
 use meilisearch_types::heed::CompactionOption;
-use meilisearch_types::milli::progress::{Progress, VariableNameStep};
+use meilisearch_types::milli::progress::Progress;
+use meilisearch_types::milli::{self};
 use meilisearch_types::tasks::{Status, Task};
 use meilisearch_types::{compression, VERSION_FILE_NAME};
 
-use crate::processing::{AtomicUpdateFileStep, SnapshotCreationProgress};
+use crate::processing::{AtomicUpdateFileStep, SnapshotCreationProgress, VariableNameStep};
 use crate::{Error, IndexScheduler, Result};
 
 impl IndexScheduler {
@@ -27,7 +28,7 @@ impl IndexScheduler {
 
         // 2. Snapshot the index-scheduler LMDB env
         //
-        // When we call copy_to_path, LMDB opens a read transaction by itself,
+        // When we call copy_to_file, LMDB opens a read transaction by itself,
         // we can't provide our own. It is an issue as we would like to know
         // the update files to copy but new ones can be enqueued between the copy
         // of the env and the new transaction we open to retrieve the enqueued tasks.
@@ -41,12 +42,7 @@ impl IndexScheduler {
         progress.update_progress(SnapshotCreationProgress::SnapshotTheIndexScheduler);
         let dst = temp_snapshot_dir.path().join("tasks");
         fs::create_dir_all(&dst)?;
-        let compaction_option = if self.scheduler.experimental_no_snapshot_compaction {
+        self.env.copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)?;
-            CompactionOption::Disabled
-        } else {
-            CompactionOption::Enabled
-        };
-        self.env.copy_to_path(dst.join("data.mdb"), compaction_option)?;
 
         // 2.2 Create a read transaction on the index-scheduler
         let rtxn = self.env.read_txn()?;
@@ -78,14 +74,12 @@ impl IndexScheduler {
 
         for (i, result) in index_mapping.iter(&rtxn)?.enumerate() {
             let (name, uuid) = result?;
-            progress.update_progress(VariableNameStep::<SnapshotCreationProgress>::new(
+            progress.update_progress(VariableNameStep::new(name, i as u32, nb_indexes));
-                name, i as u32, nb_indexes,
-            ));
             let index = self.index_mapper.index(&rtxn, name)?;
             let dst = temp_snapshot_dir.path().join("indexes").join(uuid.to_string());
             fs::create_dir_all(&dst)?;
             index
-                .copy_to_path(dst.join("data.mdb"), compaction_option)
+                .copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)
                 .map_err(|e| Error::from_milli(e, Some(name.to_string())))?;
         }
 
@@ -95,7 +89,14 @@ impl IndexScheduler {
         progress.update_progress(SnapshotCreationProgress::SnapshotTheApiKeys);
         let dst = temp_snapshot_dir.path().join("auth");
         fs::create_dir_all(&dst)?;
-        self.scheduler.auth_env.copy_to_path(dst.join("data.mdb"), compaction_option)?;
+        // TODO We can't use the open_auth_store_env function here but we should
+        let auth = unsafe {
+            milli::heed::EnvOpenOptions::new()
+                .map_size(1024 * 1024 * 1024) // 1 GiB
+                .max_dbs(2)
+                .open(&self.scheduler.auth_path)
+        }?;
+        auth.copy_to_file(dst.join("data.mdb"), CompactionOption::Enabled)?;
 
         // 5. Copy and tarball the flat snapshot
         progress.update_progress(SnapshotCreationProgress::CreateTheTarball);

crates/index-scheduler/src/scheduler/process_upgrade.rs

@@ -1,92 +0,0 @@
-use meilisearch_types::milli;
-use meilisearch_types::milli::progress::{Progress, VariableNameStep};
-
-use crate::{Error, IndexScheduler, Result};
-
-impl IndexScheduler {
-    pub(super) fn process_upgrade(
-        &self,
-        db_version: (u32, u32, u32),
-        progress: Progress,
-    ) -> Result<()> {
-        #[cfg(test)]
-        self.maybe_fail(crate::test_utils::FailureLocation::ProcessUpgrade)?;
-
-        let indexes = self.index_names()?;
-
-        for (i, uid) in indexes.iter().enumerate() {
-            let must_stop_processing = self.scheduler.must_stop_processing.clone();
-
-            if must_stop_processing.get() {
-                return Err(Error::AbortedTask);
-            }
-            progress.update_progress(VariableNameStep::<UpgradeIndex>::new(
-                format!("Upgrading index `{uid}`"),
-                i as u32,
-                indexes.len() as u32,
-            ));
-            let index = self.index(uid)?;
-            let mut index_wtxn = index.write_txn()?;
-            let regen_stats = milli::update::upgrade::upgrade(
-                &mut index_wtxn,
-                &index,
-                db_version,
-                || must_stop_processing.get(),
-                progress.clone(),
-            )
-            .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
-            if regen_stats {
-                let stats = crate::index_mapper::IndexStats::new(&index, &index_wtxn)
-                    .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
-                index_wtxn.commit()?;
-
-                // Release wtxn as soon as possible because it stops us from registering tasks
-                let mut index_schd_wtxn = self.env.write_txn()?;
-                self.index_mapper.store_stats_of(&mut index_schd_wtxn, uid, &stats)?;
-                index_schd_wtxn.commit()?;
-            } else {
-                index_wtxn.commit()?;
-            }
-        }
-
-        Ok(())
-    }
-
-    pub fn process_rollback(&self, db_version: (u32, u32, u32), progress: &Progress) -> Result<()> {
-        let mut wtxn = self.env.write_txn()?;
-        tracing::info!(?db_version, "roll back index scheduler version");
-        self.version.set_version(&mut wtxn, db_version)?;
-        let db_path = self.scheduler.version_file_path.parent().unwrap();
-        wtxn.commit()?;
-
-        let indexes = self.index_names()?;
-
-        tracing::info!("roll backing all indexes");
-        for (i, uid) in indexes.iter().enumerate() {
-            progress.update_progress(VariableNameStep::<UpgradeIndex>::new(
-                format!("Rollbacking index `{uid}`"),
-                i as u32,
-                indexes.len() as u32,
-            ));
-            let index_schd_rtxn = self.env.read_txn()?;
-
-            let rollback_outcome =
-                self.index_mapper.rollback_index(&index_schd_rtxn, uid, db_version)?;
-            if !rollback_outcome.succeeded() {
-                return Err(crate::Error::RollbackFailed { index: uid.clone(), rollback_outcome });
-            }
-        }
-
-        tracing::info!(?db_path, ?db_version, "roll back version file");
-        meilisearch_types::versioning::create_version_file(
-            db_path,
-            db_version.0,
-            db_version.1,
-            db_version.2,
-        )?;
-
-        Ok(())
-    }
-}
-
-enum UpgradeIndex {}

crates/index-scheduler/src/scheduler/snapshots/index_scheduler__scheduler__test__settings_update-7.snap

@@ -1,17 +0,0 @@
----
-source: crates/index-scheduler/src/scheduler/test.rs
-expression: config.embedder_options
----
-{
-  "Rest": {
-    "api_key": "My super secret",
-    "distribution": null,
-    "dimensions": 4,
-    "url": "http://localhost:7777",
-    "request": "{{text}}",
-    "search_fragments": {},
-    "indexing_fragments": {},
-    "response": "{{embedding}}",
-    "headers": {}
-  }
-}

crates/index-scheduler/src/scheduler/snapshots/index_scheduler__scheduler__test_embedders__import_vectors-14.snap

@@ -1,12 +0,0 @@
----
-source: crates/index-scheduler/src/scheduler/test_embedders.rs
-expression: simple_hf_config.embedder_options
----
-{
-  "HuggingFace": {
-    "model": "sentence-transformers/all-MiniLM-L6-v2",
-    "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
-    "distribution": null,
-    "pooling": "useModel"
-  }
-}

crates/index-scheduler/src/scheduler/snapshots/index_scheduler__scheduler__test_embedders__import_vectors-27.snap

@@ -1,15 +0,0 @@
----
-source: crates/index-scheduler/src/scheduler/test_embedders.rs
-expression: doc
----
-{
-  "doggo": "Intel",
-  "breed": "beagle",
-  "_vectors": {
-    "noise": [
-      0.1,
-      0.2,
-      0.3
-    ]
-  }
-}

crates/index-scheduler/src/scheduler/snapshots/index_scheduler__scheduler__test_embedders__import_vectors-40.snap

@@ -1,15 +0,0 @@
----
-source: crates/index-scheduler/src/scheduler/test_embedders.rs
-expression: doc
----
-{
-  "doggo": "kefir",
-  "breed": "patou",
-  "_vectors": {
-    "noise": [
-      0.1,
-      0.2,
-      0.3
-    ]
-  }
-}

crates/index-scheduler/src/scheduler/snapshots/index_scheduler__scheduler__test_embedders__import_vectors-8.snap

@@ -1,17 +1,12 @@
 ---
 source: crates/index-scheduler/src/scheduler/test_embedders.rs
-expression: fakerest_config.embedder_options
+expression: simple_hf_config.embedder_options
+snapshot_kind: text
 ---
 {
-  "Rest": {
+  "HuggingFace": {
-    "api_key": "My super secret",
+    "model": "sentence-transformers/all-MiniLM-L6-v2",
-    "distribution": null,
+    "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
-    "dimensions": 384,
+    "distribution": null
-    "url": "http://localhost:7777",
-    "request": "{{text}}",
-    "search_fragments": {},
-    "indexing_fragments": {},
-    "response": "{{embedding}}",
-    "headers": {}
   }
 }

crates/index-scheduler/src/scheduler/snapshots/test.rs/cancel_enqueued_task/cancel_processed.snap

@@ -1,5 +1,6 @@
 ---
 source: crates/index-scheduler/src/scheduler/test.rs
+snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -39,7 +40,7 @@ catto [0,]
 [timestamp] [0,1,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"receivedDocuments":1,"indexedDocuments":0,"matchedTasks":1,"canceledTasks":1,"originalFilter":"test_query"}, stats: {"totalNbTasks":2,"status":{"succeeded":1,"canceled":1},"types":{"documentAdditionOrUpdate":1,"taskCancelation":1},"indexUids":{"catto":1}}, stop reason: "created batch containing only task with id 1 of type `taskCancelation` that cannot be batched with any other task.", }
+0 {uid: 0, details: {"receivedDocuments":1,"indexedDocuments":0,"matchedTasks":1,"canceledTasks":1,"originalFilter":"test_query"}, stats: {"totalNbTasks":2,"status":{"succeeded":1,"canceled":1},"types":{"documentAdditionOrUpdate":1,"taskCancelation":1},"indexUids":{"catto":1}}, }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,1,]

crates/index-scheduler/src/scheduler/snapshots/test.rs/cancel_mix_of_tasks/aborted_indexation.snap

@@ -1,10 +1,11 @@
 ---
 source: crates/index-scheduler/src/scheduler/test.rs
+snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch Some(1):
 [1,]
-{uid: 1, details: {"receivedDocuments":1,"indexedDocuments":null}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"documentAdditionOrUpdate":1},"indexUids":{"beavero":1}}, stop reason: "batched all enqueued tasks for index `beavero`", }
+{uid: 1, details: {"receivedDocuments":1,"indexedDocuments":null}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"documentAdditionOrUpdate":1},"indexUids":{"beavero":1}}, }
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, batch_uid: 0, status: succeeded, details: { received_documents: 1, indexed_documents: Some(1) }, kind: DocumentAdditionOrUpdate { index_uid: "catto", primary_key: None, method: ReplaceDocuments, content_file: 00000000-0000-0000-0000-000000000000, documents_count: 1, allow_index_creation: true }}
@@ -46,7 +47,7 @@ catto: { number_of_documents: 1, field_distribution: {"id": 1} }
 [timestamp] [0,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"receivedDocuments":1,"indexedDocuments":1}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"documentAdditionOrUpdate":1},"indexUids":{"catto":1}}, stop reason: "batched all enqueued tasks for index `catto`", }
+0 {uid: 0, details: {"receivedDocuments":1,"indexedDocuments":1}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"documentAdditionOrUpdate":1},"indexUids":{"catto":1}}, }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]