Rename Body::with_file

Fix api key action inconsistencies

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

@@ -17,7 +17,7 @@ jobs:
         uses: actions/checkout@v3
 
       - name: Validate PR milestone
-        uses: actions/github-script@v6
+        uses: actions/github-script@v7
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           script: |

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

@@ -44,7 +44,7 @@ jobs:
     if: github.event.label.name == 'db change'
     steps:
       - name: Add comment
-        uses: actions/github-script@v6
+        uses: actions/github-script@v7
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           script: |

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

@@ -4,22 +4,22 @@ on:
   pull_request:
     types: [opened, synchronize, reopened, labeled, unlabeled]
 
-env:
-  GH_TOKEN: ${{ secrets.MEILI_BOT_GH_PAT }}
-
 jobs:
   check-labels:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v2
+        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/meilisearch/meilisearch/issues/${{ github.event.pull_request.number }}/labels -q .[].name)
+          LABELS=$(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

.github/workflows/milestone-workflow.yml

@@ -150,6 +150,7 @@ jobs:
 
   update-ruleset:
     runs-on: ubuntu-latest
+    if: github.event.action == 'created'
     steps:
       - uses: actions/checkout@v3
       - name: Install jq
@@ -162,15 +163,18 @@ jobs:
           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/$RULESET_ID --jq '{ conditions: .conditions }')
+          CONDITIONS=$(gh api repos/meilisearch/meilisearch/rulesets/${{ env.RULESET_ID }} --jq '{ conditions: .conditions }')
 
           # Update the conditions by appending the milestone version
-          UPDATED_CONDITIONS=$(echo $CONDITIONS | jq '.conditions.ref_name.include += ["refs/heads/release-'$MILESTONE_VERSION'"]')
+          UPDATED_CONDITIONS=$(echo $CONDITIONS | jq '.conditions.ref_name.include += ["refs/heads/release-'${{ env.MILESTONE_VERSION }}'"]')
 
           # Update the ruleset from stdin (-)
           echo $UPDATED_CONDITIONS |
-            gh api repos/meilisearch/meilisearch/rulesets/$RULESET_ID \
+            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" \

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

@@ -32,7 +32,7 @@ jobs:
       - name: Build deb package
         run: cargo deb -p meilisearch -o target/debian/meilisearch.deb
       - name: Upload debian pkg to release
-        uses: svenstaro/upload-release-action@2.7.0
+        uses: svenstaro/upload-release-action@2.11.1
         with:
           repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
           file: target/debian/meilisearch.deb

.github/workflows/publish-binaries.yml

@@ -51,7 +51,7 @@ jobs:
       # No need to upload binaries for dry run (cron)
       - name: Upload binaries to release
         if: github.event_name == 'release'
-        uses: svenstaro/upload-release-action@2.7.0
+        uses: svenstaro/upload-release-action@2.11.1
         with:
           repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
           file: target/release/meilisearch
@@ -81,7 +81,7 @@ jobs:
       # No need to upload binaries for dry run (cron)
       - name: Upload binaries to release
         if: github.event_name == 'release'
-        uses: svenstaro/upload-release-action@2.7.0
+        uses: svenstaro/upload-release-action@2.11.1
         with:
           repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
           file: target/release/${{ matrix.artifact_name }}
@@ -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@2.7.0
+        uses: svenstaro/upload-release-action@2.11.1
         with:
           repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
           file: target/${{ matrix.target }}/release/meilisearch
@@ -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@2.7.0
+        uses: svenstaro/upload-release-action@2.11.1
         with:
           repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
           file: target/${{ matrix.target }}/release/meilisearch

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

@@ -104,3 +104,22 @@ 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@v4
+      - uses: actions/checkout@v3
       - name: Define the Docker image we need to use
         id: define-image
         run: |
@@ -46,7 +46,7 @@ jobs:
       MEILISEARCH_VERSION: ${{ needs.define-docker-image.outputs.docker-image }}
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         with:
           repository: meilisearch/meilisearch-dotnet
       - name: Setup .NET Core
@@ -75,7 +75,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         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@v4
+      - uses: actions/checkout@v3
         with:
           repository: meilisearch/meilisearch-go
       - name: Get dependencies
@@ -129,7 +129,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         with:
           repository: meilisearch/meilisearch-java
       - name: Set up Java
@@ -156,7 +156,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         with:
           repository: meilisearch/meilisearch-js
       - name: Setup node
@@ -191,7 +191,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         with:
           repository: meilisearch/meilisearch-php
       - name: Install PHP
@@ -220,7 +220,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         with:
           repository: meilisearch/meilisearch-python
       - name: Set up Python
@@ -245,7 +245,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         with:
           repository: meilisearch/meilisearch-ruby
       - name: Set up Ruby 3
@@ -270,7 +270,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         with:
           repository: meilisearch/meilisearch-rust
       - name: Build
@@ -291,7 +291,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         with:
           repository: meilisearch/meilisearch-swift
       - name: Run tests
@@ -314,7 +314,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         with:
           repository: meilisearch/meilisearch-js-plugins
       - name: Setup node
@@ -345,7 +345,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         with:
           repository: meilisearch/meilisearch-rails
       - name: Set up Ruby 3
@@ -369,7 +369,7 @@ jobs:
         ports:
           - '7700:7700'
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         with:
           repository: meilisearch/meilisearch-symfony
       - name: Install PHP

.github/workflows/test-suite.yml

@@ -21,7 +21,7 @@ jobs:
       # Use ubuntu-22.04 to compile with glibc 2.35
       image: ubuntu:22.04
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - name: Install needed dependencies
         run: |
           apt-get update && apt-get install -y curl
@@ -29,7 +29,7 @@ jobs:
       - name: Setup test with Rust stable
         uses: dtolnay/rust-toolchain@1.85
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.7.7
+        uses: Swatinem/rust-cache@v2.8.0
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
         with:
@@ -51,7 +51,7 @@ jobs:
     steps:
       - uses: actions/checkout@v3
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.7.7
+        uses: Swatinem/rust-cache@v2.8.0
       - uses: dtolnay/rust-toolchain@1.85
       - name: Run cargo check without any default features
         uses: actions-rs/cargo@v1
@@ -91,7 +91,7 @@ jobs:
     env:
       MEILI_TEST_OLLAMA_SERVER: "http://localhost:11434"
     steps:
-      - uses: actions/checkout@v1
+      - uses: actions/checkout@v3
       - name: Install Ollama
         run: |
           curl -fsSL https://ollama.com/install.sh | sudo -E sh
@@ -155,7 +155,7 @@ jobs:
           apt-get install build-essential -y
       - uses: dtolnay/rust-toolchain@1.85
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.7.7
+        uses: Swatinem/rust-cache@v2.8.0
       - name: Run tests in debug
         uses: actions-rs/cargo@v1
         with:
@@ -172,7 +172,7 @@ jobs:
           profile: minimal
           components: clippy
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.7.7
+        uses: Swatinem/rust-cache@v2.8.0
       - name: Run cargo clippy
         uses: actions-rs/cargo@v1
         with:
@@ -191,7 +191,7 @@ jobs:
           override: true
           components: rustfmt
       - name: Cache dependencies
-        uses: Swatinem/rust-cache@v2.7.7
+        uses: Swatinem/rust-cache@v2.8.0
       - 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

.gitignore

@@ -5,18 +5,27 @@
 **/*.json_lines
 **/*.rs.bk
 /*.mdb
-/data.ms
+/*.ms
 /snapshots
 /dumps
 /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

@@ -57,9 +57,17 @@ 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 standard `$HOME/.cache/lindera` directory:
+We recommend using the `$HOME/.cache/meili/lindera` directory:
 ```sh
-export LINDERA_CACHE=$HOME/.cache/lindera
+export LINDERA_CACHE=$HOME/.cache/meili/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.

Cargo.toml

@@ -22,7 +22,7 @@ members = [
 ]
 
 [workspace.package]
-version = "1.14.0"
+version = "1.16.0"
 authors = [
     "Quentin de Quelen <quentin@dequelen.me>",
     "Clément Renault <clement@meilisearch.com>",

LICENSE

@@ -19,3 +19,11 @@ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.
+
+---
+
+🔒 Meilisearch Enterprise Edition (EE)
+
+Certain parts of this codebase are not licensed under the MIT license and governed by the Business Source License 1.1.
+
+See the LICENSE-EE file for details.

LICENSE-EE

@@ -0,0 +1,67 @@
+Business Source License 1.1 – Adapted for Meili SAS
+This license is based on the Business Source License version 1.1, as published by MariaDB Corporation Ab.
+
+Parameters
+
+Licensor: Meili SAS
+
+Licensed Work: Any file explicitly marked as “Enterprise Edition (EE)” or “governed by the Business Source License”.
+
+Additional Use Grant:
+You may use, modify, and distribute the Licensed Work for non-production purposes only, such as testing, development, or evaluation.
+
+Production use of the Licensed Work requires a commercial license agreement with Meilisearch. Contact bonjour@meilisearch.com for licensing.
+
+Change License: MIT
+
+Change Date: Four years from the date the Licensed Work is published.
+
+This License does not apply to any code outside of the Licensed Work, which remains under the MIT license.
+
+For information about alternative licensing arrangements for the Licensed Work,
+please contact bonjour@meilisearch.com or sales@meilisearch.com.
+
+Notice
+
+Business Source License 1.1
+
+Terms
+
+The Licensor hereby grants you the right to copy, modify, create derivative
+works, redistribute, and make non-production use of the Licensed Work. The
+Licensor may make an Additional Use Grant, above, permitting limited production use.
+
+Effective on the Change Date, or the fourth anniversary of the first publicly
+available distribution of a specific version of the Licensed Work under this
+License, whichever comes first, the Licensor hereby grants you rights under
+the terms of the Change License, and the rights granted in the paragraph
+above terminate.
+
+If your use of the Licensed Work does not comply with the requirements
+currently in effect as described in this License, you must purchase a
+commercial license from the Licensor, its affiliated entities, or authorized
+resellers, or you must refrain from using the Licensed Work.
+
+All copies of the original and modified Licensed Work, and derivative works
+of the Licensed Work, are subject to this License. This License applies
+separately for each version of the Licensed Work and the Change Date may vary
+for each version of the Licensed Work released by Licensor.
+
+You must conspicuously display this License on each original or modified copy
+of the Licensed Work. If you receive the Licensed Work in original or
+modified form from a third party, the terms and conditions set forth in this
+License apply to your use of that work.
+
+Any use of the Licensed Work in violation of this License will automatically
+terminate your rights under this License for the current and all other
+versions of the Licensed Work.
+
+This License does not grant you any right in any trademark or logo of
+Licensor or its affiliates (provided that you may use a trademark or logo of
+Licensor as expressly required by this License).
+
+TO THE EXTENT PERMITTED BY APPLICABLE LAW, THE LICENSED WORK IS PROVIDED ON
+AN "AS IS" BASIS. LICENSOR HEREBY DISCLAIMS ALL WARRANTIES AND CONDITIONS,
+EXPRESS OR IMPLIED, INCLUDING (WITHOUT LIMITATION) WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, NON-INFRINGEMENT, AND
+TITLE.

README.md

@@ -23,12 +23,6 @@
   <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>
 </p>
 
-<p align="center" name="ph-banner">
-  <a href="https://www.producthunt.com/posts/meilisearch-ai">
-    <img src="assets/ph-banner.png" alt="Meilisearch AI-powered search general availability announcement on ProductHunt">
-  </a>
-</p>
-
 <p align="center">⚡ A lightning-fast search engine that fits effortlessly into your apps, websites, and workflow 🔍</p>
 
 [Meilisearch](https://www.meilisearch.com?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=intro) helps you shape a delightful search experience in a snap, offering features that work out of the box to speed up your workflow.
@@ -47,7 +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).
 
@@ -95,6 +89,26 @@ We also offer a wide range of dedicated guides to all Meilisearch features, such
 
 Finally, for more in-depth information, refer to our articles explaining fundamental Meilisearch concepts such as [documents](https://www.meilisearch.com/docs/learn/core_concepts/documents?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced) and [indexes](https://www.meilisearch.com/docs/learn/core_concepts/indexes?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=advanced).
 
+## 🧾 Editions & Licensing
+
+Meilisearch is available in two editions:
+
+### 🧪 Community Edition (CE)
+
+- Fully open source under the [MIT license](./LICENSE)
+- Core search engine with fast and relevant full-text, semantic or hybrid search
+- Free to use for anyone, including commercial usage
+
+### 🏢 Enterprise Edition (EE)
+
+- Includes advanced features such as:
+  - Sharding
+- Governed by a [commercial license](./LICENSE-EE) or the [Business Source License 1.1](https://mariadb.com/bsl11)
+- Not allowed in production without a commercial agreement with Meilisearch.
+  - You may use, modify, and distribute the Licensed Work for non-production purposes only, such as testing, development, or evaluation.
+
+Want access to Enterprise features? → Contact us at [sales@meilisearch.com](maito:sales@meilisearch.com).
+
 ## 📊 Telemetry
 
 Meilisearch collects **anonymized** user data to help us improve our product. You can [deactivate this](https://www.meilisearch.com/docs/learn/what_is_meilisearch/telemetry?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=telemetry#how-to-disable-data-collection) whenever you want.
@@ -105,7 +119,7 @@ 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.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)
+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)
 
 🗞 [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

@@ -1501,6 +1501,300 @@
       "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": {

crates/benchmarks/Cargo.toml

@@ -11,27 +11,27 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.95"
-bumpalo = "3.16.0"
+anyhow = "1.0.98"
+bumpalo = "3.18.1"
 csv = "1.3.1"
-memmap2 = "0.9.5"
+memmap2 = "0.9.7"
 milli = { path = "../milli" }
-mimalloc = { version = "0.1.43", default-features = false }
-serde_json = { version = "1.0.135", features = ["preserve_order"] }
-tempfile = "3.15.0"
+mimalloc = { version = "0.1.47", default-features = false }
+serde_json = { version = "1.0.140", features = ["preserve_order"] }
+tempfile = "3.20.0"
 
 [dev-dependencies]
-criterion = { version = "0.5.1", features = ["html_reports"] }
+criterion = { version = "0.6.0", features = ["html_reports"] }
 rand = "0.8.5"
 rand_chacha = "0.3.1"
-roaring = "0.10.10"
+roaring = "0.10.12"
 
 [build-dependencies]
-anyhow = "1.0.95"
-bytes = "1.9.0"
-convert_case = "0.6.0"
-flate2 = "1.0.35"
-reqwest = { version = "0.12.12", features = ["blocking", "rustls-tls"], default-features = false }
+anyhow = "1.0.98"
+bytes = "1.10.1"
+convert_case = "0.8.0"
+flate2 = "1.1.2"
+reqwest = { version = "0.12.20", features = ["blocking", "rustls-tls"], default-features = false }
 
 [features]
 default = ["milli/all-tokenizations"]
@@ -51,3 +51,7 @@ harness = false
 [[bench]]
 name = "indexing"
 harness = false
+
+[[bench]]
+name = "sort"
+harness = false

crates/benchmarks/benches/indexing.rs

@@ -11,7 +11,7 @@ use milli::heed::{EnvOpenOptions, RwTxn};
 use milli::progress::Progress;
 use milli::update::new::indexer;
 use milli::update::{IndexerConfig, Settings};
-use milli::vector::EmbeddingConfigs;
+use milli::vector::RuntimeEmbedders;
 use milli::{FilterableAttributesRule, Index};
 use rand::seq::SliceRandom;
 use rand_chacha::rand_core::SeedableRng;
@@ -65,7 +65,7 @@ fn setup_settings<'t>(
     let sortable_fields = sortable_fields.iter().map(|s| s.to_string()).collect();
     builder.set_sortable_fields(sortable_fields);
 
-    builder.execute(|_| (), || false).unwrap();
+    builder.execute(&|| false, &Progress::default(), Default::default()).unwrap();
 }
 
 fn setup_index_with_settings(
@@ -154,6 +154,7 @@ fn indexing_songs_default(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -166,9 +167,10 @@ fn indexing_songs_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -220,6 +222,7 @@ fn reindexing_songs_default(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -232,9 +235,10 @@ fn reindexing_songs_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -264,6 +268,7 @@ fn reindexing_songs_default(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -276,9 +281,10 @@ fn reindexing_songs_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -332,6 +338,7 @@ fn deleting_songs_in_batches_default(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -344,9 +351,10 @@ fn deleting_songs_in_batches_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -408,6 +416,7 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -420,9 +429,10 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -452,6 +462,7 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -464,9 +475,10 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -492,6 +504,7 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -504,9 +517,10 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -559,6 +573,7 @@ fn indexing_songs_without_faceted_numbers(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -571,9 +586,10 @@ fn indexing_songs_without_faceted_numbers(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -625,6 +641,7 @@ fn indexing_songs_without_faceted_fields(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -637,9 +654,10 @@ fn indexing_songs_without_faceted_fields(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -691,6 +709,7 @@ fn indexing_wiki(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -703,9 +722,10 @@ fn indexing_wiki(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -756,6 +776,7 @@ fn reindexing_wiki(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -768,9 +789,10 @@ fn reindexing_wiki(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -800,6 +822,7 @@ fn reindexing_wiki(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -812,9 +835,10 @@ fn reindexing_wiki(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -867,6 +891,7 @@ fn deleting_wiki_in_batches_default(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -879,9 +904,10 @@ fn deleting_wiki_in_batches_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -943,6 +969,7 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -955,9 +982,10 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -988,6 +1016,7 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -1000,9 +1029,10 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1029,6 +1059,7 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -1041,9 +1072,10 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1095,6 +1127,7 @@ fn indexing_movies_default(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -1107,9 +1140,10 @@ fn indexing_movies_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1160,6 +1194,7 @@ fn reindexing_movies_default(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -1172,9 +1207,10 @@ fn reindexing_movies_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1204,6 +1240,7 @@ fn reindexing_movies_default(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -1216,9 +1253,10 @@ fn reindexing_movies_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1271,6 +1309,7 @@ fn deleting_movies_in_batches_default(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -1283,9 +1322,10 @@ fn deleting_movies_in_batches_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1331,9 +1371,10 @@ fn delete_documents_from_ids(index: Index, document_ids_to_delete: Vec<RoaringBi
             new_fields_ids_map,
             Some(primary_key),
             &document_changes,
-            EmbeddingConfigs::default(),
+            RuntimeEmbedders::default(),
             &|| false,
             &Progress::default(),
+            &Default::default(),
         )
         .unwrap();
 
@@ -1383,6 +1424,7 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -1395,9 +1437,10 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1427,6 +1470,7 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -1439,9 +1483,10 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1467,6 +1512,7 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -1479,9 +1525,10 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1556,6 +1603,7 @@ fn indexing_nested_movies_default(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -1568,9 +1616,10 @@ fn indexing_nested_movies_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1646,6 +1695,7 @@ fn deleting_nested_movies_in_batches_default(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -1658,9 +1708,10 @@ fn deleting_nested_movies_in_batches_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1728,6 +1779,7 @@ fn indexing_nested_movies_without_faceted_fields(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -1740,9 +1792,10 @@ fn indexing_nested_movies_without_faceted_fields(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1794,6 +1847,7 @@ fn indexing_geo(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -1806,9 +1860,10 @@ fn indexing_geo(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1859,6 +1914,7 @@ fn reindexing_geo(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -1871,9 +1927,10 @@ fn reindexing_geo(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1903,6 +1960,7 @@ fn reindexing_geo(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -1915,9 +1973,10 @@ fn reindexing_geo(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 
@@ -1970,6 +2029,7 @@ fn deleting_geo_in_batches_default(c: &mut Criterion) {
                         &mut new_fields_ids_map,
                         &|| false,
                         Progress::default(),
+                        None,
                     )
                     .unwrap();
 
@@ -1982,9 +2042,10 @@ fn deleting_geo_in_batches_default(c: &mut Criterion) {
                     new_fields_ids_map,
                     primary_key,
                     &document_changes,
-                    EmbeddingConfigs::default(),
+                    RuntimeEmbedders::default(),
                     &|| false,
                     &Progress::default(),
+                    &Default::default(),
                 )
                 .unwrap();
 

crates/benchmarks/benches/search_geo.rs

@@ -2,7 +2,8 @@ mod datasets_paths;
 mod utils;
 
 use criterion::{criterion_group, criterion_main};
-use milli::{update::Settings, FilterableAttributesRule};
+use milli::update::Settings;
+use milli::FilterableAttributesRule;
 use utils::Conf;
 
 #[cfg(not(windows))]

crates/benchmarks/benches/search_songs.rs

@@ -2,7 +2,8 @@ mod datasets_paths;
 mod utils;
 
 use criterion::{criterion_group, criterion_main};
-use milli::{update::Settings, FilterableAttributesRule};
+use milli::update::Settings;
+use milli::FilterableAttributesRule;
 use utils::Conf;
 
 #[cfg(not(windows))]

crates/benchmarks/benches/sort.rs

@@ -0,0 +1,114 @@
+//! 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

@@ -9,11 +9,12 @@ 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::vector::EmbeddingConfigs;
+use milli::vector::RuntimeEmbedders;
 use milli::{Criterion, Filter, Index, Object, TermsMatchingStrategy};
 use serde_json::Value;
 
@@ -35,6 +36,12 @@ 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
@@ -52,6 +59,9 @@ impl Conf<'_> {
         configure: |_| (),
         filter: None,
         sort: None,
+        offsets: &[None],
+        get_documents: false,
+        sample_size: None,
         optional_words: true,
         primary_key: None,
     };
@@ -90,7 +100,7 @@ pub fn base_setup(conf: &Conf) -> Index {
 
     (conf.configure)(&mut builder);
 
-    builder.execute(|_| (), || false).unwrap();
+    builder.execute(&|| false, &Progress::default(), Default::default()).unwrap();
     wtxn.commit().unwrap();
 
     let config = IndexerConfig::default();
@@ -113,6 +123,7 @@ pub fn base_setup(conf: &Conf) -> Index {
             &mut new_fields_ids_map,
             &|| false,
             Progress::default(),
+            None,
         )
         .unwrap();
 
@@ -125,9 +136,10 @@ pub fn base_setup(conf: &Conf) -> Index {
         new_fields_ids_map,
         primary_key,
         &document_changes,
-        EmbeddingConfigs::default(),
+        RuntimeEmbedders::default(),
         &|| false,
         &Progress::default(),
+        &Default::default(),
     )
     .unwrap();
 
@@ -144,25 +156,79 @@ 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 {
-            group.bench_with_input(BenchmarkId::from_parameter(query), &query, |b, &query| {
-                b.iter(|| {
-                    let rtxn = index.read_txn().unwrap();
-                    let mut search = index.search(&rtxn);
-                    search.query(query).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);
-                    }
-                    let _ids = search.execute().unwrap();
-                });
-            });
+            for offset in conf.offsets {
+                let parameter = match offset {
+                    None => query.to_string(),
+                    Some((offset, limit)) => format!("{query}[{offset}:{limit}]"),
+                };
+                group.bench_with_input(
+                    BenchmarkId::from_parameter(parameter),
+                    &query,
+                    |b, &query| {
+                        b.iter(|| {
+                            let rtxn = index.read_txn().unwrap();
+                            let mut search = index.search(&rtxn);
+                            search
+                                .query(query)
+                                .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::ScreamingSnake),
+            dataset.to_case(Case::UpperSnake),
             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 = "0.3.37", features = ["parsing"] }
+time = { version = "0.3.41", features = ["parsing"] }
 
 [build-dependencies]
-anyhow = "1.0.95"
-vergen-git2 = "1.0.2"
+anyhow = "1.0.98"
+vergen-git2 = "1.0.7"

crates/dump/Cargo.toml

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

crates/dump/src/lib.rs

@@ -1,12 +1,17 @@
 #![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::{Details, IndexSwap, KindWithContent, Status, Task, TaskId};
+use meilisearch_types::tasks::{
+    Details, ExportIndexSettings, IndexSwap, KindWithContent, Status, Task, TaskId, TaskNetwork,
+};
 use meilisearch_types::InstanceUid;
 use roaring::RoaringBitmap;
 use serde::{Deserialize, Serialize};
@@ -89,6 +94,8 @@ pub struct TaskDump {
         default
     )]
     pub finished_at: Option<OffsetDateTime>,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub network: Option<TaskNetwork>,
 }
 
 // A `Kind` specific version made for the dump. If modified you may break the dump.
@@ -141,6 +148,12 @@ 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),
     },
@@ -160,6 +173,7 @@ impl From<Task> for TaskDump {
             enqueued_at: task.enqueued_at,
             started_at: task.started_at,
             finished_at: task.finished_at,
+            network: task.network,
         }
     }
 }
@@ -213,6 +227,15 @@ 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 }
             }
@@ -230,14 +253,15 @@ pub(crate) mod test {
     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::update::Setting;
     use meilisearch_types::milli::{self, FilterableAttributesRule};
+    use meilisearch_types::network::{Network, Remote};
     use meilisearch_types::settings::{Checked, FacetingSettings, Settings};
     use meilisearch_types::task_view::DetailsView;
-    use meilisearch_types::tasks::{Details, Kind, Status};
+    use meilisearch_types::tasks::{BatchStopReason, Details, Kind, Status};
     use serde_json::{json, Map, Value};
     use time::macros::datetime;
     use uuid::Uuid;
@@ -305,6 +329,7 @@ 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()
@@ -326,13 +351,16 @@ pub(crate) mod test {
                 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(),
         }]
     }
 
@@ -359,6 +387,7 @@ pub(crate) mod test {
                     enqueued_at: datetime!(2022-11-11 0:00 UTC),
                     started_at: Some(datetime!(2022-11-20 0:00 UTC)),
                     finished_at: Some(datetime!(2022-11-21 0:00 UTC)),
+                    network: None,
                 },
                 None,
             ),
@@ -383,6 +412,7 @@ pub(crate) mod test {
                     enqueued_at: datetime!(2022-11-11 0:00 UTC),
                     started_at: None,
                     finished_at: None,
+                    network: None,
                 },
                 Some(vec![
                     json!({ "id": 4, "race": "leonberg" }).as_object().unwrap().clone(),
@@ -402,6 +432,7 @@ pub(crate) mod test {
                     enqueued_at: datetime!(2022-11-15 0:00 UTC),
                     started_at: None,
                     finished_at: None,
+                    network: None,
                 },
                 None,
             ),
@@ -514,7 +545,8 @@ pub(crate) mod test {
     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()) }},
+            remotes: maplit::btreemap! {"other".to_string() => Remote { url: "http://test".to_string(), search_api_key: Some("apiKey".to_string()), write_api_key: Some("docApiKey".to_string()) }},
+            sharding: false,
         }
     }
 

crates/dump/src/reader/compat/v1_to_v2.rs

@@ -1,3 +1,4 @@
+use std::fs::File;
 use std::str::FromStr;
 
 use super::v2_to_v3::CompatV2ToV3;
@@ -94,6 +95,10 @@ impl CompatIndexV1ToV2 {
         self.from.documents().map(|it| Box::new(it) as Box<dyn Iterator<Item = _>>)
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.from.documents_file()
+    }
+
     pub fn settings(&mut self) -> Result<v2::settings::Settings<v2::settings::Checked>> {
         Ok(v2::settings::Settings::<v2::settings::Unchecked>::from(self.from.settings()?).check())
     }

crates/dump/src/reader/compat/v2_to_v3.rs

@@ -1,3 +1,4 @@
+use std::fs::File;
 use std::str::FromStr;
 
 use time::OffsetDateTime;
@@ -122,6 +123,13 @@ impl CompatIndexV2ToV3 {
         }
     }
 
+    pub fn documents_file(&self) -> &File {
+        match self {
+            CompatIndexV2ToV3::V2(v2) => v2.documents_file(),
+            CompatIndexV2ToV3::Compat(compat) => compat.documents_file(),
+        }
+    }
+
     pub fn settings(&mut self) -> Result<v3::Settings<v3::Checked>> {
         let settings = match self {
             CompatIndexV2ToV3::V2(from) => from.settings()?,

crates/dump/src/reader/compat/v3_to_v4.rs

@@ -1,3 +1,5 @@
+use std::fs::File;
+
 use super::v2_to_v3::{CompatIndexV2ToV3, CompatV2ToV3};
 use super::v4_to_v5::CompatV4ToV5;
 use crate::reader::{v3, v4, UpdateFile};
@@ -252,6 +254,13 @@ impl CompatIndexV3ToV4 {
         }
     }
 
+    pub fn documents_file(&self) -> &File {
+        match self {
+            CompatIndexV3ToV4::V3(v3) => v3.documents_file(),
+            CompatIndexV3ToV4::Compat(compat) => compat.documents_file(),
+        }
+    }
+
     pub fn settings(&mut self) -> Result<v4::Settings<v4::Checked>> {
         Ok(match self {
             CompatIndexV3ToV4::V3(v3) => {

crates/dump/src/reader/compat/v4_to_v5.rs

@@ -1,3 +1,5 @@
+use std::fs::File;
+
 use super::v3_to_v4::{CompatIndexV3ToV4, CompatV3ToV4};
 use super::v5_to_v6::CompatV5ToV6;
 use crate::reader::{v4, v5, Document};
@@ -241,6 +243,13 @@ impl CompatIndexV4ToV5 {
         }
     }
 
+    pub fn documents_file(&self) -> &File {
+        match self {
+            CompatIndexV4ToV5::V4(v4) => v4.documents_file(),
+            CompatIndexV4ToV5::Compat(compat) => compat.documents_file(),
+        }
+    }
+
     pub fn settings(&mut self) -> Result<v5::Settings<v5::Checked>> {
         match self {
             CompatIndexV4ToV5::V4(v4) => Ok(v5::Settings::from(v4.settings()?).check()),

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

@@ -1,3 +1,5 @@
+use std::fs::File;
+use std::num::NonZeroUsize;
 use std::str::FromStr;
 
 use super::v4_to_v5::{CompatIndexV4ToV5, CompatV4ToV5};
@@ -159,6 +161,7 @@ impl CompatV5ToV6 {
                     enqueued_at: task_view.enqueued_at,
                     started_at: task_view.started_at,
                     finished_at: task_view.finished_at,
+                    network: None,
                 };
 
                 (task, content_file)
@@ -242,6 +245,13 @@ impl CompatIndexV5ToV6 {
         }
     }
 
+    pub fn documents_file(&self) -> &File {
+        match self {
+            CompatIndexV5ToV6::V5(v5) => v5.documents_file(),
+            CompatIndexV5ToV6::Compat(compat) => compat.documents_file(),
+        }
+    }
+
     pub fn settings(&mut self) -> Result<v6::Settings<v6::Checked>> {
         match self {
             CompatIndexV5ToV6::V5(v5) => Ok(v6::Settings::from(v5.settings()?).check()),
@@ -373,6 +383,7 @@ 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,
@@ -387,7 +398,13 @@ 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: pagination.max_total_hits.into(),
+                    max_total_hits: match pagination.max_total_hits {
+                        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,
@@ -397,6 +414,7 @@ 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

@@ -116,6 +116,15 @@ 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()),
@@ -183,6 +192,14 @@ impl DumpIndexReader {
         }
     }
 
+    /// A reference to a file in the NDJSON format containing all the documents of the index
+    pub fn documents_file(&self) -> &File {
+        match self {
+            DumpIndexReader::Current(v6) => v6.documents_file(),
+            DumpIndexReader::Compat(compat) => compat.documents_file(),
+        }
+    }
+
     pub fn settings(&mut self) -> Result<v6::Settings<v6::Checked>> {
         match self {
             DumpIndexReader::Current(v6) => v6.settings(),

crates/dump/src/reader/v1/mod.rs

@@ -72,6 +72,10 @@ impl V1IndexReader {
             .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }))
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.documents.get_ref()
+    }
+
     pub fn settings(&mut self) -> Result<self::settings::Settings> {
         Ok(serde_json::from_reader(&mut self.settings)?)
     }

crates/dump/src/reader/v2/mod.rs

@@ -203,6 +203,10 @@ impl V2IndexReader {
             .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }))
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.documents.get_ref()
+    }
+
     pub fn settings(&mut self) -> Result<Settings<Checked>> {
         Ok(self.settings.clone())
     }

crates/dump/src/reader/v3/mod.rs

@@ -215,6 +215,10 @@ impl V3IndexReader {
             .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }))
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.documents.get_ref()
+    }
+
     pub fn settings(&mut self) -> Result<Settings<Checked>> {
         Ok(self.settings.clone())
     }

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

@@ -210,6 +210,10 @@ impl V4IndexReader {
             .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }))
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.documents.get_ref()
+    }
+
     pub fn settings(&mut self) -> Result<Settings<Checked>> {
         Ok(self.settings.clone())
     }

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

@@ -247,6 +247,10 @@ impl V5IndexReader {
             .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }))
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.documents.get_ref()
+    }
+
     pub fn settings(&mut self) -> Result<Settings<Checked>> {
         Ok(self.settings.clone())
     }

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

@@ -1,3 +1,4 @@
+use std::ffi::OsStr;
 use std::fs::{self, File};
 use std::io::{BufRead, BufReader, ErrorKind};
 use std::path::Path;
@@ -21,8 +22,9 @@ 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;
+pub type Network = meilisearch_types::network::Network;
 
 // ===== Other types to clarify the code of the compat module
 // everything related to the tasks
@@ -192,6 +194,34 @@ impl V6Reader {
         )
     }
 
+    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
     }
@@ -254,6 +284,10 @@ impl V6IndexReader {
             .map(|line| -> Result<_> { Ok(serde_json::from_str(&line?)?) }))
     }
 
+    pub fn documents_file(&self) -> &File {
+        self.documents.get_ref()
+    }
+
     pub fn settings(&mut self) -> Result<Settings<Checked>> {
         let mut settings: Settings<Unchecked> = serde_json::from_reader(&mut self.settings)?;
         patch_embedders(&mut settings);

crates/dump/src/writer.rs

@@ -5,8 +5,9 @@ use std::path::PathBuf;
 use flate2::write::GzEncoder;
 use flate2::Compression;
 use meilisearch_types::batches::Batch;
-use meilisearch_types::features::{Network, RuntimeTogglableFeatures};
+use meilisearch_types::features::{ChatCompletionSettings, RuntimeTogglableFeatures};
 use meilisearch_types::keys::Key;
+use meilisearch_types::network::Network;
 use meilisearch_types::settings::{Checked, Settings};
 use serde_json::{Map, Value};
 use tempfile::TempDir;
@@ -51,6 +52,10 @@ 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"))
     }
@@ -104,6 +109,24 @@ 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,

crates/file-store/Cargo.toml

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

crates/file-store/src/lib.rs

@@ -148,11 +148,10 @@ impl File {
         Ok(Self { path: PathBuf::new(), file: None })
     }
 
-    pub fn persist(self) -> Result<()> {
-        if let Some(file) = self.file {
-            file.persist(&self.path)?;
-        }
-        Ok(())
+    pub fn persist(self) -> Result<Option<StdFile>> {
+        let Some(file) = self.file else { return Ok(None) };
+
+        Ok(Some(file.persist(&self.path)?))
     }
 }
 

crates/filter-parser/Cargo.toml

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

crates/flatten-serde-json/Cargo.toml

@@ -16,7 +16,7 @@ license.workspace = true
 serde_json = "1.0"
 
 [dev-dependencies]
-criterion = { version = "0.5.1", features = ["html_reports"] }
+criterion = { version = "0.6.0", 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 = "3.16.0"
-clap = { version = "4.5.24", features = ["derive"] }
-either = "1.13.0"
+bumpalo = "3.18.1"
+clap = { version = "4.5.40", features = ["derive"] }
+either = "1.15.0"
 fastrand = "2.3.0"
 milli = { path = "../milli" }
-serde = { version = "1.0.217", features = ["derive"] }
-serde_json = { version = "1.0.135", features = ["preserve_order"] }
-tempfile = "3.15.0"
+serde = { version = "1.0.219", features = ["derive"] }
+serde_json = { version = "1.0.140", features = ["preserve_order"] }
+tempfile = "3.20.0"

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

@@ -13,7 +13,7 @@ use milli::heed::EnvOpenOptions;
 use milli::progress::Progress;
 use milli::update::new::indexer;
 use milli::update::IndexerConfig;
-use milli::vector::EmbeddingConfigs;
+use milli::vector::RuntimeEmbedders;
 use milli::Index;
 use serde_json::Value;
 use tempfile::TempDir;
@@ -89,7 +89,7 @@ fn main() {
                             let mut new_fields_ids_map = db_fields_ids_map.clone();
 
                             let indexer_alloc = Bump::new();
-                            let embedders = EmbeddingConfigs::default();
+                            let embedders = RuntimeEmbedders::default();
                             let mut indexer = indexer::DocumentOperation::new();
 
                             let mut operations = Vec::new();
@@ -129,6 +129,7 @@ fn main() {
                                     &mut new_fields_ids_map,
                                     &|| false,
                                     Progress::default(),
+                                    None,
                                 )
                                 .unwrap();
 
@@ -144,6 +145,7 @@ fn main() {
                                 embedders,
                                 &|| false,
                                 &Progress::default(),
+                                &Default::default(),
                             )
                             .unwrap();
 

crates/index-scheduler/Cargo.toml

@@ -11,29 +11,31 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-anyhow = "1.0.95"
+anyhow = "1.0.98"
 bincode = "1.3.3"
-bumpalo = "3.16.0"
+byte-unit = "5.1.6"
+bumpalo = "3.18.1"
 bumparaw-collections = "0.1.4"
-convert_case = "0.6.0"
+convert_case = "0.8.0"
 csv = "1.3.1"
 derive_builder = "0.20.2"
 dump = { path = "../dump" }
 enum-iterator = "2.1.0"
 file-store = { path = "../file-store" }
-flate2 = "1.0.35"
+flate2 = "1.1.2"
+indexmap = "2.9.0"
 meilisearch-auth = { path = "../meilisearch-auth" }
 meilisearch-types = { path = "../meilisearch-types" }
-memmap2 = "0.9.5"
+memmap2 = "0.9.7"
 page_size = "0.6.0"
 rayon = "1.10.0"
-roaring = { version = "0.10.10", features = ["serde"] }
-serde = { version = "1.0.217", features = ["derive"] }
-serde_json = { version = "1.0.138", features = ["preserve_order"] }
+roaring = { version = "0.10.12", features = ["serde"] }
+serde = { version = "1.0.219", features = ["derive"] }
+serde_json = { version = "1.0.140", features = ["preserve_order"] }
 synchronoise = "1.0.1"
-tempfile = "3.15.0"
-thiserror = "2.0.9"
-time = { version = "0.3.37", features = [
+tempfile = "3.20.0"
+thiserror = "2.0.12"
+time = { version = "0.3.41", features = [
     "serde-well-known",
     "formatting",
     "parsing",
@@ -41,11 +43,12 @@ time = { version = "0.3.37", features = [
 ] }
 tracing = "0.1.41"
 ureq = "2.12.1"
-uuid = { version = "1.11.0", features = ["serde", "v4"] }
+uuid = { version = "1.17.0", features = ["serde", "v4"] }
+backoff = "0.4.0"
 
 [dev-dependencies]
 big_s = "1.0.2"
-crossbeam-channel = "0.5.14"
+crossbeam-channel = "0.5.15"
 # 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

@@ -4,6 +4,7 @@ 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;
 use meilisearch_types::tasks::{Kind, KindWithContent, Status, Task};
 use roaring::RoaringBitmap;
@@ -146,6 +147,7 @@ impl<'a> Dump<'a> {
             canceled_by: task.canceled_by,
             details: task.details,
             status: task.status,
+            network: task.network,
             kind: match task.kind {
                 KindDump::DocumentImport {
                     primary_key,
@@ -211,6 +213,23 @@ 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 },
             },
         };

crates/index-scheduler/src/error.rs

@@ -2,6 +2,7 @@ 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;
@@ -151,7 +152,27 @@ pub enum Error {
     #[error(transparent)]
     DatabaseUpgrade(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),
 
@@ -195,6 +216,7 @@ impl Error {
             | Error::BatchNotFound(_)
             | Error::TaskDeletionWithEmptyQuery
             | Error::TaskCancelationWithEmptyQuery
+            | Error::FromRemoteWhenExporting { .. }
             | Error::AbortedTask
             | Error::Dump(_)
             | Error::Heed(_)
@@ -204,11 +226,15 @@ impl Error {
             | Error::IoError(_)
             | Error::Persist(_)
             | Error::FeatureNotEnabled(_)
+            | Error::Export(_)
             | Error::Anyhow(_) => true,
             Error::CreateBatch(_)
             | Error::CorruptedTaskQueue
             | Error::DatabaseUpgrade(_)
             | Error::UnrecoverableError(_)
+            | Error::IndexSchedulerVersionMismatch { .. }
+            | Error::IndexVersionMismatch { .. }
+            | Error::RollbackFailed { .. }
             | Error::HeedTransaction(_) => false,
             #[cfg(test)]
             Error::PlannedFailure => false,
@@ -262,6 +288,7 @@ impl ErrorCode for Error {
             Error::Dump(e) => e.error_code(),
             Error::Milli { error, .. } => error.error_code(),
             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(),
@@ -274,7 +301,11 @@ impl ErrorCode for Error {
             Error::CorruptedTaskQueue => Code::Internal,
             Error::CorruptedDump => Code::Internal,
             Error::DatabaseUpgrade(_) => 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

@@ -1,8 +1,9 @@
 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::network::Network;
 
 use crate::error::FeatureNotEnabledError;
 use crate::Result;
@@ -131,6 +132,32 @@ impl RoFeatures {
             .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 {

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

@@ -7,6 +7,7 @@ use meilisearch_types::heed::types::{SerdeJson, Str};
 use meilisearch_types::heed::{Database, Env, RoTxn, RwTxn, WithoutTls};
 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};
@@ -431,6 +432,51 @@ 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

@@ -20,6 +20,7 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
 
     let IndexScheduler {
         cleanup_enabled: _,
+        experimental_no_edition_2024_for_dumps: _,
         processing_tasks,
         env,
         version,
@@ -34,6 +35,7 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
         planned_failures: _,
         run_loop_iteration: _,
         embedders: _,
+        chat_settings: _,
     } = scheduler;
 
     let rtxn = env.read_txn().unwrap();
@@ -41,11 +43,8 @@ pub fn snapshot_index_scheduler(scheduler: &IndexScheduler) -> String {
     let mut snap = String::new();
 
     let indx_sched_version = version.get_version(&rtxn).unwrap();
-    let latest_version = (
-        versioning::VERSION_MAJOR.parse().unwrap(),
-        versioning::VERSION_MINOR.parse().unwrap(),
-        versioning::VERSION_PATCH.parse().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"));
     }
@@ -214,6 +213,7 @@ pub fn snapshot_task(task: &Task) -> String {
         details,
         status,
         kind,
+        network,
     } = task;
     snap.push('{');
     snap.push_str(&format!("uid: {uid}, "));
@@ -231,6 +231,9 @@ pub fn snapshot_task(task: &Task) -> String {
         snap.push_str(&format!("details: {}, ", &snapshot_details(details)));
     }
     snap.push_str(&format!("kind: {kind:?}"));
+    if let Some(network) = network {
+        snap.push_str(&format!("network: {network:?}, "))
+    }
 
     snap.push('}');
     snap
@@ -291,6 +294,9 @@ 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:?} }}")
         }
@@ -341,9 +347,20 @@ 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 { uid, details, stats, started_at, finished_at, progress: _, enqueued_at } = batch;
+    let 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()
     };
@@ -358,6 +375,13 @@ pub fn snapshot_batch(batch: &Batch) -> String {
     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()));
+    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
 }

crates/index-scheduler/src/lib.rs

@@ -51,16 +51,22 @@ pub use features::RoFeatures;
 use flate2::bufread::GzEncoder;
 use flate2::Compression;
 use meilisearch_types::batches::Batch;
-use meilisearch_types::features::{InstanceTogglableFeatures, Network, RuntimeTogglableFeatures};
+use meilisearch_types::features::{
+    ChatCompletionSettings, InstanceTogglableFeatures, RuntimeTogglableFeatures,
+};
 use meilisearch_types::heed::byteorder::BE;
-use meilisearch_types::heed::types::I128;
-use meilisearch_types::heed::{self, Env, RoTxn, WithoutTls};
-use meilisearch_types::milli::index::IndexEmbeddingConfig;
+use meilisearch_types::heed::types::{DecodeIgnore, SerdeJson, Str, I128};
+use meilisearch_types::heed::{self, Database, Env, RoTxn, WithoutTls};
 use meilisearch_types::milli::update::IndexerConfig;
-use meilisearch_types::milli::vector::{Embedder, EmbedderOptions, EmbeddingConfigs};
+use meilisearch_types::milli::vector::json_template::JsonTemplate;
+use meilisearch_types::milli::vector::{
+    Embedder, EmbedderOptions, RuntimeEmbedder, RuntimeEmbedders, RuntimeFragment,
+};
 use meilisearch_types::milli::{self, Index};
+use meilisearch_types::network::Network;
 use meilisearch_types::task_view::TaskView;
-use meilisearch_types::tasks::{KindWithContent, Task};
+use meilisearch_types::tasks::{KindWithContent, Task, TaskNetwork};
+use milli::vector::db::IndexEmbeddingConfig;
 use processing::ProcessingTasks;
 pub use queue::Query;
 use queue::Queue;
@@ -74,6 +80,9 @@ 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.
@@ -129,6 +138,8 @@ pub struct IndexSchedulerOptions {
     ///
     /// 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
@@ -149,12 +160,18 @@ pub struct IndexScheduler {
     /// 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,
 
+    /// Whether we should use the old document indexer or the new one.
+    pub(crate) experimental_no_edition_2024_for_dumps: bool,
+
     /// The webhook url we should send tasks to after processing every batches.
     pub(crate) webhook_url: Option<String>,
     /// The Authorization header to send to the webhook URL.
@@ -197,6 +214,7 @@ impl IndexScheduler {
 
             index_mapper: self.index_mapper.clone(),
             cleanup_enabled: self.cleanup_enabled,
+            experimental_no_edition_2024_for_dumps: self.experimental_no_edition_2024_for_dumps,
             webhook_url: self.webhook_url.clone(),
             webhook_authorization_header: self.webhook_authorization_header.clone(),
             embedders: self.embedders.clone(),
@@ -207,11 +225,16 @@ 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()
+        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.
@@ -265,6 +288,7 @@ impl IndexScheduler {
         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.
@@ -277,6 +301,9 @@ impl IndexScheduler {
             index_mapper,
             env,
             cleanup_enabled: options.cleanup_enabled,
+            experimental_no_edition_2024_for_dumps: options
+                .indexer_config
+                .experimental_no_edition_2024_for_dumps,
             webhook_url: options.webhook_url,
             webhook_authorization_header: options.webhook_authorization_header,
             embedders: Default::default(),
@@ -288,12 +315,17 @@ 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()?;
@@ -370,15 +402,16 @@ impl IndexScheduler {
         }
     }
 
-    pub fn read_txn(&self) -> Result<RoTxn<WithoutTls>> {
-        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"))
@@ -396,9 +429,9 @@ impl IndexScheduler {
                         Ok(Ok(TickOutcome::StopProcessingForever)) => break,
                         Ok(Err(e)) => {
                             tracing::error!("{e}");
-                            // Wait one second when an irrecoverable error occurs.
+                            // Wait when an irrecoverable error occurs.
                             if !e.is_recoverable() {
-                                std::thread::sleep(Duration::from_secs(1));
+                                std::thread::sleep(Duration::from_secs(10));
                             }
                         }
                         Err(_panic) => {
@@ -425,6 +458,17 @@ 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.
@@ -475,7 +519,7 @@ impl IndexScheduler {
 
     /// Returns the total number of indexes available for the specified filter.
     /// And a `Vec` of the index_uid + its stats
-    pub fn get_paginated_indexes_stats(
+    pub fn paginated_indexes_stats(
         &self,
         filters: &meilisearch_auth::AuthFilter,
         from: usize,
@@ -516,6 +560,24 @@ 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.
@@ -540,6 +602,11 @@ impl IndexScheduler {
         Ok(nbr_index_processing_tasks > 0)
     }
 
+    /// Whether the index should use the old document indexer.
+    pub fn no_edition_2024_for_dumps(&self) -> bool {
+        self.experimental_no_edition_2024_for_dumps
+    }
+
     /// Return the tasks matching the query from the user's point of view along
     /// with the total number of tasks matching the query, ignoring from and limit.
     ///
@@ -578,6 +645,16 @@ impl IndexScheduler {
         self.queue.get_task_ids_from_authorized_indexes(&rtxn, query, filters, &processing)
     }
 
+    pub fn set_task_network(&self, task_id: TaskId, network: TaskNetwork) -> Result<()> {
+        let mut wtxn = self.env.write_txn()?;
+        let mut task =
+            self.queue.tasks.get_task(&wtxn, task_id)?.ok_or(Error::TaskNotFound(task_id))?;
+        task.network = Some(network);
+        self.queue.tasks.all_tasks.put(&mut wtxn, &task_id, &task)?;
+        wtxn.commit()?;
+        Ok(())
+    }
+
     /// Return the batches matching the query from the user's point of view along
     /// with the total number of batches matching the query, ignoring from and limit.
     ///
@@ -625,9 +702,10 @@ impl IndexScheduler {
         task_id: Option<TaskId>,
         dry_run: bool,
     ) -> Result<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, .. } if !tasks.is_empty())
-            && (self.env.non_free_pages_size()? * 100) / self.env.info().map_size as u64 > 40
+        // 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 !matches!(&kind, KindWithContent::TaskDeletion { tasks, .. } | KindWithContent::TaskCancelation { tasks, .. } if !tasks.is_empty())
+            && (self.env.non_free_pages_size()? * 100) / self.env.info().map_size as u64
+                > TASK_SCHEDULER_SIZE_THRESHOLD_PERCENT_INT
         {
             return Err(Error::NoSpaceLeftInTaskQueue);
         }
@@ -799,29 +877,42 @@ impl IndexScheduler {
         &self,
         index_uid: String,
         embedding_configs: Vec<IndexEmbeddingConfig>,
-    ) -> Result<EmbeddingConfigs> {
+    ) -> Result<RuntimeEmbedders> {
         let res: Result<_> = embedding_configs
             .into_iter()
             .map(
                 |IndexEmbeddingConfig {
                      name,
                      config: milli::vector::EmbeddingConfig { embedder_options, prompt, quantized },
-                     ..
-                 }| {
-                    let prompt = Arc::new(
-                        prompt
-                            .try_into()
-                            .map_err(meilisearch_types::milli::Error::from)
-                            .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?,
-                    );
+                     fragments,
+                 }|
+                 -> Result<(String, Arc<RuntimeEmbedder>)> {
+                    let document_template = prompt
+                        .try_into()
+                        .map_err(meilisearch_types::milli::Error::from)
+                        .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) {
-                            return Ok((
-                                name,
-                                (embedder.clone(), prompt, quantized.unwrap_or_default()),
+                            let runtime = Arc::new(RuntimeEmbedder::new(
+                                embedder.clone(),
+                                document_template,
+                                fragments,
+                                quantized.unwrap_or_default(),
                             ));
+
+                            return Ok((name, runtime));
                         }
                     }
 
@@ -837,11 +928,44 @@ 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(EmbeddingConfigs::new)
+        res.map(RuntimeEmbedders::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)
     }
 }
 

crates/index-scheduler/src/processing.rs

@@ -64,9 +64,17 @@ make_enum_progress! {
     }
 }
 
+make_enum_progress! {
+    pub enum FinalizingIndexStep {
+        Committing,
+        ComputingStats,
+    }
+}
+
 make_enum_progress! {
     pub enum TaskCancelationProgress {
         RetrievingTasks,
+        CancelingUpgrade,
         UpdatingTasks,
     }
 }
@@ -95,6 +103,7 @@ make_enum_progress! {
     pub enum DumpCreationProgress {
         StartTheDumpCreation,
         DumpTheApiKeys,
+        DumpTheChatCompletionSettings,
         DumpTheTasks,
         DumpTheBatches,
         DumpTheIndexes,
@@ -167,8 +176,17 @@ make_enum_progress! {
     }
 }
 
+make_enum_progress! {
+    pub enum Export {
+        EnsuringCorrectnessOfTheTarget,
+        ExportingTheSettings,
+        ExportingTheDocuments,
+    }
+}
+
 make_atomic_progress!(Task alias AtomicTaskStep => "task" );
 make_atomic_progress!(Document alias AtomicDocumentStep => "document" );
+make_atomic_progress!(Index alias AtomicIndexStep => "index" );
 make_atomic_progress!(Batch alias AtomicBatchStep => "batch" );
 make_atomic_progress!(UpdateFile alias AtomicUpdateFileStep => "update file" );
 

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

@@ -179,9 +179,11 @@ 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(),
             },
         )?;
 

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

@@ -106,7 +106,7 @@ fn query_batches_simple() {
     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,
       "details": {
@@ -126,9 +126,10 @@ fn query_batches_simple() {
       },
       "startedAt": "1970-01-01T00:00:00Z",
       "finishedAt": null,
-      "enqueuedAt": 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

@@ -279,6 +279,7 @@ impl Queue {
             details: kind.default_details(),
             status: Status::Enqueued,
             kind: kind.clone(),
+            network: None,
         };
         // For deletion and cancelation tasks, we want to make extra sure that they
         // don't attempt to delete/cancel tasks that are newer than themselves.
@@ -292,8 +293,6 @@ 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

@@ -1,6 +1,5 @@
 ---
 source: crates/index-scheduler/src/queue/batches_test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -49,8 +48,8 @@ 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}}, }
-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}}, }
+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.", }
+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.", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

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

@@ -1,6 +1,5 @@
 ---
 source: crates/index-scheduler/src/queue/batches_test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -48,9 +47,9 @@ 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}}, }
-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}}, }
+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.", }
+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.", }
+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.", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

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

@@ -1,11 +1,10 @@
 ---
 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}}, }
+{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.", }
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, batch_uid: 0, status: succeeded, details: { primary_key: Some("mouse") }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
@@ -43,7 +42,7 @@ 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}}, }
+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.", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

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

@@ -1,6 +1,5 @@
 ---
 source: crates/index-scheduler/src/queue/batches_test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -48,9 +47,9 @@ 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}}, }
-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}}, }
+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.", }
+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.", }
+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.", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

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

@@ -1,6 +1,5 @@
 ---
 source: crates/index-scheduler/src/queue/batches_test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -53,10 +52,10 @@ 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}}, }
-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":{}}, }
-3 {uid: 3, details: {"swaps":[{"indexes":["catto","whalo"]}]}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"indexSwap":1},"indexUids":{}}, }
+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.", }
+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.", }
+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.", }
+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.", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

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

@@ -1,6 +1,5 @@
 ---
 source: crates/index-scheduler/src/queue/tasks_test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -49,8 +48,8 @@ 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}}, }
-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}}, }
+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.", }
+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.", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

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

@@ -1,6 +1,5 @@
 ---
 source: crates/index-scheduler/src/queue/tasks_test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -48,9 +47,9 @@ 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}}, }
-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}}, }
+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.", }
+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.", }
+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.", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

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

@@ -1,6 +1,5 @@
 ---
 source: crates/index-scheduler/src/queue/tasks_test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -48,9 +47,9 @@ 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}}, }
-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}}, }
+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.", }
+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.", }
+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.", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

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

@@ -97,7 +97,22 @@ impl TaskQueue {
         Ok(self.all_tasks.get(rtxn, &task_id)?)
     }
 
-    pub(crate) fn update_task(&self, wtxn: &mut RwTxn, task: &Task) -> Result<()> {
+    /// Update the inverted task indexes and write the new value of the task.
+    ///
+    /// The passed `task` object typically comes from a previous transaction, so two kinds of modification might have occurred:
+    /// 1. Modification to the `task` object after loading it from the DB (the purpose of this method is to persist these changes)
+    /// 2. Modification to the task committed by another transaction in the DB (an annoying consequence of having lost the original
+    ///    transaction from which the `task` instance was deserialized)
+    ///
+    /// When calling this function, this `task` is modified to take into account any existing `network`
+    /// that can have been added since the task was loaded into memory.
+    ///
+    /// Any other modification to the task that was committed from the DB since the parameter was pulled from the DB will be overwritten.
+    ///
+    /// # Errors
+    ///
+    /// - CorruptedTaskQueue: The task doesn't exist in the database
+    pub(crate) fn update_task(&self, wtxn: &mut RwTxn, task: &mut Task) -> Result<()> {
         let old_task = self.get_task(wtxn, task.uid)?.ok_or(Error::CorruptedTaskQueue)?;
         let reprocessing = old_task.status != Status::Enqueued;
 
@@ -157,6 +172,12 @@ impl TaskQueue {
             }
         }
 
+        task.network = match (old_task.network, task.network.take()) {
+            (None, None) => None,
+            (None, Some(network)) | (Some(network), None) => Some(network),
+            (Some(_), Some(network)) => Some(network),
+        };
+
         self.all_tasks.put(wtxn, &task.uid, task)?;
         Ok(())
     }

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

@@ -364,7 +364,7 @@ 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 that doesn't delete anything shouldn't be accepted
+    // Even the task deletion and cancelation that don't delete anything should be refused
     let result = index_scheduler
         .register(
             KindWithContent::TaskDeletion { query: S("test"), tasks: RoaringBitmap::new() },
@@ -373,10 +373,39 @@ 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 deletion that delete something should works
+    // But a task cancelation that cancel something should work
+    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

@@ -5,9 +5,10 @@ tasks affecting a single index into a [batch](crate::batch::Batch).
 The main function of the autobatcher is [`next_autobatch`].
 */
 
-use meilisearch_types::tasks::TaskId;
 use std::ops::ControlFlow::{self, Break, Continue};
 
+use meilisearch_types::tasks::{BatchStopReason, PrimaryKeyMismatchReason, TaskId};
+
 use crate::KindWithContent;
 
 /// Succinctly describes a task's [`Kind`](meilisearch_types::tasks::Kind)
@@ -70,6 +71,7 @@ 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.")
@@ -145,16 +147,42 @@ impl BatchKind {
     // TODO use an AutoBatchKind as input
     pub fn new(
         task_id: TaskId,
-        kind: KindWithContent,
+        kind_with_content: KindWithContent,
         primary_key: Option<&str>,
-    ) -> (ControlFlow<BatchKind, BatchKind>, bool) {
+    ) -> (ControlFlow<(BatchKind, BatchStopReason), BatchKind>, bool) {
         use AutobatchKind as K;
 
-        match AutobatchKind::from(kind) {
-            K::IndexCreation => (Break(BatchKind::IndexCreation { id: task_id }), true),
-            K::IndexDeletion => (Break(BatchKind::IndexDeletion { ids: vec![task_id] }), false),
-            K::IndexUpdate => (Break(BatchKind::IndexUpdate { id: task_id }), false),
-            K::IndexSwap => (Break(BatchKind::IndexSwap { id: task_id }), false),
+        let kind = kind_with_content.as_kind();
+
+        match AutobatchKind::from(kind_with_content) {
+            K::IndexCreation => (
+                Break((
+                    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 }
                 if primary_key.is_none() || pk.is_none() || primary_key == pk.as_deref() =>
@@ -169,15 +197,28 @@ 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 } => (
-                Break(BatchKind::DocumentOperation {
-                    allow_index_creation,
-                    primary_key,
-                    operation_ids: vec![task_id],
-                }),
+            K::DocumentImport { allow_index_creation, primary_key: pk } => (
+                Break((
+                    BatchKind::DocumentOperation {
+                        allow_index_creation,
+                        primary_key: pk.clone(),
+                        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 => (Break(BatchKind::DocumentEdition { id: task_id }), false),
+            K::DocumentEdition => (
+                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],
@@ -197,43 +238,60 @@ 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: AutobatchKind, index_already_exists: bool, primary_key: Option<&str>) -> ControlFlow<BatchKind, BatchKind> {
+    fn accumulate(self, id: TaskId, kind_with_content: KindWithContent, index_already_exists: bool, primary_key: Option<&str>) -> ControlFlow<(BatchKind, BatchStopReason), BatchKind> {
         use AutobatchKind as K;
 
-        match (self, kind) {
+        let kind = kind_with_content.as_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),
+            (this, K::IndexCreation | K::IndexUpdate | K::IndexSwap | K::DocumentEdition) => Break((this, BatchStopReason::TaskCannotBeBatched { kind, id })),
             // 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)
-            },
-            // 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().is_none_or(|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)
+                Break((this, BatchStopReason::IndexCreationMismatch { id }))
             },
             // The index deletion can batch with everything but must stop after
             (
@@ -244,7 +302,7 @@ impl BatchKind {
                 K::IndexDeletion,
             ) => {
                 ids.push(id);
-                Break(BatchKind::IndexDeletion { ids })
+                Break((BatchKind::IndexDeletion { ids }, BatchStopReason::IndexDeletion { id }))
             }
             (
                 BatchKind::ClearAndSettings { settings_ids: mut ids, allow_index_creation: _, mut other },
@@ -252,7 +310,7 @@ impl BatchKind {
             ) => {
                 ids.push(id);
                 ids.append(&mut other);
-                Break(BatchKind::IndexDeletion { ids })
+                Break((BatchKind::IndexDeletion { ids }, BatchStopReason::IndexDeletion { id }))
             }
 
             (
@@ -265,7 +323,7 @@ impl BatchKind {
             (
                 this @ BatchKind::DocumentClear { .. },
                 K::DocumentImport { .. } | K::Settings { .. },
-            ) => Break(this),
+            ) => Break((this, BatchStopReason::DocumentOperationWithSettings { id })),
             (
                 BatchKind::DocumentOperation { allow_index_creation: _, primary_key: _, mut operation_ids },
                 K::DocumentClear,
@@ -277,7 +335,7 @@ impl BatchKind {
             // we can autobatch different kind of document operations and mix replacements with updates
             (
                 BatchKind::DocumentOperation { allow_index_creation, primary_key: _, mut operation_ids },
-                K::DocumentImport { primary_key: pk, .. },
+                K::DocumentImport { primary_key: _, .. },
             ) => {
                 operation_ids.push(id);
                 Continue(BatchKind::DocumentOperation {
@@ -287,15 +345,15 @@ impl BatchKind {
                 })
             }
             (
-                BatchKind::DocumentOperation { allow_index_creation, primary_key, mut operation_ids },
+                BatchKind::DocumentOperation { allow_index_creation, primary_key: _, mut operation_ids },
                 K::DocumentDeletion { by_filter: false },
             ) => {
                 operation_ids.push(id);
 
                 Continue(BatchKind::DocumentOperation {
                     allow_index_creation,
-                    primary_key,
                     operation_ids,
+                    primary_key: pk,
                 })
             }
             // We can't batch a document operation with a delete by filter
@@ -303,12 +361,12 @@ impl BatchKind {
                 this @ BatchKind::DocumentOperation { .. },
                 K::DocumentDeletion { by_filter: true },
             ) => {
-                Break(this)
+                Break((this, BatchStopReason::DocumentOperationWithDeletionByFilter { id }))
             }
             (
                 this @ BatchKind::DocumentOperation { .. },
                 K::Settings { .. },
-            ) => Break(this),
+            ) => Break((this, BatchStopReason::DocumentOperationWithSettings { id })),
 
             (BatchKind::DocumentDeletion { mut deletion_ids, includes_by_filter: _ }, K::DocumentClear) => {
                 deletion_ids.push(id);
@@ -318,7 +376,7 @@ impl BatchKind {
             (
                 this @ BatchKind::DocumentDeletion { deletion_ids: _, includes_by_filter: true },
                 K::DocumentImport { .. }
-            ) => Break(this),
+            ) => Break((this, BatchStopReason::DeletionByFilterWithDocumentOperation { id })),
             // we can autobatch the deletion and import if the index already exists
             (
                 BatchKind::DocumentDeletion { mut deletion_ids, includes_by_filter: false },
@@ -345,18 +403,18 @@ impl BatchKind {
                     operation_ids: deletion_ids,
                 })
             }
-            // we can't autobatch a deletion and an import if the index does not exists but would be created by an addition
+            // we can't autobatch a deletion and an import if the index does not exist but would be created by an addition
             (
                 this @ BatchKind::DocumentDeletion { .. },
                 K::DocumentImport { .. }
             ) => {
-                Break(this)
+                Break((this, BatchStopReason::IndexCreationMismatch { id }))
             }
             (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),
+            (this @ BatchKind::DocumentDeletion { .. }, K::Settings { .. }) => Break((this, BatchStopReason::DocumentOperationWithSettings { id })),
 
             (
                 BatchKind::Settings { settings_ids, allow_index_creation },
@@ -369,7 +427,7 @@ impl BatchKind {
             (
                 this @ BatchKind::Settings { .. },
                 K::DocumentImport { .. } | K::DocumentDeletion { .. },
-            ) => Break(this),
+            ) => Break((this, BatchStopReason::SettingsWithDocumentOperation { id })),
             (
                 BatchKind::Settings { mut settings_ids, allow_index_creation },
                 K::Settings { .. },
@@ -392,7 +450,7 @@ impl BatchKind {
                     allow_index_creation,
                 })
             }
-            (this @ BatchKind::ClearAndSettings { .. }, K::DocumentImport { .. }) => Break(this),
+            (this @ BatchKind::ClearAndSettings { .. }, K::DocumentImport { .. }) => Break((this, BatchStopReason::SettingsWithDocumentOperation { id })),
             (
                 BatchKind::ClearAndSettings {
                     mut other,
@@ -448,7 +506,7 @@ pub fn autobatch(
     enqueued: Vec<(TaskId, KindWithContent)>,
     index_already_exists: bool,
     primary_key: Option<&str>,
-) -> Option<(BatchKind, bool)> {
+) -> Option<(BatchKind, bool, Option<BatchStopReason>)> {
     let mut enqueued = enqueued.into_iter();
     let (id, kind) = enqueued.next()?;
 
@@ -457,18 +515,22 @@ pub fn autobatch(
 
     let (mut acc, must_create_index) = match BatchKind::new(id, kind, primary_key) {
         (Continue(acc), create) => (acc, create),
-        (Break(acc), create) => return Some((acc, create)),
+        (Break((acc, batch_stop_reason)), 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) in enqueued {
-        acc = match acc.accumulate(id, kind.into(), index_exist, primary_key) {
+    for (id, kind_with_content) in enqueued {
+        acc = match acc.accumulate(id, kind_with_content, index_exist, primary_key) {
             Continue(acc) => acc,
-            Break(acc) => return Some((acc, must_create_index)),
+            Break((acc, batch_stop_reason)) => {
+                return Some((acc, must_create_index, Some(batch_stop_reason)))
+            }
         };
     }
 
-    Some((acc, must_create_index))
+    Some((acc, must_create_index, None))
 }

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::{IndexSwap, KindWithContent};
+use meilisearch_types::tasks::{BatchStopReason, 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<(BatchKind, bool, Option<BatchStopReason>)> {
     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))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { 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))");
-    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))");
+    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, 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, 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, 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))");
 
     // 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))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_imp(ReplaceDocuments, false, None)]), @"Some((DocumentOperation { 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))");
-    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))");
+    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, 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, 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, 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 })))");
 
     // 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))");
-    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))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { 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))");
+    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), 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, 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), 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))");
 
     // 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))");
-    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))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_imp(UpdateDocuments, false, None)]), @"Some((DocumentOperation { 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))");
+    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), 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, 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), 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))");
 
     // 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))");
-    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))");
-    debug_snapshot!(autobatch_from(false,None,  [doc_del(), doc_del(), doc_del()]), @"Some((DocumentDeletion { deletion_ids: [0, 1, 2], includes_by_filter: false }, false))");
+    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(), 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()]), @"Some((DocumentDeletion { deletion_ids: [0], 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, None))");
 
     // 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))");
-    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))");
-    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))");
+    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(), 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()]), @"Some((DocumentDeletion { deletion_ids: [0], 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, None))");
 
     // 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))");
-    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))");
-    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(true, None, [settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0] }, 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, None))");
+    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), settings(false), settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0, 1, 2] }, false, 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))");
-    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))");
+    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), settings(true), settings(true)]), @"Some((Settings { allow_index_creation: true, settings_ids: [0, 1, 2] }, true, None))");
+    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), settings(false), settings(false)]), @"Some((Settings { allow_index_creation: false, settings_ids: [0, 1, 2] }, false, None))");
 
     // 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))");
-    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))");
-    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))");
-    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))");
-    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))"###);
-    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))"###);
-    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))"###);
-    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))"###);
-    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))");
-    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))");
-    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))");
-    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))");
-    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))"###);
-    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))"###);
-    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))"###);
-    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))"###);
+    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(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(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(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(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(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(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(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(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(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(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(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(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(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(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(UpdateDocuments, false, Some("catto")), doc_del()]), @r###"Some((DocumentOperation { allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false, None))"###);
     // 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))");
-    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))");
-    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))");
-    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))");
-    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))"###);
-    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))"###);
-    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))"###);
-    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))"###);
-    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))");
-    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))");
-    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))"###);
-    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))"###);
+    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(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(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(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(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(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(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(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(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(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(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(UpdateDocuments, false, Some("catto"))]), @r###"Some((DocumentOperation { allow_index_creation: false, primary_key: Some("catto"), operation_ids: [0, 1] }, false, None))"###);
 
     // 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))");
-    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))");
-    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))");
-    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))");
-    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))"###);
-    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))"###);
-    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))"###);
-    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))"###);
-    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))");
-    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))");
-    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))");
-    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))");
-    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))"###);
-    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))"###);
-    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))"###);
-    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))"###);
+    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(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(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(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(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(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(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(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(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(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(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(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(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(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(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(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 })))"###);
     // 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))");
-    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))");
-    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))");
-    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))");
-    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))");
-    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))");
-    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))");
+    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(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(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(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(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(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(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(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(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(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(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(UpdateDocuments, false, Some("catto"))]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, Some(DeletionByFilterWithDocumentOperation { id: 1 })))");
 }
 
 #[test]
 fn simple_different_document_operations_autobatch_together() {
     // addition and updates with 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))");
-    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))");
-    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))");
-    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))");
-    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))");
+    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(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_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 { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithDeletionByFilter { 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, 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, Some(DeletionByFilterWithDocumentOperation { id: 1 })))");
 
-    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))");
-    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))");
-    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))");
+    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(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_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_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_imp(ReplaceDocuments, true, None), idx_update()]), @"Some((DocumentOperation { 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))");
-    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))");
+    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(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_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_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_imp(ReplaceDocuments, true, None), idx_swap()]), @"Some((DocumentOperation { 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))");
-    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))");
+    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(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_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_fil(), idx_swap()]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: true }, false, Some(TaskCannotBeBatched { kind: IndexSwap, id: 1 })))");
 }
 
 #[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))");
-    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))");
+    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(UpdateDocuments, true, None), settings(true)]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
 
     // 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))");
-    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))");
+    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 { allow_index_creation: true, primary_key: None, operation_ids: [0, 1] }, true, Some(DocumentOperationWithSettings { id: 2 })))");
 
     // 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))");
-    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))");
+    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(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 })))");
 
     // 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))");
-    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))");
-    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))");
-    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))");
-    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))");
-    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))");
-    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))");
-    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))");
-    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))");
-    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))");
+    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(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(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(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(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(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(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(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(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(UpdateDocuments, true, None), settings(true), idx_swap()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
 }
 
 #[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))");
-    debug_snapshot!(autobatch_from(true, None, [doc_clr(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentClear { ids: [0] }, false))");
+    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(UpdateDocuments, true, None)]), @"Some((DocumentClear { ids: [0] }, false, Some(DocumentOperationWithSettings { id: 1 })))");
 
     // 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))");
-    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))");
+    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(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None), doc_clr()]), @"Some((DocumentClear { ids: [0, 1, 2] }, true, None))");
 
     // 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))");
-    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))");
+    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(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 })))");
 
     // 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))");
-    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))");
+    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(UpdateDocuments, true, None), doc_imp(UpdateDocuments, true, None), doc_clr(), doc_clr(), doc_clr()]), @"Some((DocumentClear { ids: [0, 1, 2, 3, 4] }, true, None))");
 }
 
 #[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))");
+    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, [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))");
-    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))");
+    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, [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(UpdateDocuments, true, None), settings(true), doc_clr()]), @"Some((DocumentOperation { allow_index_creation: true, primary_key: None, operation_ids: [0] }, true, Some(DocumentOperationWithSettings { id: 1 })))");
 }
 
 #[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))");
-    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))");
-    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))");
-    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))");
-    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))");
+    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(UpdateDocuments, true, 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, Some(IndexDeletion { id: 0 })))");
+    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_del()]), @"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, Some(IndexDeletion { id: 0 })))");
+    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(), settings(true)]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
+    debug_snapshot!(autobatch_from(true, None, [idx_del(), settings(false)]), @"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))");
-    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))");
-    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))");
-    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))");
-    debug_snapshot!(autobatch_from(false,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(UpdateDocuments, true, 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, Some(IndexDeletion { id: 0 })))");
+    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_del()]), @"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, Some(IndexDeletion { id: 0 })))");
+    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(), settings(true)]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
+    debug_snapshot!(autobatch_from(false,None,  [idx_del(), settings(false)]), @"Some((IndexDeletion { ids: [0] }, false, Some(IndexDeletion { id: 0 })))");
 
     // 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))");
-    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))");
-    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))");
-    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))");
-    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))");
+    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(UpdateDocuments, true, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true, Some(IndexDeletion { id: 1 })))");
+    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(UpdateDocuments, false, None), 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, Some(IndexDeletion { id: 1 })))");
+    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_clr(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false, Some(IndexDeletion { id: 1 })))");
+    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(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false, 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))");
-    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))");
-    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))");
-    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))");
-    debug_snapshot!(autobatch_from(false,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(UpdateDocuments, true, None), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, true, Some(IndexDeletion { id: 1 })))");
+    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(UpdateDocuments, false, None), 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, Some(IndexDeletion { id: 1 })))");
+    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_clr(), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false, Some(IndexDeletion { id: 1 })))");
+    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(false), idx_del()]), @"Some((IndexDeletion { ids: [0, 1] }, false, Some(IndexDeletion { id: 1 })))");
 }
 
 #[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))");
-    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))");
-    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))");
-    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))");
-    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))");
+    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, 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, 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, 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, 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(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))");
-    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))");
-    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))");
-    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))");
-    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))");
+    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, 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, 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, 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, false, None), settings(true)]), @"Some((DocumentOperation { allow_index_creation: false, primary_key: None, operation_ids: [0] }, false, Some(IndexCreationMismatch { id: 1 })))");
 
     // 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))");
-    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))");
-    debug_snapshot!(autobatch_from(false, None, [doc_del(), doc_imp(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false))");
+    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(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(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(UpdateDocuments, true, None)]), @"Some((DocumentDeletion { deletion_ids: [0], includes_by_filter: false }, false, Some(IndexCreationMismatch { id: 1 })))");
 }
 
 #[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))");
-    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))"###);
-    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))"###);
+    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, 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("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" })))"###);
 
     // 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))");
-    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))"###);
-    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] }, true))"###);
-    debug_snapshot!(autobatch_from(true, Some("id"), [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, Some("other"))]), @"Some((DocumentOperation { 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)]), @"Some((DocumentOperation { 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"))]), @"Some((DocumentOperation { 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, 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, 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")), 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("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")), 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, 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, Some("id")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { 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))"###);
-    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] }, 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))"###);
-    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))"###);
-    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))"###);
+    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, 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")), 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("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")), 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, 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("other")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { 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))"###);
-    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))"###);
-    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))"###);
-    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))"###);
-    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))"###);
+    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, 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")), 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"))]), @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 { 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 { allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true, Some(PrimaryKeyIndexMismatch { id: 0, in_index: "id", in_task: "other" })))"###);
 
     // ==> 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))");
-    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))"###);
-    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))"###);
+    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, 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("other"))]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("other"), operation_ids: [0] }, true, None))"###);
 
     // 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))");
-    debug_snapshot!(autobatch_from(true, None, [doc_imp(ReplaceDocuments, true, None), doc_imp(ReplaceDocuments, true, Some("id"))]), @"Some((DocumentOperation { 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] }, true))"###);
+    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, 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, Some("id")), doc_imp(ReplaceDocuments, true, None)]), @r###"Some((DocumentOperation { allow_index_creation: true, primary_key: Some("id"), operation_ids: [0, 1] }, true, None))"###);
 }

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

@@ -1,9 +1,10 @@
 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::{Kind, KindWithContent, Status, Task};
+use meilisearch_types::tasks::{BatchStopReason, Kind, KindWithContent, Status, Task};
 use roaring::RoaringBitmap;
 use uuid::Uuid;
 
@@ -47,6 +48,9 @@ pub(crate) enum Batch {
     IndexSwap {
         task: Task,
     },
+    Export {
+        task: Task,
+    },
     UpgradeDatabase {
         tasks: Vec<Task>,
     },
@@ -103,6 +107,7 @@ 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()
             }
@@ -142,6 +147,7 @@ impl Batch {
             | TaskDeletions(_)
             | SnapshotCreation(_)
             | Dump(_)
+            | Export { .. }
             | UpgradeDatabase { .. }
             | IndexSwap { .. } => None,
             IndexOperation { op, .. } => Some(op.index_uid()),
@@ -167,6 +173,7 @@ 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 {
@@ -423,11 +430,13 @@ impl IndexScheduler {
     }
 
     /// Create the next batch to be processed;
-    /// 1. We get the *last* task to cancel.
+    /// 0. 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* snapshot to process.
-    /// 4. We get the *next* dump to process.
-    /// 5. We get the *next* tasks to process for a specific index.
+    /// 3. We get the *next* export to process.
+    /// 4. We get the *next* snapshot to process.
+    /// 5. We get the *next* dump to process.
+    /// 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,
@@ -440,9 +449,23 @@ 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. The priority over everything is to upgrade the instance
+        // 0. we get the last task to cancel.
+        let to_cancel = self.queue.tasks.get_kind(rtxn, Kind::TaskCancelation)? & enqueued;
+        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() {
@@ -453,16 +476,26 @@ impl IndexScheduler {
                 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)));
         }
 
-        // 1. we get the last task to cancel.
-        let to_cancel = self.queue.tasks.get_kind(rtxn, Kind::TaskCancelation)? & enqueued;
-        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));
-            return Ok(Some((Batch::TaskCancelation { task }, 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
@@ -470,27 +503,45 @@ impl IndexScheduler {
         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 snapshot.
+        // 3. we batch the export.
+        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)));
         }
 
-        // 4. we batch the dumps.
+        // 5. 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)));
         }
 
-        // 5. We make a batch from the unprioritised tasks. Start by taking the next enqueued task.
+        // 6. 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)?;
@@ -504,6 +555,10 @@ 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)));
         };
 
@@ -525,9 +580,14 @@ 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().take(tasks_limit) {
+        for task_id in index_tasks.into_iter() {
+            if enqueued.len() >= tasks_limit {
+                stop_reason = BatchStopReason::ReachedTaskLimit { task_limit: tasks_limit };
+                break;
+            }
             let task = self
                 .queue
                 .tasks
@@ -535,20 +595,35 @@ impl IndexScheduler {
                 .and_then(|task| task.ok_or(Error::CorruptedTaskQueue))?;
 
             if let Some(uuid) = task.content_uuid() {
-                let content_size = self.queue.file_store.compute_size(uuid)?;
+                let content_size = match 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);
             }
 
-            if total_size > self.scheduler.batched_tasks_size_limit && !enqueued.is_empty() {
+            let size_limit = self.scheduler.batched_tasks_size_limit;
+            if total_size > size_limit && !enqueued.is_empty() {
+                stop_reason = BatchStopReason::ReachedSizeLimit { size_limit, size: total_size };
                 break;
             }
 
             enqueued.push((task.uid, task.kind));
         }
 
-        if let Some((batchkind, create_index)) =
+        stop_reason.replace_unspecified({
+            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

@@ -4,6 +4,7 @@ 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;
@@ -20,10 +21,12 @@ 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;
@@ -81,6 +84,9 @@ pub struct Scheduler {
     ///
     /// 0 disables the cache.
     pub(crate) embedding_cache_cap: usize,
+
+    /// Snapshot compaction status.
+    pub(crate) experimental_no_snapshot_compaction: bool,
 }
 
 impl Scheduler {
@@ -96,6 +102,7 @@ impl Scheduler {
             auth_env: self.auth_env.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,
         }
     }
 
@@ -112,6 +119,7 @@ impl Scheduler {
             auth_env,
             version_file_path: options.version_file_path.clone(),
             embedding_cache_cap: options.embedding_cache_cap,
+            experimental_no_snapshot_compaction: options.experimental_no_snapshot_compaction,
         }
     }
 }
@@ -223,16 +231,16 @@ impl IndexScheduler {
         let mut stop_scheduler_forever = false;
         let mut wtxn = self.env.write_txn().map_err(Error::HeedTransaction)?;
         let mut canceled = RoaringBitmap::new();
-        let mut congestion = None;
+        let mut process_batch_info = ProcessBatchInfo::default();
 
         match res {
-            Ok((tasks, cong)) => {
+            Ok((tasks, info)) => {
                 #[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);
-                congestion = cong;
+                process_batch_info = info;
                 let mut success = 0;
                 let mut failure = 0;
                 let mut canceled_by = None;
@@ -260,7 +268,7 @@ impl IndexScheduler {
 
                     self.queue
                         .tasks
-                        .update_task(&mut wtxn, &task)
+                        .update_task(&mut wtxn, &mut task)
                         .map_err(|e| Error::UnrecoverableError(Box::new(e)))?;
                 }
                 if let Some(canceled_by) = canceled_by {
@@ -341,7 +349,7 @@ impl IndexScheduler {
 
                     self.queue
                         .tasks
-                        .update_task(&mut wtxn, &task)
+                        .update_task(&mut wtxn, &mut task)
                         .map_err(|e| Error::UnrecoverableError(Box::new(e)))?;
                 }
             }
@@ -350,6 +358,9 @@ impl IndexScheduler {
         // 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| {
@@ -359,6 +370,35 @@ impl IndexScheduler {
             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!(

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

@@ -6,13 +6,14 @@ use meilisearch_types::batches::{BatchEnqueuedAt, BatchId};
 use meilisearch_types::heed::{RoTxn, RwTxn};
 use meilisearch_types::milli::progress::{Progress, VariableNameStep};
 use meilisearch_types::milli::{self, ChannelCongestion};
-use meilisearch_types::tasks::{Details, IndexSwap, KindWithContent, Status, Task};
+use meilisearch_types::tasks::{Details, IndexSwap, Kind, 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,
+    AtomicBatchStep, AtomicTaskStep, CreateIndexProgress, DeleteIndexProgress, FinalizingIndexStep,
     InnerSwappingTwoIndexes, SwappingTheIndexes, TaskCancelationProgress, TaskDeletionProgress,
     UpdateIndexProgress,
 };
@@ -22,6 +23,16 @@ use crate::utils::{
 };
 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.
     ///
@@ -35,7 +46,7 @@ impl IndexScheduler {
         batch: Batch,
         current_batch: &mut ProcessingBatch,
         progress: Progress,
-    ) -> Result<(Vec<Task>, Option<ChannelCongestion>)> {
+    ) -> Result<(Vec<Task>, ProcessBatchInfo)> {
         #[cfg(test)]
         {
             self.maybe_fail(crate::test_utils::FailureLocation::InsideProcessBatch)?;
@@ -76,7 +87,7 @@ impl IndexScheduler {
 
                 canceled_tasks.push(task);
 
-                Ok((canceled_tasks, None))
+                Ok((canceled_tasks, ProcessBatchInfo::default()))
             }
             Batch::TaskDeletions(mut tasks) => {
                 // 1. Retrieve the tasks that matched the query at enqueue-time.
@@ -115,14 +126,14 @@ impl IndexScheduler {
                         _ => unreachable!(),
                     }
                 }
-                Ok((tasks, None))
-            }
-            Batch::SnapshotCreation(tasks) => {
-                self.process_snapshot(progress, tasks).map(|tasks| (tasks, None))
-            }
-            Batch::Dump(task) => {
-                self.process_dump_creation(progress, task).map(|tasks| (tasks, None))
+                Ok((tasks, ProcessBatchInfo::default()))
             }
+            Batch::SnapshotCreation(tasks) => self
+                .process_snapshot(progress, tasks)
+                .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 {
@@ -134,15 +145,33 @@ 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 mut index_wtxn = index.write_txn()?;
-                let (tasks, congestion) =
-                    self.apply_index_operation(&mut index_wtxn, &index, op, progress)?;
+                let pre_commit_dabases_sizes = index.database_sizes(&index_wtxn)?;
+                let (tasks, congestion) = self.apply_index_operation(
+                    &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();
 
@@ -153,12 +182,15 @@ 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(())
                 }();
@@ -171,7 +203,16 @@ impl IndexScheduler {
                     ),
                 }
 
-                Ok((tasks, congestion))
+                let info = ProcessBatchInfo {
+                    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);
@@ -202,10 +243,12 @@ impl IndexScheduler {
                     );
                     builder.set_primary_key(primary_key);
                     let must_stop_processing = self.scheduler.must_stop_processing.clone();
+
                     builder
                         .execute(
-                            |indexing_step| tracing::debug!(update = ?indexing_step),
-                            || must_stop_processing.get(),
+                            &|| must_stop_processing.get(),
+                            &progress,
+                            current_batch.embedder_stats.clone(),
                         )
                         .map_err(|e| Error::from_milli(e, Some(index_uid.to_string())))?;
                     index_wtxn.commit()?;
@@ -239,7 +282,7 @@ impl IndexScheduler {
                     ),
                 }
 
-                Ok((vec![task], None))
+                Ok((vec![task], ProcessBatchInfo::default()))
             }
             Batch::IndexDeletion { index_uid, index_has_been_created, mut tasks } => {
                 progress.update_progress(DeleteIndexProgress::DeletingTheIndex);
@@ -273,7 +316,9 @@ impl IndexScheduler {
                     };
                 }
 
-                Ok((tasks, None))
+                // Here we could also show that all the internal database sizes goes to 0
+                // but it would mean opening the index and that's costly.
+                Ok((tasks, ProcessBatchInfo::default()))
             }
             Batch::IndexSwap { mut task } => {
                 progress.update_progress(SwappingTheIndexes::EnsuringCorrectnessOfTheSwap);
@@ -321,15 +366,57 @@ impl IndexScheduler {
                 }
                 wtxn.commit()?;
                 task.status = Status::Succeeded;
-                Ok((vec![task], None))
+                Ok((vec![task], ProcessBatchInfo::default()))
+            }
+            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>() {
@@ -351,7 +438,7 @@ impl IndexScheduler {
                     task.error = None;
                 }
 
-                Ok((tasks, None))
+                Ok((tasks, ProcessBatchInfo::default()))
             }
         }
     }
@@ -627,17 +714,81 @@ 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
-        let cancelable_tasks = self.queue.tasks.get_status(rtxn, Status::Enqueued)?;
-        let tasks_to_cancel = cancelable_tasks & matched_tasks;
+        tasks_to_cancel |= enqueued_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

@@ -5,6 +5,7 @@ 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::progress::{Progress, VariableNameStep};
 use meilisearch_types::milli::vector::parsed_vectors::{ExplicitVectors, VectorOrArrayOfVectors};
 use meilisearch_types::milli::{self};
@@ -43,7 +44,16 @@ impl IndexScheduler {
 
         let rtxn = self.env.read_txn()?;
 
-        // 2. dump the tasks
+        // 2. dump the chat completion settings
+        // 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()?;
 
@@ -81,7 +91,7 @@ impl IndexScheduler {
 
             let mut dump_content_file = dump_tasks.push_task(&t.into())?;
 
-            // 2.1. Dump the `content_file` associated with the task if there is one and the task is not finished yet.
+            // 3.1. 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);
@@ -105,7 +115,7 @@ impl IndexScheduler {
         }
         dump_tasks.flush()?;
 
-        // 3. dump the batches
+        // 4. dump the batches
         progress.update_progress(DumpCreationProgress::DumpTheBatches);
         let mut dump_batches = dump.create_batches_queue()?;
 
@@ -138,7 +148,7 @@ impl IndexScheduler {
         }
         dump_batches.flush()?;
 
-        // 4. Dump the indexes
+        // 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;
@@ -165,9 +175,6 @@ 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 nb_documents = index
                 .number_of_documents(&rtxn)
@@ -178,7 +185,7 @@ impl IndexScheduler {
             let documents = index
                 .all_documents(&rtxn)
                 .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
-            // 4.1. Dump the documents
+            // 5.1. Dump the documents
             for ret in documents {
                 if self.scheduler.must_stop_processing.get() {
                     return Err(Error::AbortedTask);
@@ -221,16 +228,21 @@ impl IndexScheduler {
                         return Err(Error::from_milli(user_err, Some(uid.to_string())));
                     };
 
-                    for (embedder_name, embeddings) in embeddings {
-                        let user_provided = embedding_configs
-                            .iter()
-                            .find(|conf| conf.name == embedder_name)
-                            .is_some_and(|conf| conf.user_provided.contains(id));
+                    for (
+                        embedder_name,
+                        EmbeddingsWithMetadata { embeddings, regenerate, has_fragments },
+                    ) in embeddings
+                    {
                         let embeddings = ExplicitVectors {
                             embeddings: Some(VectorOrArrayOfVectors::from_array_of_vectors(
                                 embeddings,
                             )),
-                            regenerate: !user_provided,
+                            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());
                     }
@@ -240,7 +252,7 @@ impl IndexScheduler {
                 atomic.fetch_add(1, Ordering::Relaxed);
             }
 
-            // 4.2. Dump the settings
+            // 5.2. Dump the settings
             let settings = meilisearch_types::settings::settings(
                 index,
                 &rtxn,
@@ -251,7 +263,7 @@ impl IndexScheduler {
             Ok(())
         })?;
 
-        // 5. Dump experimental feature settings
+        // 6. Dump experimental feature settings
         progress.update_progress(DumpCreationProgress::DumpTheExperimentalFeatures);
         let features = self.features().runtime_features();
         dump.create_experimental_features(features)?;

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

@@ -0,0 +1,377 @@
+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

@@ -1,11 +1,13 @@
+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::Progress;
+use meilisearch_types::milli::progress::{EmbedderStats, Progress};
 use meilisearch_types::milli::update::new::indexer::{self, UpdateByFunction};
 use meilisearch_types::milli::update::DocumentAdditionResult;
-use meilisearch_types::milli::{self, ChannelCongestion, Filter, ThreadPoolNoAbortBuilder};
+use meilisearch_types::milli::{self, ChannelCongestion, Filter};
 use meilisearch_types::settings::apply_settings_to_builder;
 use meilisearch_types::tasks::{Details, KindWithContent, Status, Task};
 use meilisearch_types::Index;
@@ -24,7 +26,7 @@ impl IndexScheduler {
     /// The list of processed tasks.
     #[tracing::instrument(
         level = "trace",
-        skip(self, index_wtxn, index, progress),
+        skip(self, index_wtxn, index, progress, embedder_stats),
         target = "indexing::scheduler"
     )]
     pub(crate) fn apply_index_operation<'i>(
@@ -32,7 +34,8 @@ impl IndexScheduler {
         index_wtxn: &mut RwTxn<'i>,
         index: &'i Index,
         operation: IndexOperation,
-        progress: Progress,
+        progress: &Progress,
+        embedder_stats: Arc<EmbedderStats>,
     ) -> Result<(Vec<Task>, Option<ChannelCongestion>)> {
         let indexer_alloc = Bump::new();
         let started_processing_at = std::time::Instant::now();
@@ -63,6 +66,11 @@ impl IndexScheduler {
             }
             IndexOperation::DocumentOperation { index_uid, primary_key, operations, mut tasks } => {
                 progress.update_progress(DocumentOperationProgress::RetrievingConfig);
+
+                let network = self.network();
+
+                let shards = network.shards();
+
                 // 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.
@@ -86,8 +94,9 @@ impl IndexScheduler {
                 let mut content_files_iter = content_files.iter();
                 let mut indexer = indexer::DocumentOperation::new();
                 let embedders = index
+                    .embedding_configs()
                     .embedding_configs(index_wtxn)
-                    .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
+                    .map_err(|e| Error::from_milli(e.into(), Some(index_uid.clone())))?;
                 let embedders = self.embedders(index_uid.clone(), embedders)?;
                 for operation in operations {
                     match operation {
@@ -113,18 +122,8 @@ impl IndexScheduler {
                     }
                 }
 
-                let local_pool;
                 let indexer_config = self.index_mapper.indexer_config();
-                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 pool = &indexer_config.thread_pool;
 
                 progress.update_progress(DocumentOperationProgress::ComputingDocumentChanges);
                 let (document_changes, operation_stats, primary_key) = indexer
@@ -136,6 +135,7 @@ impl IndexScheduler {
                         &mut new_fields_ids_map,
                         &|| must_stop_processing.get(),
                         progress.clone(),
+                        shards.as_ref(),
                     )
                     .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?;
 
@@ -186,7 +186,8 @@ impl IndexScheduler {
                             &document_changes,
                             embedders,
                             &|| must_stop_processing.get(),
-                            &progress,
+                            progress,
+                            &embedder_stats,
                         )
                         .map_err(|e| Error::from_milli(e, Some(index_uid.clone())))?,
                     );
@@ -266,18 +267,8 @@ impl IndexScheduler {
 
                 let mut congestion = None;
                 if task.error.is_none() {
-                    let local_pool;
                     let indexer_config = self.index_mapper.indexer_config();
-                    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 pool = &indexer_config.thread_pool;
 
                     let candidates_count = candidates.len();
                     progress.update_progress(DocumentEditionProgress::ComputingDocumentChanges);
@@ -290,8 +281,9 @@ impl IndexScheduler {
                         })
                         .unwrap()?;
                     let embedders = index
+                        .embedding_configs()
                         .embedding_configs(index_wtxn)
-                        .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
+                        .map_err(|err| Error::from_milli(err.into(), Some(index_uid.clone())))?;
                     let embedders = self.embedders(index_uid.clone(), embedders)?;
 
                     progress.update_progress(DocumentEditionProgress::Indexing);
@@ -307,7 +299,8 @@ impl IndexScheduler {
                             &document_changes,
                             embedders,
                             &|| must_stop_processing.get(),
-                            &progress,
+                            progress,
+                            &embedder_stats,
                         )
                         .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?,
                     );
@@ -429,18 +422,8 @@ impl IndexScheduler {
 
                 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 = 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 pool = &indexer_config.thread_pool;
 
                     progress.update_progress(DocumentDeletionProgress::DeleteDocuments);
                     let mut indexer = indexer::DocumentDeletion::new();
@@ -448,8 +431,9 @@ 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, Some(index_uid.clone())))?;
+                        .map_err(|err| Error::from_milli(err.into(), Some(index_uid.clone())))?;
                     let embedders = self.embedders(index_uid.clone(), embedders)?;
 
                     progress.update_progress(DocumentDeletionProgress::Indexing);
@@ -465,7 +449,8 @@ impl IndexScheduler {
                             &document_changes,
                             embedders,
                             &|| must_stop_processing.get(),
-                            &progress,
+                            progress,
+                            &embedder_stats,
                         )
                         .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?,
                     );
@@ -498,14 +483,11 @@ impl IndexScheduler {
                 }
 
                 progress.update_progress(SettingsProgress::ApplyTheSettings);
-                builder
-                    .execute(
-                        |indexing_step| tracing::debug!(update = ?indexing_step),
-                        || must_stop_processing.get(),
-                    )
+                let congestion = builder
+                    .execute(&|| must_stop_processing.get(), progress, embedder_stats)
                     .map_err(|err| Error::from_milli(err, Some(index_uid.clone())))?;
 
-                Ok((tasks, None))
+                Ok((tasks, congestion))
             }
             IndexOperation::DocumentClearAndSetting {
                 index_uid,
@@ -520,7 +502,8 @@ impl IndexScheduler {
                         index_uid: index_uid.clone(),
                         tasks: cleared_tasks,
                     },
-                    progress.clone(),
+                    progress,
+                    embedder_stats.clone(),
                 )?;
 
                 let (settings_tasks, _congestion) = self.apply_index_operation(
@@ -528,6 +511,7 @@ impl IndexScheduler {
                     index,
                     IndexOperation::Settings { index_uid, settings, tasks: settings_tasks },
                     progress,
+                    embedder_stats,
                 )?;
 
                 let mut tasks = settings_tasks;

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

@@ -41,7 +41,12 @@ impl IndexScheduler {
         progress.update_progress(SnapshotCreationProgress::SnapshotTheIndexScheduler);
         let dst = temp_snapshot_dir.path().join("tasks");
         fs::create_dir_all(&dst)?;
-        self.env.copy_to_path(dst.join("data.mdb"), CompactionOption::Enabled)?;
+        let compaction_option = if self.scheduler.experimental_no_snapshot_compaction {
+            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()?;
@@ -80,7 +85,7 @@ impl IndexScheduler {
             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"), CompactionOption::Enabled)
+                .copy_to_path(dst.join("data.mdb"), compaction_option)
                 .map_err(|e| Error::from_milli(e, Some(name.to_string())))?;
         }
 
@@ -90,7 +95,7 @@ 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"), CompactionOption::Enabled)?;
+        self.scheduler.auth_env.copy_to_path(dst.join("data.mdb"), compaction_option)?;
 
         // 5. Copy and tarball the flat snapshot
         progress.update_progress(SnapshotCreationProgress::CreateTheTarball);

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

@@ -12,10 +12,14 @@ impl IndexScheduler {
         #[cfg(test)]
         self.maybe_fail(crate::test_utils::FailureLocation::ProcessUpgrade)?;
 
-        enum UpgradeIndex {}
         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,
@@ -27,6 +31,7 @@ impl IndexScheduler {
                 &mut index_wtxn,
                 &index,
                 db_version,
+                || must_stop_processing.get(),
                 progress.clone(),
             )
             .map_err(|e| Error::from_milli(e, Some(uid.to_string())))?;
@@ -46,4 +51,42 @@ impl IndexScheduler {
 
         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

@@ -0,0 +1,17 @@
+---
+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

@@ -0,0 +1,12 @@
+---
+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

@@ -0,0 +1,15 @@
+---
+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

@@ -0,0 +1,15 @@
+---
+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

@@ -1,12 +1,17 @@
 ---
 source: crates/index-scheduler/src/scheduler/test_embedders.rs
-expression: simple_hf_config.embedder_options
+expression: fakerest_config.embedder_options
 ---
 {
-  "HuggingFace": {
-    "model": "sentence-transformers/all-MiniLM-L6-v2",
-    "revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
+  "Rest": {
+    "api_key": "My super secret",
     "distribution": null,
-    "pooling": "useModel"
+    "dimensions": 384,
+    "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

@@ -1,6 +1,5 @@
 ---
 source: crates/index-scheduler/src/scheduler/test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -40,7 +39,7 @@ 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}}, }
+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.", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,1,]

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

@@ -1,11 +1,10 @@
 ---
 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}}, }
+{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`", }
 ----------------------------------------------------------------------
 ### 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 }}
@@ -47,7 +46,7 @@ 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}}, }
+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`", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

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

@@ -1,6 +1,5 @@
 ---
 source: crates/index-scheduler/src/scheduler/test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -50,8 +49,8 @@ catto: { number_of_documents: 1, field_distribution: {"id": 1} }
 [timestamp] [1,2,3,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"receivedDocuments":1,"indexedDocuments":1}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"documentAdditionOrUpdate":1},"indexUids":{"catto":1}}, }
-1 {uid: 1, details: {"receivedDocuments":2,"indexedDocuments":0,"matchedTasks":3,"canceledTasks":2,"originalFilter":"test_query"}, stats: {"totalNbTasks":3,"status":{"succeeded":1,"canceled":2},"types":{"documentAdditionOrUpdate":2,"taskCancelation":1},"indexUids":{"beavero":1,"wolfo":1}}, }
+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`", }
+1 {uid: 1, details: {"receivedDocuments":2,"indexedDocuments":0,"matchedTasks":3,"canceledTasks":2,"originalFilter":"test_query"}, stats: {"totalNbTasks":3,"status":{"succeeded":1,"canceled":2},"types":{"documentAdditionOrUpdate":2,"taskCancelation":1},"indexUids":{"beavero":1,"wolfo":1}}, stop reason: "created batch containing only task with id 3 of type `taskCancelation` that cannot be batched with any other task.", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

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

@@ -1,6 +1,5 @@
 ---
 source: crates/index-scheduler/src/scheduler/test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -42,7 +41,7 @@ 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}}, }
+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`", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

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

@@ -1,11 +1,10 @@
 ---
 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}}, }
+{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`", }
 ----------------------------------------------------------------------
 ### 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 +45,7 @@ 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}}, }
+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`", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

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

@@ -1,6 +1,5 @@
 ---
 source: crates/index-scheduler/src/scheduler/test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -39,7 +38,7 @@ canceled [0,]
 [timestamp] [0,1,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"matchedTasks":1,"canceledTasks":1,"originalFilter":"cancel dump"}, stats: {"totalNbTasks":2,"status":{"succeeded":1,"canceled":1},"types":{"taskCancelation":1,"dumpCreation":1},"indexUids":{}}, }
+0 {uid: 0, details: {"matchedTasks":1,"canceledTasks":1,"originalFilter":"cancel dump"}, stats: {"totalNbTasks":2,"status":{"succeeded":1,"canceled":1},"types":{"taskCancelation":1,"dumpCreation":1},"indexUids":{}}, stop reason: "created batch containing only task with id 1 of type `taskCancelation` that cannot be batched with any other task.", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,1,]

crates/index-scheduler/src/scheduler/snapshots/test.rs/cancel_processing_dump/cancel_registered.snap

@@ -1,11 +1,10 @@
 ---
 source: crates/index-scheduler/src/scheduler/test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch Some(0):
 [0,]
-{uid: 0, details: {"dumpUid":null}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"dumpCreation":1},"indexUids":{}}, }
+{uid: 0, details: {"dumpUid":null}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"dumpCreation":1},"indexUids":{}}, stop reason: "created batch containing only task with id 0 of type `dumpCreation` that cannot be batched with any other task.", }
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: enqueued, details: { dump_uid: None }, kind: DumpCreation { keys: [], instance_uid: None }}

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

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

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

@@ -1,6 +1,5 @@
 ---
 source: crates/index-scheduler/src/scheduler/test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -41,7 +40,7 @@ catto: { number_of_documents: 0, field_distribution: {} }
 [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}}, }
+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.", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,1,]

crates/index-scheduler/src/scheduler/snapshots/test.rs/cancel_processing_task/cancel_task_registered.snap

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

crates/index-scheduler/src/scheduler/snapshots/test.rs/cancel_processing_task/initial_task_processing.snap

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

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

@@ -1,6 +1,5 @@
 ---
 source: crates/index-scheduler/src/scheduler/test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -41,8 +40,8 @@ catto: { number_of_documents: 1, field_distribution: {"id": 1} }
 [timestamp] [1,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"receivedDocuments":1,"indexedDocuments":1}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"documentAdditionOrUpdate":1},"indexUids":{"catto":1}}, }
-1 {uid: 1, details: {"matchedTasks":1,"canceledTasks":0,"originalFilter":"test_query"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"taskCancelation":1},"indexUids":{}}, }
+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", }
+1 {uid: 1, details: {"matchedTasks":1,"canceledTasks":0,"originalFilter":"test_query"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"taskCancelation":1},"indexUids":{}}, stop reason: "created batch containing only task with id 1 of type `taskCancelation` that cannot be batched with any other task.", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

crates/index-scheduler/src/scheduler/snapshots/test.rs/cancel_succeeded_task/initial_task_processed.snap

@@ -1,6 +1,5 @@
 ---
 source: crates/index-scheduler/src/scheduler/test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -36,7 +35,7 @@ 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}}, }
+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", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

crates/index-scheduler/src/scheduler/snapshots/test.rs/do_not_batch_task_of_different_indexes/all_tasks_processed.snap

@@ -1,6 +1,5 @@
 ---
 source: crates/index-scheduler/src/scheduler/test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -61,12 +60,12 @@ girafos: { number_of_documents: 0, field_distribution: {} }
 [timestamp] [5,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggos":1}}, }
-1 {uid: 1, details: {}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"cattos":1}}, }
-2 {uid: 2, details: {}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"girafos":1}}, }
-3 {uid: 3, details: {"deletedDocuments":0}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"documentDeletion":1},"indexUids":{"doggos":1}}, }
-4 {uid: 4, details: {"deletedDocuments":0}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"documentDeletion":1},"indexUids":{"cattos":1}}, }
-5 {uid: 5, details: {"deletedDocuments":0}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"documentDeletion":1},"indexUids":{"girafos":1}}, }
+0 {uid: 0, details: {}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggos":1}}, stop reason: "created batch containing only task with id 0 of type `indexCreation` that cannot be batched with any other task.", }
+1 {uid: 1, details: {}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"cattos":1}}, stop reason: "created batch containing only task with id 1 of type `indexCreation` that cannot be batched with any other task.", }
+2 {uid: 2, details: {}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"girafos":1}}, stop reason: "created batch containing only task with id 2 of type `indexCreation` that cannot be batched with any other task.", }
+3 {uid: 3, details: {"deletedDocuments":0}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"documentDeletion":1},"indexUids":{"doggos":1}}, stop reason: "batched all enqueued tasks for index `doggos`", }
+4 {uid: 4, details: {"deletedDocuments":0}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"documentDeletion":1},"indexUids":{"cattos":1}}, stop reason: "batched all enqueued tasks for index `cattos`", }
+5 {uid: 5, details: {"deletedDocuments":0}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"documentDeletion":1},"indexUids":{"girafos":1}}, stop reason: "batched all enqueued tasks", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

crates/index-scheduler/src/scheduler/snapshots/test.rs/document_addition_and_index_deletion/before_index_creation.snap

@@ -1,6 +1,5 @@
 ---
 source: crates/index-scheduler/src/scheduler/test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -42,7 +41,7 @@ doggos: { number_of_documents: 0, field_distribution: {} }
 [timestamp] [0,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggos":1}}, }
+0 {uid: 0, details: {}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggos":1}}, stop reason: "created batch containing only task with id 0 of type `indexCreation` that cannot be batched with any other task.", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

crates/index-scheduler/src/scheduler/snapshots/test.rs/document_addition_and_index_deletion/both_task_succeeded.snap

@@ -1,6 +1,5 @@
 ---
 source: crates/index-scheduler/src/scheduler/test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -43,8 +42,8 @@ doggos [0,1,2,]
 [timestamp] [1,2,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggos":1}}, }
-1 {uid: 1, details: {"receivedDocuments":1,"indexedDocuments":0,"deletedDocuments":0}, stats: {"totalNbTasks":2,"status":{"succeeded":2},"types":{"documentAdditionOrUpdate":1,"indexDeletion":1},"indexUids":{"doggos":2}}, }
+0 {uid: 0, details: {}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggos":1}}, stop reason: "created batch containing only task with id 0 of type `indexCreation` that cannot be batched with any other task.", }
+1 {uid: 1, details: {"receivedDocuments":1,"indexedDocuments":0,"deletedDocuments":0}, stats: {"totalNbTasks":2,"status":{"succeeded":2},"types":{"documentAdditionOrUpdate":1,"indexDeletion":1},"indexUids":{"doggos":2}}, stop reason: "stopped after task with id 2 because it deletes the index", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,]

crates/index-scheduler/src/scheduler/snapshots/test.rs/document_addition_and_index_deletion_on_unexisting_index/2.snap

@@ -1,6 +1,5 @@
 ---
 source: crates/index-scheduler/src/scheduler/test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch None:
@@ -38,7 +37,7 @@ doggos [0,1,]
 [timestamp] [0,1,]
 ----------------------------------------------------------------------
 ### All Batches:
-0 {uid: 0, details: {"receivedDocuments":1,"indexedDocuments":0,"deletedDocuments":0}, stats: {"totalNbTasks":2,"status":{"succeeded":2},"types":{"documentAdditionOrUpdate":1,"indexDeletion":1},"indexUids":{"doggos":2}}, }
+0 {uid: 0, details: {"receivedDocuments":1,"indexedDocuments":0,"deletedDocuments":0}, stats: {"totalNbTasks":2,"status":{"succeeded":2},"types":{"documentAdditionOrUpdate":1,"indexDeletion":1},"indexUids":{"doggos":2}}, stop reason: "stopped after task with id 1 because it deletes the index", }
 ----------------------------------------------------------------------
 ### Batch to tasks mapping:
 0 [0,1,]

crates/index-scheduler/src/scheduler/snapshots/test.rs/insert_task_while_another_task_is_processing/after_batch_creation.snap

@@ -1,11 +1,10 @@
 ---
 source: crates/index-scheduler/src/scheduler/test.rs
-snapshot_kind: text
 ---
 ### Autobatching Enabled = true
 ### Processing batch Some(0):
 [0,]
-{uid: 0, details: {"primaryKey":"id"}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"indexCreation":1},"indexUids":{"index_a":1}}, }
+{uid: 0, details: {"primaryKey":"id"}, stats: {"totalNbTasks":1,"status":{"processing":1},"types":{"indexCreation":1},"indexUids":{"index_a":1}}, stop reason: "created batch containing only task with id 0 of type `indexCreation` that cannot be batched with any other task.", }
 ----------------------------------------------------------------------
 ### All Tasks:
 0 {uid: 0, status: enqueued, details: { primary_key: Some("id") }, kind: IndexCreation { index_uid: "index_a", primary_key: Some("id") }}