mirror of
https://github.com/meilisearch/meilisearch.git
synced 2025-12-07 13:15:43 +00:00
Compare commits
2 Commits
update-ver
...
prototype-
| Author | SHA1 | Date | |
|---|---|---|---|
|
e180cd27d3 | ||
|
|
ef3884e46f |
5
.github/ISSUE_TEMPLATE/new_feature_issue.md
vendored
5
.github/ISSUE_TEMPLATE/new_feature_issue.md
vendored
@@ -24,11 +24,6 @@ TBD
|
||||
- [ ] If not, add the `no db change` label to your PR, and you're good to merge.
|
||||
- [ ] If yes, add the `db change` label to your PR. You'll receive a message explaining you what to do.
|
||||
|
||||
### Reminders when adding features
|
||||
|
||||
- [ ] Write unit tests using insta
|
||||
- [ ] Write declarative integration tests in [workloads/tests](https://github.com/meilisearch/meilisearch/tree/main/workloads/test). Specify the routes to call and then call `cargo xtask test workloads/tests/YOUR_TEST.json --update-responses` so that responses are automatically filled.
|
||||
|
||||
### Reminders when modifying the API
|
||||
|
||||
- [ ] Update the openAPI file with utoipa:
|
||||
|
||||
2
.github/workflows/bench-pr.yml
vendored
2
.github/workflows/bench-pr.yml
vendored
@@ -67,6 +67,8 @@ jobs:
|
||||
ref: ${{ steps.comment-branch.outputs.head_ref }}
|
||||
|
||||
- uses: dtolnay/rust-toolchain@1.89
|
||||
with:
|
||||
profile: minimal
|
||||
|
||||
- name: Run benchmarks on PR ${{ github.event.issue.id }}
|
||||
run: |
|
||||
|
||||
2
.github/workflows/bench-push-indexing.yml
vendored
2
.github/workflows/bench-push-indexing.yml
vendored
@@ -13,6 +13,8 @@ jobs:
|
||||
steps:
|
||||
- uses: actions/checkout@v5
|
||||
- uses: dtolnay/rust-toolchain@1.89
|
||||
with:
|
||||
profile: minimal
|
||||
|
||||
# Run benchmarks
|
||||
- name: Run benchmarks - Dataset ${BENCH_NAME} - Branch main - Commit ${{ github.sha }}
|
||||
|
||||
6
.github/workflows/db-change-comments.yml
vendored
6
.github/workflows/db-change-comments.yml
vendored
@@ -6,7 +6,7 @@ on:
|
||||
|
||||
env:
|
||||
MESSAGE: |
|
||||
### Hello, I'm a bot 🤖
|
||||
### Hello, I'm a bot 🤖
|
||||
|
||||
You are receiving this message because you declared that this PR make changes to the Meilisearch database.
|
||||
Depending on the nature of the change, additional actions might be required on your part. The following sections detail the additional actions depending on the nature of the change, please copy the relevant section in the description of your PR, and make sure to perform the required actions.
|
||||
@@ -19,7 +19,6 @@ env:
|
||||
|
||||
- [ ] Detail the change to the DB format and why they are forward compatible
|
||||
- [ ] Forward-compatibility: A database created before this PR and using the features touched by this PR was able to be opened by a Meilisearch produced by the code of this PR.
|
||||
- [ ] Declarative test: add a [declarative test containing a dumpless upgrade](https://github.com/meilisearch/meilisearch/blob/main/TESTING.md#typical-usage)
|
||||
|
||||
|
||||
## This PR makes breaking changes
|
||||
@@ -36,7 +35,8 @@ env:
|
||||
- [ ] Write the code to go from the old database to the new one
|
||||
- If the change happened in milli, the upgrade function should be written and called [here](https://github.com/meilisearch/meilisearch/blob/3fd86e8d76d7d468b0095d679adb09211ca3b6c0/crates/milli/src/update/upgrade/mod.rs#L24-L47)
|
||||
- If the change happened in the index-scheduler, we've never done it yet, but the right place to do it should be [here](https://github.com/meilisearch/meilisearch/blob/3fd86e8d76d7d468b0095d679adb09211ca3b6c0/crates/index-scheduler/src/scheduler/process_upgrade/mod.rs#L13)
|
||||
- [ ] Declarative test: add a [declarative test containing a dumpless upgrade](https://github.com/meilisearch/meilisearch/blob/main/TESTING.md#typical-usage)
|
||||
- [ ] Write an integration test [here](https://github.com/meilisearch/meilisearch/blob/main/crates/meilisearch/tests/upgrade/mod.rs) ensuring you can read the old database, upgrade to the new database, and read the new database as expected
|
||||
|
||||
|
||||
jobs:
|
||||
add-comment:
|
||||
|
||||
6
.github/workflows/flaky-tests.yml
vendored
6
.github/workflows/flaky-tests.yml
vendored
@@ -13,12 +13,6 @@ jobs:
|
||||
image: ubuntu:22.04
|
||||
steps:
|
||||
- uses: actions/checkout@v5
|
||||
- name: Clean space as per https://github.com/actions/virtual-environments/issues/709
|
||||
run: |
|
||||
sudo rm -rf "/opt/ghc" || true
|
||||
sudo rm -rf "/usr/share/dotnet" || true
|
||||
sudo rm -rf "/usr/local/lib/android" || true
|
||||
sudo rm -rf "/usr/local/share/boost" || true
|
||||
- name: Install needed dependencies
|
||||
run: |
|
||||
apt-get update && apt-get install -y curl
|
||||
|
||||
2
.github/workflows/fuzzer-indexing.yml
vendored
2
.github/workflows/fuzzer-indexing.yml
vendored
@@ -13,6 +13,8 @@ jobs:
|
||||
steps:
|
||||
- uses: actions/checkout@v5
|
||||
- uses: dtolnay/rust-toolchain@1.89
|
||||
with:
|
||||
profile: minimal
|
||||
|
||||
# Run benchmarks
|
||||
- name: Run the fuzzer
|
||||
|
||||
6
.github/workflows/publish-apt-brew-pkg.yml
vendored
6
.github/workflows/publish-apt-brew-pkg.yml
vendored
@@ -25,12 +25,6 @@ jobs:
|
||||
run: |
|
||||
apt-get update && apt-get install -y curl
|
||||
apt-get install build-essential -y
|
||||
- name: Clean space as per https://github.com/actions/virtual-environments/issues/709
|
||||
run: |
|
||||
sudo rm -rf "/opt/ghc" || true
|
||||
sudo rm -rf "/usr/share/dotnet" || true
|
||||
sudo rm -rf "/usr/local/lib/android" || true
|
||||
sudo rm -rf "/usr/local/share/boost" || true
|
||||
- uses: dtolnay/rust-toolchain@1.89
|
||||
- name: Install cargo-deb
|
||||
run: cargo install cargo-deb
|
||||
|
||||
69
.github/workflows/publish-docker-images.yml
vendored
69
.github/workflows/publish-docker-images.yml
vendored
@@ -13,6 +13,9 @@ on:
|
||||
- cron: '0 23 * * *' # Every day at 11:00pm
|
||||
workflow_dispatch:
|
||||
|
||||
env:
|
||||
REGISTRY_IMAGE: getmeili/meilisearch
|
||||
|
||||
jobs:
|
||||
build:
|
||||
runs-on: ${{ matrix.runner }}
|
||||
@@ -20,18 +23,11 @@ jobs:
|
||||
strategy:
|
||||
matrix:
|
||||
platform: [amd64, arm64]
|
||||
edition: [community, enterprise]
|
||||
include:
|
||||
- platform: amd64
|
||||
runner: ubuntu-24.04
|
||||
- platform: arm64
|
||||
runner: ubuntu-24.04-arm
|
||||
- edition: community
|
||||
registry: getmeili/meilisearch
|
||||
feature-flag: ""
|
||||
- edition: enterprise
|
||||
registry: getmeili/meilisearch-enterprise
|
||||
feature-flag: "--features enterprise"
|
||||
|
||||
permissions: {}
|
||||
steps:
|
||||
@@ -58,7 +54,7 @@ jobs:
|
||||
id: meta
|
||||
uses: docker/metadata-action@v5
|
||||
with:
|
||||
images: ${{ matrix.registry }}
|
||||
images: ${{ env.REGISTRY_IMAGE }}
|
||||
# Prevent `latest` to be updated for each new tag pushed.
|
||||
# We need latest and `vX.Y` tags to only be pushed for the stable Meilisearch releases.
|
||||
flavor: latest=false
|
||||
@@ -75,13 +71,12 @@ jobs:
|
||||
with:
|
||||
platforms: linux/${{ matrix.platform }}
|
||||
labels: ${{ steps.meta.outputs.labels }}
|
||||
tags: ${{ matrix.registry }}
|
||||
tags: ${{ env.REGISTRY_IMAGE }}
|
||||
outputs: type=image,push-by-digest=true,name-canonical=true,push=true
|
||||
build-args: |
|
||||
COMMIT_SHA=${{ github.sha }}
|
||||
COMMIT_DATE=${{ steps.build-metadata.outputs.date }}
|
||||
GIT_TAG=${{ github.ref_name }}
|
||||
EXTRA_ARGS=${{ matrix.feature-flag }}
|
||||
|
||||
- name: Export digest
|
||||
run: |
|
||||
@@ -92,21 +87,13 @@ jobs:
|
||||
- name: Upload digest
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: digests-${{ matrix.edition }}-${{ env.PLATFORM_PAIR }}
|
||||
name: digests-${{ env.PLATFORM_PAIR }}
|
||||
path: ${{ runner.temp }}/digests/*
|
||||
if-no-files-found: error
|
||||
retention-days: 1
|
||||
|
||||
merge:
|
||||
runs-on: ubuntu-latest
|
||||
strategy:
|
||||
matrix:
|
||||
edition: [community, enterprise]
|
||||
include:
|
||||
- edition: community
|
||||
registry: getmeili/meilisearch
|
||||
- edition: enterprise
|
||||
registry: getmeili/meilisearch-enterprise
|
||||
needs:
|
||||
- build
|
||||
|
||||
@@ -160,7 +147,7 @@ jobs:
|
||||
uses: actions/download-artifact@v4
|
||||
with:
|
||||
path: ${{ runner.temp }}/digests
|
||||
pattern: digests-${{ matrix.edition }}-*
|
||||
pattern: digests-*
|
||||
merge-multiple: true
|
||||
|
||||
- name: Login to Docker Hub
|
||||
@@ -176,7 +163,7 @@ jobs:
|
||||
id: meta
|
||||
uses: docker/metadata-action@v5
|
||||
with:
|
||||
images: ${{ matrix.registry }}
|
||||
images: ${{ env.REGISTRY_IMAGE }}
|
||||
# Prevent `latest` to be updated for each new tag pushed.
|
||||
# We need latest and `vX.Y` tags to only be pushed for the stable Meilisearch releases.
|
||||
flavor: latest=false
|
||||
@@ -191,11 +178,11 @@ jobs:
|
||||
working-directory: ${{ runner.temp }}/digests
|
||||
run: |
|
||||
docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
|
||||
$(printf '${{ matrix.registry }}@sha256:%s ' *)
|
||||
$(printf '${{ env.REGISTRY_IMAGE }}@sha256:%s ' *)
|
||||
|
||||
- name: Inspect image to fetch digest to sign
|
||||
- name: Inspect image
|
||||
run: |
|
||||
digest=$(docker buildx imagetools inspect --format='{{ json .Manifest }}' ${{ matrix.registry }}:${{ steps.meta.outputs.version }} | jq -r '.digest')
|
||||
digest=$(docker buildx imagetools inspect --raw ${{ env.REGISTRY_IMAGE }}:${{ steps.meta.outputs.version }} | jq -r '.manifests[0].digest')
|
||||
echo "DIGEST=${digest}" >> $GITHUB_ENV
|
||||
|
||||
- name: Sign the images with GitHub OIDC Token
|
||||
@@ -208,10 +195,10 @@ jobs:
|
||||
done
|
||||
cosign sign --yes ${images}
|
||||
|
||||
# /!\ Don't touch this without checking with engineers working on the Cloud code base on #discussion-engineering Slack channel
|
||||
- name: Notify meilisearch-cloud
|
||||
# /!\ Don't touch this without checking with Cloud team
|
||||
- name: Send CI information to Cloud team
|
||||
# Do not send if nightly build (i.e. 'schedule' or 'workflow_dispatch' event)
|
||||
if: ${{ (github.event_name == 'push') && (matrix.edition == 'enterprise') }}
|
||||
if: github.event_name == 'push'
|
||||
uses: peter-evans/repository-dispatch@v3
|
||||
with:
|
||||
token: ${{ secrets.MEILI_BOT_GH_PAT }}
|
||||
@@ -219,13 +206,21 @@ jobs:
|
||||
event-type: cloud-docker-build
|
||||
client-payload: '{ "meilisearch_version": "${{ github.ref_name }}", "stable": "${{ steps.check-tag-format.outputs.stable }}" }'
|
||||
|
||||
# /!\ Don't touch this without checking with integration team members on #discussion-integrations Slack channel
|
||||
- name: Notify meilisearch-kubernetes
|
||||
# Do not send if nightly build (i.e. 'schedule' or 'workflow_dispatch' event), or if not stable
|
||||
if: ${{ github.event_name == 'push' && matrix.edition == 'community' && steps.check-tag-format.outputs.stable == 'true' }}
|
||||
uses: peter-evans/repository-dispatch@v3
|
||||
with:
|
||||
token: ${{ secrets.MEILI_BOT_GH_PAT }}
|
||||
repository: meilisearch/meilisearch-kubernetes
|
||||
event-type: meilisearch-release
|
||||
client-payload: '{ "version": "${{ github.ref_name }}" }'
|
||||
# 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
|
||||
|
||||
184
.github/workflows/publish-release-assets.yml
vendored
184
.github/workflows/publish-release-assets.yml
vendored
@@ -32,61 +32,157 @@ jobs:
|
||||
if: github.event_name == 'release' && steps.check-tag-format.outputs.stable == 'true'
|
||||
run: bash .github/scripts/check-release.sh
|
||||
|
||||
publish-binaries:
|
||||
name: Publish binary for ${{ matrix.release }} ${{ matrix.edition }} edition
|
||||
runs-on: ${{ matrix.os }}
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
edition: [community, enterprise]
|
||||
release:
|
||||
[macos-amd64, macos-aarch64, windows, linux-amd64, linux-aarch64]
|
||||
include:
|
||||
- edition: "community"
|
||||
feature-flag: ""
|
||||
edition-suffix: ""
|
||||
- edition: "enterprise"
|
||||
feature-flag: "--features enterprise"
|
||||
edition-suffix: "enterprise-"
|
||||
- release: macos-amd64
|
||||
os: macos-15-intel
|
||||
binary_path: release/meilisearch
|
||||
asset_name: macos-amd64
|
||||
extra-args: ""
|
||||
- release: macos-aarch64
|
||||
os: macos-14
|
||||
binary_path: aarch64-apple-darwin/release/meilisearch
|
||||
asset_name: macos-apple-silicon
|
||||
extra-args: "--target aarch64-apple-darwin"
|
||||
- release: windows
|
||||
os: windows-2022
|
||||
binary_path: release/meilisearch.exe
|
||||
asset_name: windows-amd64.exe
|
||||
extra-args: ""
|
||||
- release: linux-amd64
|
||||
os: ubuntu-22.04
|
||||
binary_path: x86_64-unknown-linux-gnu/release/meilisearch
|
||||
asset_name: linux-amd64
|
||||
extra-args: "--target x86_64-unknown-linux-gnu"
|
||||
- release: linux-aarch64
|
||||
os: ubuntu-22.04-arm
|
||||
binary_path: aarch64-unknown-linux-gnu/release/meilisearch
|
||||
asset_name: linux-aarch64
|
||||
extra-args: "--target aarch64-unknown-linux-gnu"
|
||||
publish-linux:
|
||||
name: Publish binary for Linux
|
||||
runs-on: ubuntu-latest
|
||||
needs: check-version
|
||||
container:
|
||||
# Use ubuntu-22.04 to compile with glibc 2.35
|
||||
image: ubuntu:22.04
|
||||
steps:
|
||||
- uses: actions/checkout@v5
|
||||
- name: Install needed dependencies
|
||||
run: |
|
||||
apt-get update && apt-get install -y curl
|
||||
apt-get install build-essential -y
|
||||
- uses: dtolnay/rust-toolchain@1.89
|
||||
- name: Build
|
||||
run: cargo build --release --locked ${{ matrix.feature-flag }} ${{ matrix.extra-args }}
|
||||
run: cargo build --release --locked
|
||||
# No need to upload binaries for dry run (cron or workflow_dispatch)
|
||||
- name: Upload binaries to release
|
||||
if: github.event_name == 'release'
|
||||
uses: svenstaro/upload-release-action@2.11.2
|
||||
with:
|
||||
repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
|
||||
file: target/${{ matrix.binary_path }}
|
||||
asset_name: meilisearch-${{ matrix.edition-suffix }}${{ matrix.asset_name }}
|
||||
file: target/release/meilisearch
|
||||
asset_name: meilisearch-linux-amd64
|
||||
tag: ${{ github.ref }}
|
||||
|
||||
publish-macos-windows:
|
||||
name: Publish binary for ${{ matrix.os }}
|
||||
runs-on: ${{ matrix.os }}
|
||||
needs: check-version
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
os: [macos-13, windows-2022]
|
||||
include:
|
||||
- os: macos-13
|
||||
artifact_name: meilisearch
|
||||
asset_name: meilisearch-macos-amd64
|
||||
- os: windows-2022
|
||||
artifact_name: meilisearch.exe
|
||||
asset_name: meilisearch-windows-amd64.exe
|
||||
steps:
|
||||
- uses: actions/checkout@v5
|
||||
- uses: dtolnay/rust-toolchain@1.89
|
||||
- name: Build
|
||||
run: cargo build --release --locked
|
||||
# No need to upload binaries for dry run (cron or workflow_dispatch)
|
||||
- name: Upload binaries to release
|
||||
if: github.event_name == 'release'
|
||||
uses: svenstaro/upload-release-action@2.11.2
|
||||
with:
|
||||
repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
|
||||
file: target/release/${{ matrix.artifact_name }}
|
||||
asset_name: ${{ matrix.asset_name }}
|
||||
tag: ${{ github.ref }}
|
||||
|
||||
publish-macos-apple-silicon:
|
||||
name: Publish binary for macOS silicon
|
||||
runs-on: macos-13
|
||||
needs: check-version
|
||||
strategy:
|
||||
matrix:
|
||||
include:
|
||||
- target: aarch64-apple-darwin
|
||||
asset_name: meilisearch-macos-apple-silicon
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v5
|
||||
- name: Installing Rust toolchain
|
||||
uses: dtolnay/rust-toolchain@1.89
|
||||
with:
|
||||
profile: minimal
|
||||
target: ${{ matrix.target }}
|
||||
- name: Cargo build
|
||||
uses: actions-rs/cargo@v1
|
||||
with:
|
||||
command: build
|
||||
args: --release --target ${{ matrix.target }}
|
||||
- name: Upload the binary to release
|
||||
# No need to upload binaries for dry run (cron or workflow_dispatch)
|
||||
if: github.event_name == 'release'
|
||||
uses: svenstaro/upload-release-action@2.11.2
|
||||
with:
|
||||
repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
|
||||
file: target/${{ matrix.target }}/release/meilisearch
|
||||
asset_name: ${{ matrix.asset_name }}
|
||||
tag: ${{ github.ref }}
|
||||
|
||||
publish-aarch64:
|
||||
name: Publish binary for aarch64
|
||||
runs-on: ubuntu-latest
|
||||
needs: check-version
|
||||
env:
|
||||
DEBIAN_FRONTEND: noninteractive
|
||||
container:
|
||||
# Use ubuntu-22.04 to compile with glibc 2.35
|
||||
image: ubuntu:22.04
|
||||
strategy:
|
||||
matrix:
|
||||
include:
|
||||
- target: aarch64-unknown-linux-gnu
|
||||
asset_name: meilisearch-linux-aarch64
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v5
|
||||
- name: Install needed dependencies
|
||||
run: |
|
||||
apt-get update -y && apt upgrade -y
|
||||
apt-get install -y curl build-essential gcc-aarch64-linux-gnu
|
||||
- name: Set up Docker for cross compilation
|
||||
run: |
|
||||
apt-get install -y curl apt-transport-https ca-certificates software-properties-common
|
||||
curl -fsSL https://download.docker.com/linux/ubuntu/gpg | apt-key add -
|
||||
add-apt-repository "deb [arch=$(dpkg --print-architecture)] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable"
|
||||
apt-get update -y && apt-get install -y docker-ce
|
||||
- name: Installing Rust toolchain
|
||||
uses: dtolnay/rust-toolchain@1.89
|
||||
with:
|
||||
profile: minimal
|
||||
target: ${{ matrix.target }}
|
||||
- name: Configure target aarch64 GNU
|
||||
## Environment variable is not passed using env:
|
||||
## LD gold won't work with MUSL
|
||||
# env:
|
||||
# JEMALLOC_SYS_WITH_LG_PAGE: 16
|
||||
# RUSTFLAGS: '-Clink-arg=-fuse-ld=gold'
|
||||
run: |
|
||||
echo '[target.aarch64-unknown-linux-gnu]' >> ~/.cargo/config
|
||||
echo 'linker = "aarch64-linux-gnu-gcc"' >> ~/.cargo/config
|
||||
echo 'JEMALLOC_SYS_WITH_LG_PAGE=16' >> $GITHUB_ENV
|
||||
- name: Install a default toolchain that will be used to build cargo cross
|
||||
run: |
|
||||
rustup default stable
|
||||
- name: Cargo build
|
||||
uses: actions-rs/cargo@v1
|
||||
with:
|
||||
command: build
|
||||
use-cross: true
|
||||
args: --release --target ${{ matrix.target }}
|
||||
env:
|
||||
CROSS_DOCKER_IN_DOCKER: true
|
||||
- name: List target output files
|
||||
run: ls -lR ./target
|
||||
- name: Upload the binary to release
|
||||
# No need to upload binaries for dry run (cron or workflow_dispatch)
|
||||
if: github.event_name == 'release'
|
||||
uses: svenstaro/upload-release-action@2.11.2
|
||||
with:
|
||||
repo_token: ${{ secrets.MEILI_BOT_GH_PAT }}
|
||||
file: target/${{ matrix.target }}/release/meilisearch
|
||||
asset_name: ${{ matrix.asset_name }}
|
||||
tag: ${{ github.ref }}
|
||||
|
||||
publish-openapi-file:
|
||||
|
||||
24
.github/workflows/sdks-tests.yml
vendored
24
.github/workflows/sdks-tests.yml
vendored
@@ -68,7 +68,7 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
services:
|
||||
meilisearch:
|
||||
image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
env:
|
||||
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
|
||||
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
|
||||
@@ -92,7 +92,7 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
services:
|
||||
meilisearch:
|
||||
image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
env:
|
||||
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
|
||||
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
|
||||
@@ -122,7 +122,7 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
services:
|
||||
meilisearch:
|
||||
image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
env:
|
||||
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
|
||||
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
|
||||
@@ -149,7 +149,7 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
services:
|
||||
meilisearch:
|
||||
image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
env:
|
||||
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
|
||||
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
|
||||
@@ -184,7 +184,7 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
services:
|
||||
meilisearch:
|
||||
image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
env:
|
||||
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
|
||||
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
|
||||
@@ -213,7 +213,7 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
services:
|
||||
meilisearch:
|
||||
image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
env:
|
||||
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
|
||||
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
|
||||
@@ -238,7 +238,7 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
services:
|
||||
meilisearch:
|
||||
image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
env:
|
||||
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
|
||||
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
|
||||
@@ -263,7 +263,7 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
services:
|
||||
meilisearch:
|
||||
image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
env:
|
||||
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
|
||||
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
|
||||
@@ -284,7 +284,7 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
services:
|
||||
meilisearch:
|
||||
image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
env:
|
||||
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
|
||||
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
|
||||
@@ -307,7 +307,7 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
services:
|
||||
meilisearch:
|
||||
image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
env:
|
||||
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
|
||||
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
|
||||
@@ -338,7 +338,7 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
services:
|
||||
meilisearch:
|
||||
image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
env:
|
||||
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
|
||||
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
|
||||
@@ -370,7 +370,7 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
services:
|
||||
meilisearch:
|
||||
image: getmeili/meilisearch-enterprise:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
image: getmeili/meilisearch:${{ needs.define-docker-image.outputs.docker-image }}
|
||||
env:
|
||||
MEILI_MASTER_KEY: ${{ env.MEILI_MASTER_KEY }}
|
||||
MEILI_NO_ANALYTICS: ${{ env.MEILI_NO_ANALYTICS }}
|
||||
|
||||
150
.github/workflows/test-suite.yml
vendored
150
.github/workflows/test-suite.yml
vendored
@@ -15,40 +15,31 @@ env:
|
||||
|
||||
jobs:
|
||||
test-linux:
|
||||
name: Tests on Ubuntu
|
||||
runs-on: ${{ matrix.runner }}
|
||||
strategy:
|
||||
matrix:
|
||||
runner: [ubuntu-22.04, ubuntu-22.04-arm]
|
||||
features: ["", "--features enterprise"]
|
||||
name: Tests on ubuntu-22.04
|
||||
runs-on: ubuntu-latest
|
||||
container:
|
||||
# Use ubuntu-22.04 to compile with glibc 2.35
|
||||
image: ubuntu:22.04
|
||||
steps:
|
||||
- uses: actions/checkout@v5
|
||||
- name: check free space before
|
||||
run: df -h
|
||||
- name: Clean space as per https://github.com/actions/virtual-environments/issues/709
|
||||
- name: Install needed dependencies
|
||||
run: |
|
||||
sudo rm -rf "/opt/ghc" || true
|
||||
sudo rm -rf "/usr/share/dotnet" || true
|
||||
sudo rm -rf "/usr/local/lib/android" || true
|
||||
sudo rm -rf "/usr/local/share/boost" || true
|
||||
- name: check free space after
|
||||
run: df -h
|
||||
apt-get update && apt-get install -y curl
|
||||
apt-get install build-essential -y
|
||||
- name: Setup test with Rust stable
|
||||
uses: dtolnay/rust-toolchain@1.89
|
||||
- name: Cache dependencies
|
||||
uses: Swatinem/rust-cache@v2.8.0
|
||||
with:
|
||||
key: ${{ matrix.features }}
|
||||
- name: Run cargo build without any default features
|
||||
- name: Run cargo check without any default features
|
||||
uses: actions-rs/cargo@v1
|
||||
with:
|
||||
command: build
|
||||
args: --locked --no-default-features --all
|
||||
args: --locked --release --no-default-features --all
|
||||
- name: Run cargo test
|
||||
uses: actions-rs/cargo@v1
|
||||
with:
|
||||
command: test
|
||||
args: --locked --all ${{ matrix.features }}
|
||||
args: --locked --release --all
|
||||
|
||||
test-others:
|
||||
name: Tests on ${{ matrix.os }}
|
||||
@@ -56,58 +47,51 @@ jobs:
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
os: [macos-14, windows-2022]
|
||||
features: ["", "--features enterprise"]
|
||||
if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
|
||||
os: [macos-13, windows-2022]
|
||||
steps:
|
||||
- uses: actions/checkout@v5
|
||||
- name: Cache dependencies
|
||||
uses: Swatinem/rust-cache@v2.8.0
|
||||
- uses: dtolnay/rust-toolchain@1.89
|
||||
- name: Run cargo build without any default features
|
||||
- name: Run cargo check without any default features
|
||||
uses: actions-rs/cargo@v1
|
||||
with:
|
||||
command: build
|
||||
args: --locked --no-default-features --all
|
||||
args: --locked --release --no-default-features --all
|
||||
- name: Run cargo test
|
||||
uses: actions-rs/cargo@v1
|
||||
with:
|
||||
command: test
|
||||
args: --locked --all ${{ matrix.features }}
|
||||
args: --locked --release --all
|
||||
|
||||
test-all-features:
|
||||
name: Tests almost all features
|
||||
runs-on: ubuntu-22.04
|
||||
runs-on: ubuntu-latest
|
||||
container:
|
||||
# Use ubuntu-22.04 to compile with glibc 2.35
|
||||
image: ubuntu:22.04
|
||||
if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
|
||||
steps:
|
||||
- uses: actions/checkout@v5
|
||||
- name: Clean space as per https://github.com/actions/virtual-environments/issues/709
|
||||
- name: Install needed dependencies
|
||||
run: |
|
||||
sudo rm -rf "/opt/ghc" || true
|
||||
sudo rm -rf "/usr/share/dotnet" || true
|
||||
sudo rm -rf "/usr/local/lib/android" || true
|
||||
sudo rm -rf "/usr/local/share/boost" || true
|
||||
apt-get update
|
||||
apt-get install --assume-yes build-essential curl
|
||||
- uses: dtolnay/rust-toolchain@1.89
|
||||
- name: Run cargo build with almost all features
|
||||
run: |
|
||||
cargo build --workspace --locked --features "$(cargo xtask list-features --exclude-feature cuda,test-ollama)"
|
||||
cargo build --workspace --locked --release --features "$(cargo xtask list-features --exclude-feature cuda,test-ollama)"
|
||||
- name: Run cargo test with almost all features
|
||||
run: |
|
||||
cargo test --workspace --locked --features "$(cargo xtask list-features --exclude-feature cuda,test-ollama)"
|
||||
cargo test --workspace --locked --release --features "$(cargo xtask list-features --exclude-feature cuda,test-ollama)"
|
||||
|
||||
ollama-ubuntu:
|
||||
name: Test with Ollama
|
||||
runs-on: ubuntu-22.04
|
||||
runs-on: ubuntu-latest
|
||||
env:
|
||||
MEILI_TEST_OLLAMA_SERVER: "http://localhost:11434"
|
||||
steps:
|
||||
- uses: actions/checkout@v5
|
||||
- name: Clean space as per https://github.com/actions/virtual-environments/issues/709
|
||||
run: |
|
||||
sudo rm -rf "/opt/ghc" || true
|
||||
sudo rm -rf "/usr/share/dotnet" || true
|
||||
sudo rm -rf "/usr/local/lib/android" || true
|
||||
sudo rm -rf "/usr/local/share/boost" || true
|
||||
- name: Install Ollama
|
||||
run: |
|
||||
curl -fsSL https://ollama.com/install.sh | sudo -E sh
|
||||
@@ -131,20 +115,20 @@ jobs:
|
||||
uses: actions-rs/cargo@v1
|
||||
with:
|
||||
command: test
|
||||
args: --locked -p meilisearch --features test-ollama ollama
|
||||
args: --locked --release --all --features test-ollama ollama
|
||||
|
||||
test-disabled-tokenization:
|
||||
name: Test disabled tokenization
|
||||
runs-on: ubuntu-22.04
|
||||
runs-on: ubuntu-latest
|
||||
container:
|
||||
image: ubuntu:22.04
|
||||
if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
|
||||
steps:
|
||||
- uses: actions/checkout@v5
|
||||
- name: Clean space as per https://github.com/actions/virtual-environments/issues/709
|
||||
- name: Install needed dependencies
|
||||
run: |
|
||||
sudo rm -rf "/opt/ghc" || true
|
||||
sudo rm -rf "/usr/share/dotnet" || true
|
||||
sudo rm -rf "/usr/local/lib/android" || true
|
||||
sudo rm -rf "/usr/local/share/boost" || true
|
||||
apt-get update
|
||||
apt-get install --assume-yes build-essential curl
|
||||
- uses: dtolnay/rust-toolchain@1.89
|
||||
- name: Run cargo tree without default features and check lindera is not present
|
||||
run: |
|
||||
@@ -156,39 +140,36 @@ jobs:
|
||||
run: |
|
||||
cargo tree -f '{p} {f}' -e normal | grep lindera -qz
|
||||
|
||||
build:
|
||||
name: Build in release
|
||||
runs-on: ubuntu-22.04
|
||||
# We run tests in debug also, to make sure that the debug_assertions are hit
|
||||
test-debug:
|
||||
name: Run tests in debug
|
||||
runs-on: ubuntu-latest
|
||||
container:
|
||||
# Use ubuntu-22.04 to compile with glibc 2.35
|
||||
image: ubuntu:22.04
|
||||
steps:
|
||||
- uses: actions/checkout@v5
|
||||
- name: Clean space as per https://github.com/actions/virtual-environments/issues/709
|
||||
- name: Install needed dependencies
|
||||
run: |
|
||||
sudo rm -rf "/opt/ghc" || true
|
||||
sudo rm -rf "/usr/share/dotnet" || true
|
||||
sudo rm -rf "/usr/local/lib/android" || true
|
||||
sudo rm -rf "/usr/local/share/boost" || true
|
||||
apt-get update && apt-get install -y curl
|
||||
apt-get install build-essential -y
|
||||
- uses: dtolnay/rust-toolchain@1.89
|
||||
- name: Cache dependencies
|
||||
uses: Swatinem/rust-cache@v2.8.0
|
||||
- name: Build
|
||||
run: cargo build --release --locked --target x86_64-unknown-linux-gnu
|
||||
- name: Run tests in debug
|
||||
uses: actions-rs/cargo@v1
|
||||
with:
|
||||
command: test
|
||||
args: --locked --all
|
||||
|
||||
clippy:
|
||||
name: Run Clippy
|
||||
runs-on: ubuntu-22.04
|
||||
strategy:
|
||||
matrix:
|
||||
features: ["", "--features enterprise"]
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v5
|
||||
- name: Clean space as per https://github.com/actions/virtual-environments/issues/709
|
||||
run: |
|
||||
sudo rm -rf "/opt/ghc" || true
|
||||
sudo rm -rf "/usr/share/dotnet" || true
|
||||
sudo rm -rf "/usr/local/lib/android" || true
|
||||
sudo rm -rf "/usr/local/share/boost" || true
|
||||
- uses: dtolnay/rust-toolchain@1.89
|
||||
with:
|
||||
profile: minimal
|
||||
components: clippy
|
||||
- name: Cache dependencies
|
||||
uses: Swatinem/rust-cache@v2.8.0
|
||||
@@ -196,21 +177,18 @@ jobs:
|
||||
uses: actions-rs/cargo@v1
|
||||
with:
|
||||
command: clippy
|
||||
args: --all-targets ${{ matrix.features }} -- --deny warnings
|
||||
args: --all-targets -- --deny warnings
|
||||
|
||||
fmt:
|
||||
name: Run Rustfmt
|
||||
runs-on: ubuntu-22.04
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v5
|
||||
- name: Clean space as per https://github.com/actions/virtual-environments/issues/709
|
||||
run: |
|
||||
sudo rm -rf "/opt/ghc" || true
|
||||
sudo rm -rf "/usr/share/dotnet" || true
|
||||
sudo rm -rf "/usr/local/lib/android" || true
|
||||
sudo rm -rf "/usr/local/share/boost" || true
|
||||
- uses: dtolnay/rust-toolchain@1.89
|
||||
with:
|
||||
profile: minimal
|
||||
toolchain: nightly-2024-07-09
|
||||
override: true
|
||||
components: rustfmt
|
||||
- name: Cache dependencies
|
||||
uses: Swatinem/rust-cache@v2.8.0
|
||||
@@ -221,23 +199,3 @@ jobs:
|
||||
run: |
|
||||
echo -ne "\n" > crates/benchmarks/benches/datasets_paths.rs
|
||||
cargo fmt --all -- --check
|
||||
|
||||
declarative-tests:
|
||||
name: Run declarative tests
|
||||
runs-on: ubuntu-22.04-arm
|
||||
permissions:
|
||||
contents: read
|
||||
steps:
|
||||
- uses: actions/checkout@v5
|
||||
- name: Clean space as per https://github.com/actions/virtual-environments/issues/709
|
||||
run: |
|
||||
sudo rm -rf "/opt/ghc" || true
|
||||
sudo rm -rf "/usr/share/dotnet" || true
|
||||
sudo rm -rf "/usr/local/lib/android" || true
|
||||
sudo rm -rf "/usr/local/share/boost" || true
|
||||
- uses: dtolnay/rust-toolchain@1.89
|
||||
- name: Cache dependencies
|
||||
uses: Swatinem/rust-cache@v2.8.0
|
||||
- name: Run declarative tests
|
||||
run: |
|
||||
cargo xtask test workloads/tests/*.json
|
||||
|
||||
@@ -18,13 +18,9 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v5
|
||||
- name: Clean space as per https://github.com/actions/virtual-environments/issues/709
|
||||
run: |
|
||||
sudo rm -rf "/opt/ghc" || true
|
||||
sudo rm -rf "/usr/share/dotnet" || true
|
||||
sudo rm -rf "/usr/local/lib/android" || true
|
||||
sudo rm -rf "/usr/local/share/boost" || true
|
||||
- uses: dtolnay/rust-toolchain@1.89
|
||||
with:
|
||||
profile: minimal
|
||||
- name: Install sd
|
||||
run: cargo install sd
|
||||
- name: Update Cargo.toml file
|
||||
|
||||
@@ -124,7 +124,6 @@ They are JSON files with the following structure (comments are not actually supp
|
||||
{
|
||||
// Name of the workload. Must be unique to the workload, as it will be used to group results on the dashboard.
|
||||
"name": "hackernews.ndjson_1M,no-threads",
|
||||
"type": "bench",
|
||||
// Number of consecutive runs of the commands that should be performed.
|
||||
// Each run uses a fresh instance of Meilisearch and a fresh database.
|
||||
// Each run produces its own report file.
|
||||
|
||||
1183
Cargo.lock
generated
1183
Cargo.lock
generated
File diff suppressed because it is too large
Load Diff
@@ -23,7 +23,7 @@ members = [
|
||||
]
|
||||
|
||||
[workspace.package]
|
||||
version = "1.29.0"
|
||||
version = "1.26.0"
|
||||
authors = [
|
||||
"Quentin de Quelen <quentin@dequelen.me>",
|
||||
"Clément Renault <clement@meilisearch.com>",
|
||||
@@ -50,5 +50,3 @@ opt-level = 3
|
||||
opt-level = 3
|
||||
[profile.dev.package.roaring]
|
||||
opt-level = 3
|
||||
[profile.dev.package.gemm-f16]
|
||||
opt-level = 3
|
||||
|
||||
7
Cross.toml
Normal file
7
Cross.toml
Normal file
@@ -0,0 +1,7 @@
|
||||
[build.env]
|
||||
passthrough = [
|
||||
"RUST_BACKTRACE",
|
||||
"CARGO_TERM_COLOR",
|
||||
"RUSTFLAGS",
|
||||
"JEMALLOC_SYS_WITH_LG_PAGE"
|
||||
]
|
||||
@@ -8,14 +8,16 @@ WORKDIR /
|
||||
ARG COMMIT_SHA
|
||||
ARG COMMIT_DATE
|
||||
ARG GIT_TAG
|
||||
ARG EXTRA_ARGS
|
||||
ENV VERGEN_GIT_SHA=${COMMIT_SHA} VERGEN_GIT_COMMIT_TIMESTAMP=${COMMIT_DATE} VERGEN_GIT_DESCRIBE=${GIT_TAG}
|
||||
ENV RUSTFLAGS="-C target-feature=-crt-static"
|
||||
|
||||
COPY . .
|
||||
RUN set -eux; \
|
||||
apkArch="$(apk --print-arch)"; \
|
||||
cargo build --release -p meilisearch -p meilitool ${EXTRA_ARGS}
|
||||
if [ "$apkArch" = "aarch64" ]; then \
|
||||
export JEMALLOC_SYS_WITH_LG_PAGE=16; \
|
||||
fi && \
|
||||
cargo build --release -p meilisearch -p meilitool
|
||||
|
||||
# Run
|
||||
FROM alpine:3.22
|
||||
|
||||
326
TESTING.md
326
TESTING.md
@@ -1,326 +0,0 @@
|
||||
# Declarative tests
|
||||
|
||||
Declarative tests ensure that Meilisearch features remain stable across versions.
|
||||
|
||||
While we already have unit tests, those are run against **temporary databases** that are created fresh each time and therefore never risk corruption.
|
||||
|
||||
Declarative tests instead **simulate the lifetime of a database**: they chain together commands and requests to change the binary, verifying that database state and API responses remain consistent.
|
||||
|
||||
## Basic example
|
||||
|
||||
```jsonc
|
||||
{
|
||||
"type": "test",
|
||||
"name": "api-keys",
|
||||
"binary": { // the first command will run on the binary following this specification.
|
||||
"source": "release", // get the binary as a release from GitHub
|
||||
"version": "1.19.0", // version to fetch
|
||||
"edition": "community" // edition to fetch
|
||||
},
|
||||
"commands": []
|
||||
}
|
||||
```
|
||||
|
||||
This example defines a no-op test (it does nothing).
|
||||
|
||||
If the file is saved at `workloads/tests/example.json`, you can run it with:
|
||||
|
||||
```bash
|
||||
cargo xtask test workloads/tests/example.json
|
||||
```
|
||||
|
||||
## Commands
|
||||
|
||||
Commands represent API requests sent to Meilisearch endpoints during a test.
|
||||
|
||||
They are executed sequentially, and their responses can be validated to ensure consistent behavior across upgrades.
|
||||
|
||||
```jsonc
|
||||
|
||||
{
|
||||
"route": "keys",
|
||||
"method": "POST",
|
||||
"body": {
|
||||
"inline": {
|
||||
"actions": [
|
||||
"search",
|
||||
"documents.add"
|
||||
],
|
||||
"description": "Test API Key",
|
||||
"expiresAt": null,
|
||||
"indexes": [ "movies" ]
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
This command issues a `POST /keys` request, creating an API key with permissions to search and add documents in the `movies` index.
|
||||
|
||||
### Using assets in commands
|
||||
|
||||
To keep tests concise and reusable, you can define **assets** at the root of the workload file.
|
||||
|
||||
Assets are external data sources (such as datasets) that are cached between runs, making tests faster and easier to read.
|
||||
|
||||
```jsonc
|
||||
{
|
||||
"type": "test",
|
||||
"name": "movies",
|
||||
"binary": {
|
||||
"source": "release",
|
||||
"version": "1.19.0",
|
||||
"edition": "community"
|
||||
},
|
||||
"assets": {
|
||||
"movies.json": {
|
||||
"local_location": null,
|
||||
"remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/movies.json",
|
||||
"sha256": "5b6e4cb660bc20327776e8a33ea197b43d9ec84856710ead1cc87ab24df77de1"
|
||||
}
|
||||
},
|
||||
"commands": [
|
||||
{
|
||||
"route": "indexes/movies/documents",
|
||||
"method": "POST",
|
||||
"body": {
|
||||
"asset": "movies.json"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
In this example:
|
||||
- The `movies.json` dataset is defined as an asset, pointing to a remote URL.
|
||||
- The SHA-256 checksum ensures integrity.
|
||||
- The `POST /indexes/movies/documents` command uses this asset as the request body.
|
||||
|
||||
This makes the test much cleaner than inlining a large dataset directly into the command.
|
||||
|
||||
For asset handling, please refer to the [declarative benchmarks documentation](/BENCHMARKS.md#adding-new-assets).
|
||||
|
||||
### Asserting responses
|
||||
|
||||
Commands can specify both the **expected status code** and the **expected response body**.
|
||||
|
||||
```jsonc
|
||||
{
|
||||
"route": "indexes/movies/documents",
|
||||
"method": "POST",
|
||||
"body": {
|
||||
"asset": "movies.json"
|
||||
},
|
||||
"expectedStatus": 202,
|
||||
"expectedResponse": {
|
||||
"enqueuedAt": "[timestamp]", // Set to a bracketed string to ignore the value
|
||||
"indexUid": "movies",
|
||||
"status": "enqueued",
|
||||
"taskUid": 1,
|
||||
"type": "documentAdditionOrUpdate"
|
||||
},
|
||||
"synchronous": "WaitForTask"
|
||||
}
|
||||
```
|
||||
|
||||
Manually writing `expectedResponse` fields can be tedious.
|
||||
|
||||
Instead, you can let the test runner populate them automatically:
|
||||
|
||||
```bash
|
||||
# Run the workload to populate expected fields. Only adds the missing ones, doesn't change existing data
|
||||
cargo xtask test workloads/tests/example.json --add-missing-responses
|
||||
|
||||
# OR
|
||||
|
||||
# Run the workload to populate expected fields. Updates all fields including existing ones
|
||||
cargo xtask test workloads/tests/example.json --update-responses
|
||||
```
|
||||
|
||||
This workflow is recommended:
|
||||
|
||||
1. Write the test without expected fields.
|
||||
2. Run it with `--add-missing-responses` to capture the actual responses.
|
||||
3. Review and commit the generated expectations.
|
||||
|
||||
## Changing binary
|
||||
|
||||
It is possible to insert an instruction to change the current Meilisearch instance from one binary specification to another during a test.
|
||||
|
||||
When executed, such an instruction will:
|
||||
1. Stop the current Meilisearch instance.
|
||||
2. Fetch the binary specified by the instruction.
|
||||
3. Restart the server with the specified binary on the same database.
|
||||
|
||||
```jsonc
|
||||
{
|
||||
"type": "test",
|
||||
"name": "movies",
|
||||
"binary": {
|
||||
"source": "release",
|
||||
"version": "1.19.0", // start with version v1.19.0
|
||||
"edition": "community"
|
||||
},
|
||||
"assets": {
|
||||
"movies.json": {
|
||||
"local_location": null,
|
||||
"remote_location": "https://milli-benchmarks.fra1.digitaloceanspaces.com/bench/datasets/movies.json",
|
||||
"sha256": "5b6e4cb660bc20327776e8a33ea197b43d9ec84856710ead1cc87ab24df77de1"
|
||||
}
|
||||
},
|
||||
"commands": [
|
||||
// setup some data
|
||||
{
|
||||
"route": "indexes/movies/documents",
|
||||
"method": "POST",
|
||||
"body": {
|
||||
"asset": "movies.json"
|
||||
}
|
||||
},
|
||||
// switch binary to v1.24.0
|
||||
{
|
||||
"binary": {
|
||||
"source": "release",
|
||||
"version": "1.24.0",
|
||||
"edition": "community"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
### Typical Usage
|
||||
|
||||
In most cases, the change binary instruction will be used to update a database.
|
||||
|
||||
- **Set up** some data using commands on an older version.
|
||||
- **Upgrade** to the latest version.
|
||||
- **Assert** that the data and API behavior remain correct after the upgrade.
|
||||
|
||||
To properly test the dumpless upgrade, one should typically:
|
||||
|
||||
1. Open the database without processing the update task: Use a `binary` instruction to switch to the desired version, passing `--experimental-dumpless-upgrade` and `--experimental-max-number-of-batched-tasks=0` as extra CLI arguments
|
||||
2. Check that the search, stats and task queue still work.
|
||||
3. Open the database and process the update task: Use a `binary` instruction to switch to the desired version, passing `--experimental-dumpless-upgrade` as the extra CLI argument. Use a `health` command to wait for the upgrade task to finish.
|
||||
4. Check that the indexing, search, stats, and task queue still work.
|
||||
|
||||
```jsonc
|
||||
{
|
||||
"type": "test",
|
||||
"name": "movies",
|
||||
"binary": {
|
||||
"source": "release",
|
||||
"version": "1.12.0",
|
||||
"edition": "community"
|
||||
},
|
||||
"commands": [
|
||||
// 0. Run commands to populate the database
|
||||
{
|
||||
// ..
|
||||
},
|
||||
// 1. Open the database with new MS without processing the update task
|
||||
{
|
||||
"binary": {
|
||||
"source": "build", // build the binary from the sources in the current git repository
|
||||
"edition": "community",
|
||||
"extraCliArgs": [
|
||||
"--experimental-dumpless-upgrade", // allows to open with a newer MS
|
||||
"--experimental-max-number-of-batched-tasks=0" // prevent processing of the update task
|
||||
]
|
||||
}
|
||||
},
|
||||
// 2. Check the search etc.
|
||||
{
|
||||
// ..
|
||||
},
|
||||
// 3. Open the database with new MS and processing the update task
|
||||
{
|
||||
"binary": {
|
||||
"source": "build", // build the binary from the sources in the current git repository
|
||||
"edition": "community",
|
||||
"extraCliArgs": [
|
||||
"--experimental-dumpless-upgrade" // allows to open with a newer MS
|
||||
// no `--experimental-max-number-of-batched-tasks=0`
|
||||
]
|
||||
}
|
||||
},
|
||||
// 4. Check the indexing, search, etc.
|
||||
{
|
||||
// ..
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
This ensures backward compatibility: databases created with older Meilisearch versions should remain functional and consistent after an upgrade.
|
||||
|
||||
## Variables
|
||||
|
||||
Sometimes a command needs to use a value returned by a **previous response**.
|
||||
These values can be captured and reused using the register field.
|
||||
|
||||
```jsonc
|
||||
{
|
||||
"route": "keys",
|
||||
"method": "POST",
|
||||
"body": {
|
||||
"inline": {
|
||||
"actions": [
|
||||
"search",
|
||||
"documents.add"
|
||||
],
|
||||
"description": "Test API Key",
|
||||
"expiresAt": null,
|
||||
"indexes": [ "movies" ]
|
||||
}
|
||||
},
|
||||
"expectedResponse": {
|
||||
"key": "c6f64630bad2996b1f675007c8800168e14adf5d6a7bb1a400a6d2b158050eaf",
|
||||
// ...
|
||||
},
|
||||
"register": {
|
||||
"key": "/key"
|
||||
},
|
||||
"synchronous": "WaitForResponse"
|
||||
}
|
||||
```
|
||||
|
||||
The `register` field captures the value at the JSON path `/key` from the response.
|
||||
Paths follow the **JavaScript Object Notation Pointer (RFC 6901)** format.
|
||||
Registered variables are available for all subsequent commands.
|
||||
|
||||
Registered variables can be referenced by wrapping their name in double curly braces:
|
||||
|
||||
In the route/path:
|
||||
|
||||
```jsonc
|
||||
{
|
||||
"route": "tasks/{{ task_id }}",
|
||||
"method": "GET"
|
||||
}
|
||||
```
|
||||
|
||||
In the request body:
|
||||
|
||||
```jsonc
|
||||
{
|
||||
"route": "indexes/movies/documents",
|
||||
"method": "PATCH",
|
||||
"body": {
|
||||
"inline": {
|
||||
"id": "{{ document_id }}",
|
||||
"overview": "Shazam turns evil and the world is in danger.",
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Or they can be referenced by their name (**without curly braces**) as an API key:
|
||||
|
||||
```jsonc
|
||||
{
|
||||
"route": "indexes/movies/documents",
|
||||
"method": "POST",
|
||||
"body": { /* ... */ },
|
||||
"apiKeyVariable": "key" // The **content** of the key variable will be used as an API key
|
||||
}
|
||||
```
|
||||
@@ -11,27 +11,27 @@ edition.workspace = true
|
||||
license.workspace = true
|
||||
|
||||
[dependencies]
|
||||
anyhow = "1.0.100"
|
||||
bumpalo = "3.19.0"
|
||||
csv = "1.4.0"
|
||||
memmap2 = "0.9.9"
|
||||
anyhow = "1.0.98"
|
||||
bumpalo = "3.18.1"
|
||||
csv = "1.3.1"
|
||||
memmap2 = "0.9.7"
|
||||
milli = { path = "../milli" }
|
||||
mimalloc = { version = "0.1.48", default-features = false }
|
||||
serde_json = { version = "1.0.145", features = ["preserve_order"] }
|
||||
tempfile = "3.23.0"
|
||||
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 = "0.7.0", features = ["html_reports"] }
|
||||
criterion = { version = "0.6.0", features = ["html_reports"] }
|
||||
rand = "0.8.5"
|
||||
rand_chacha = "0.3.1"
|
||||
roaring = "0.10.12"
|
||||
|
||||
[build-dependencies]
|
||||
anyhow = "1.0.100"
|
||||
bytes = "1.11.0"
|
||||
convert_case = "0.9.0"
|
||||
flate2 = "1.1.5"
|
||||
reqwest = { version = "0.12.24", 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"]
|
||||
|
||||
@@ -21,10 +21,6 @@ use roaring::RoaringBitmap;
|
||||
#[global_allocator]
|
||||
static ALLOC: mimalloc::MiMalloc = mimalloc::MiMalloc;
|
||||
|
||||
fn no_cancel() -> bool {
|
||||
false
|
||||
}
|
||||
|
||||
const BENCHMARK_ITERATION: usize = 10;
|
||||
|
||||
fn setup_dir(path: impl AsRef<Path>) {
|
||||
@@ -69,7 +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(&no_cancel, &Progress::default(), Default::default()).unwrap();
|
||||
builder.execute(&|| false, &Progress::default(), Default::default()).unwrap();
|
||||
}
|
||||
|
||||
fn setup_index_with_settings(
|
||||
@@ -156,7 +152,7 @@ fn indexing_songs_default(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -172,7 +168,7 @@ fn indexing_songs_default(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -224,7 +220,7 @@ fn reindexing_songs_default(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -240,7 +236,7 @@ fn reindexing_songs_default(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -270,7 +266,7 @@ fn reindexing_songs_default(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -286,7 +282,7 @@ fn reindexing_songs_default(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -340,7 +336,7 @@ fn deleting_songs_in_batches_default(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -356,7 +352,7 @@ fn deleting_songs_in_batches_default(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -418,7 +414,7 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -434,7 +430,7 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -464,7 +460,7 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -480,7 +476,7 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -506,7 +502,7 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -522,7 +518,7 @@ fn indexing_songs_in_three_batches_default(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -575,7 +571,7 @@ fn indexing_songs_without_faceted_numbers(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -591,7 +587,7 @@ fn indexing_songs_without_faceted_numbers(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -643,7 +639,7 @@ fn indexing_songs_without_faceted_fields(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -659,7 +655,7 @@ fn indexing_songs_without_faceted_fields(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -711,7 +707,7 @@ fn indexing_wiki(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -727,7 +723,7 @@ fn indexing_wiki(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -778,7 +774,7 @@ fn reindexing_wiki(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -794,7 +790,7 @@ fn reindexing_wiki(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -824,7 +820,7 @@ fn reindexing_wiki(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -840,7 +836,7 @@ fn reindexing_wiki(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -893,7 +889,7 @@ fn deleting_wiki_in_batches_default(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -909,7 +905,7 @@ fn deleting_wiki_in_batches_default(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -971,7 +967,7 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -987,7 +983,7 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -1018,7 +1014,7 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -1034,7 +1030,7 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -1061,7 +1057,7 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -1077,7 +1073,7 @@ fn indexing_wiki_in_three_batches(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -1129,7 +1125,7 @@ fn indexing_movies_default(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -1145,7 +1141,7 @@ fn indexing_movies_default(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -1196,7 +1192,7 @@ fn reindexing_movies_default(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -1212,7 +1208,7 @@ fn reindexing_movies_default(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -1242,7 +1238,7 @@ fn reindexing_movies_default(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -1258,7 +1254,7 @@ fn reindexing_movies_default(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -1311,7 +1307,7 @@ fn deleting_movies_in_batches_default(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -1327,7 +1323,7 @@ fn deleting_movies_in_batches_default(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -1376,7 +1372,7 @@ fn delete_documents_from_ids(index: Index, document_ids_to_delete: Vec<RoaringBi
|
||||
Some(primary_key),
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -1426,7 +1422,7 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -1442,7 +1438,7 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -1472,7 +1468,7 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -1488,7 +1484,7 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -1514,7 +1510,7 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -1530,7 +1526,7 @@ fn indexing_movies_in_three_batches(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -1605,7 +1601,7 @@ fn indexing_nested_movies_default(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -1621,7 +1617,7 @@ fn indexing_nested_movies_default(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -1697,7 +1693,7 @@ fn deleting_nested_movies_in_batches_default(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -1713,7 +1709,7 @@ fn deleting_nested_movies_in_batches_default(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -1781,7 +1777,7 @@ fn indexing_nested_movies_without_faceted_fields(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -1797,7 +1793,7 @@ fn indexing_nested_movies_without_faceted_fields(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -1849,7 +1845,7 @@ fn indexing_geo(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -1865,7 +1861,7 @@ fn indexing_geo(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -1916,7 +1912,7 @@ fn reindexing_geo(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -1932,7 +1928,7 @@ fn reindexing_geo(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -1962,7 +1958,7 @@ fn reindexing_geo(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -1978,7 +1974,7 @@ fn reindexing_geo(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -2031,7 +2027,7 @@ fn deleting_geo_in_batches_default(c: &mut Criterion) {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -2047,7 +2043,7 @@ fn deleting_geo_in_batches_default(c: &mut Criterion) {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
|
||||
@@ -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 = "0.3.44", features = ["parsing"] }
|
||||
time = { version = "0.3.41", features = ["parsing"] }
|
||||
|
||||
[build-dependencies]
|
||||
anyhow = "1.0.100"
|
||||
vergen-gitcl = "1.0.8"
|
||||
anyhow = "1.0.98"
|
||||
vergen-git2 = "1.0.7"
|
||||
|
||||
@@ -15,7 +15,7 @@ fn emit_git_variables() -> anyhow::Result<()> {
|
||||
// Note: any code that needs VERGEN_ environment variables should take care to define them manually in the Dockerfile and pass them
|
||||
// in the corresponding GitHub workflow (publish_docker.yml).
|
||||
// This is due to the Dockerfile building the binary outside of the git directory.
|
||||
let mut builder = vergen_gitcl::GitclBuilder::default();
|
||||
let mut builder = vergen_git2::Git2Builder::default();
|
||||
|
||||
builder.branch(true);
|
||||
builder.commit_timestamp(true);
|
||||
@@ -25,5 +25,5 @@ fn emit_git_variables() -> anyhow::Result<()> {
|
||||
|
||||
let git2 = builder.build()?;
|
||||
|
||||
vergen_gitcl::Emitter::default().fail_on_error().add_instructions(&git2)?.emit()
|
||||
vergen_git2::Emitter::default().fail_on_error().add_instructions(&git2)?.emit()
|
||||
}
|
||||
|
||||
@@ -1,6 +0,0 @@
|
||||
use build_info::BuildInfo;
|
||||
|
||||
fn main() {
|
||||
let info = BuildInfo::from_build();
|
||||
dbg!(info);
|
||||
}
|
||||
@@ -11,27 +11,24 @@ readme.workspace = true
|
||||
license.workspace = true
|
||||
|
||||
[dependencies]
|
||||
anyhow = "1.0.100"
|
||||
flate2 = "1.1.5"
|
||||
anyhow = "1.0.98"
|
||||
flate2 = "1.1.2"
|
||||
http = "1.3.1"
|
||||
meilisearch-types = { path = "../meilisearch-types" }
|
||||
once_cell = "1.21.3"
|
||||
regex = "1.12.2"
|
||||
regex = "1.11.1"
|
||||
roaring = { version = "0.10.12", features = ["serde"] }
|
||||
serde = { version = "1.0.228", features = ["derive"] }
|
||||
serde_json = { version = "1.0.145", features = ["preserve_order"] }
|
||||
serde = { version = "1.0.219", features = ["derive"] }
|
||||
serde_json = { version = "1.0.140", features = ["preserve_order"] }
|
||||
tar = "0.4.44"
|
||||
tempfile = "3.23.0"
|
||||
thiserror = "2.0.17"
|
||||
time = { version = "0.3.44", features = ["serde-well-known", "formatting", "parsing", "macros"] }
|
||||
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 = "1.18.1", features = ["serde", "v4"] }
|
||||
uuid = { version = "1.17.0", features = ["serde", "v4"] }
|
||||
|
||||
[dev-dependencies]
|
||||
big_s = "1.0.2"
|
||||
maplit = "1.0.2"
|
||||
meili-snap = { path = "../meili-snap" }
|
||||
meilisearch-types = { path = "../meilisearch-types" }
|
||||
|
||||
[features]
|
||||
enterprise = ["meilisearch-types/enterprise"]
|
||||
@@ -262,13 +262,13 @@ pub(crate) mod test {
|
||||
use big_s::S;
|
||||
use maplit::{btreemap, btreeset};
|
||||
use meilisearch_types::batches::{Batch, BatchEnqueuedAt, BatchStats};
|
||||
use meilisearch_types::enterprise_edition::network::{Network, Remote};
|
||||
use meilisearch_types::facet_values_sort::FacetValuesSort;
|
||||
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::{BatchStopReason, Details, Kind, Status};
|
||||
|
||||
@@ -24,7 +24,7 @@ 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::network::Network;
|
||||
pub type Network = meilisearch_types::enterprise_edition::network::Network;
|
||||
pub type Webhooks = meilisearch_types::webhooks::WebhooksDumpView;
|
||||
|
||||
// ===== Other types to clarify the code of the compat module
|
||||
|
||||
@@ -5,9 +5,9 @@ use std::path::PathBuf;
|
||||
use flate2::write::GzEncoder;
|
||||
use flate2::Compression;
|
||||
use meilisearch_types::batches::Batch;
|
||||
use meilisearch_types::enterprise_edition::network::Network;
|
||||
use meilisearch_types::features::{ChatCompletionSettings, RuntimeTogglableFeatures};
|
||||
use meilisearch_types::keys::Key;
|
||||
use meilisearch_types::network::Network;
|
||||
use meilisearch_types::settings::{Checked, Settings};
|
||||
use meilisearch_types::webhooks::WebhooksDumpView;
|
||||
use serde_json::{Map, Value};
|
||||
|
||||
@@ -11,7 +11,7 @@ edition.workspace = true
|
||||
license.workspace = true
|
||||
|
||||
[dependencies]
|
||||
tempfile = "3.23.0"
|
||||
thiserror = "2.0.17"
|
||||
tempfile = "3.20.0"
|
||||
thiserror = "2.0.12"
|
||||
tracing = "0.1.41"
|
||||
uuid = { version = "1.18.1", features = ["serde", "v4"] }
|
||||
uuid = { version = "1.17.0", features = ["serde", "v4"] }
|
||||
|
||||
@@ -16,7 +16,7 @@ license.workspace = true
|
||||
serde_json = "1.0"
|
||||
|
||||
[dev-dependencies]
|
||||
criterion = { version = "0.7.0", features = ["html_reports"] }
|
||||
criterion = { version = "0.6.0", features = ["html_reports"] }
|
||||
|
||||
[[bench]]
|
||||
name = "benchmarks"
|
||||
|
||||
@@ -11,12 +11,12 @@ edition.workspace = true
|
||||
license.workspace = true
|
||||
|
||||
[dependencies]
|
||||
arbitrary = { version = "1.4.2", features = ["derive"] }
|
||||
bumpalo = "3.19.0"
|
||||
clap = { version = "4.5.52", features = ["derive"] }
|
||||
arbitrary = { version = "1.4.1", features = ["derive"] }
|
||||
bumpalo = "3.18.1"
|
||||
clap = { version = "4.5.40", features = ["derive"] }
|
||||
either = "1.15.0"
|
||||
fastrand = "2.3.0"
|
||||
milli = { path = "../milli" }
|
||||
serde = { version = "1.0.228", features = ["derive"] }
|
||||
serde_json = { version = "1.0.145", features = ["preserve_order"] }
|
||||
tempfile = "3.23.0"
|
||||
serde = { version = "1.0.219", features = ["derive"] }
|
||||
serde_json = { version = "1.0.140", features = ["preserve_order"] }
|
||||
tempfile = "3.20.0"
|
||||
|
||||
@@ -11,33 +11,33 @@ edition.workspace = true
|
||||
license.workspace = true
|
||||
|
||||
[dependencies]
|
||||
anyhow = "1.0.100"
|
||||
anyhow = "1.0.98"
|
||||
bincode = "1.3.3"
|
||||
byte-unit = "5.1.6"
|
||||
bytes = "1.11.0"
|
||||
bumpalo = "3.19.0"
|
||||
bytes = "1.10.1"
|
||||
bumpalo = "3.18.1"
|
||||
bumparaw-collections = "0.1.4"
|
||||
convert_case = "0.9.0"
|
||||
csv = "1.4.0"
|
||||
convert_case = "0.8.0"
|
||||
csv = "1.3.1"
|
||||
derive_builder = "0.20.2"
|
||||
dump = { path = "../dump" }
|
||||
enum-iterator = "2.3.0"
|
||||
enum-iterator = "2.1.0"
|
||||
file-store = { path = "../file-store" }
|
||||
flate2 = "1.1.5"
|
||||
indexmap = "2.12.0"
|
||||
flate2 = "1.1.2"
|
||||
indexmap = "2.9.0"
|
||||
meilisearch-auth = { path = "../meilisearch-auth" }
|
||||
meilisearch-types = { path = "../meilisearch-types" }
|
||||
memmap2 = "0.9.9"
|
||||
memmap2 = "0.9.7"
|
||||
page_size = "0.6.0"
|
||||
rayon = "1.11.0"
|
||||
rayon = "1.10.0"
|
||||
roaring = { version = "0.10.12", features = ["serde"] }
|
||||
serde = { version = "1.0.228", features = ["derive"] }
|
||||
serde_json = { version = "1.0.145", features = ["preserve_order"] }
|
||||
serde = { version = "1.0.219", features = ["derive"] }
|
||||
serde_json = { version = "1.0.140", features = ["preserve_order"] }
|
||||
tar = "0.4.44"
|
||||
synchronoise = "1.0.1"
|
||||
tempfile = "3.23.0"
|
||||
thiserror = "2.0.17"
|
||||
time = { version = "0.3.44", features = [
|
||||
tempfile = "3.20.0"
|
||||
thiserror = "2.0.12"
|
||||
time = { version = "0.3.41", features = [
|
||||
"serde-well-known",
|
||||
"formatting",
|
||||
"parsing",
|
||||
@@ -45,11 +45,11 @@ time = { version = "0.3.44", features = [
|
||||
] }
|
||||
tracing = "0.1.41"
|
||||
ureq = "2.12.1"
|
||||
uuid = { version = "1.18.1", features = ["serde", "v4"] }
|
||||
uuid = { version = "1.17.0", features = ["serde", "v4"] }
|
||||
backoff = "0.4.0"
|
||||
reqwest = { version = "0.12.24", features = ["rustls-tls", "http2"], default-features = false }
|
||||
reqwest = { version = "0.12.23", features = ["rustls-tls", "http2"], default-features = false }
|
||||
rusty-s3 = "0.8.1"
|
||||
tokio = { version = "1.48.0", features = ["full"] }
|
||||
tokio = { version = "1.47.1", features = ["full"] }
|
||||
|
||||
[dev-dependencies]
|
||||
big_s = "1.0.2"
|
||||
|
||||
@@ -1,9 +1,9 @@
|
||||
use std::sync::{Arc, RwLock};
|
||||
|
||||
use meilisearch_types::enterprise_edition::network::Network;
|
||||
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;
|
||||
|
||||
@@ -6,7 +6,7 @@ use meilisearch_types::heed::types::{SerdeBincode, SerdeJson, Str};
|
||||
use meilisearch_types::heed::{Database, RoTxn};
|
||||
use meilisearch_types::milli::{CboRoaringBitmapCodec, RoaringBitmapCodec, BEU32};
|
||||
use meilisearch_types::tasks::{Details, Kind, Status, Task};
|
||||
use meilisearch_types::versioning::{self, VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH};
|
||||
use meilisearch_types::versioning;
|
||||
use roaring::RoaringBitmap;
|
||||
|
||||
use crate::index_mapper::IndexMapper;
|
||||
@@ -320,11 +320,7 @@ fn snapshot_details(d: &Details) -> String {
|
||||
format!("{{ url: {url:?}, api_key: {api_key:?}, payload_size: {payload_size:?}, indexes: {indexes:?} }}")
|
||||
}
|
||||
Details::UpgradeDatabase { from, to } => {
|
||||
if to == &(VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH) {
|
||||
format!("{{ from: {from:?}, to: [current version] }}")
|
||||
} else {
|
||||
format!("{{ from: {from:?}, to: {to:?} }}")
|
||||
}
|
||||
format!("{{ from: {from:?}, to: {to:?} }}")
|
||||
}
|
||||
Details::IndexCompaction { index_uid, pre_compaction_size, post_compaction_size } => {
|
||||
format!("{{ index_uid: {index_uid:?}, pre_compaction_size: {pre_compaction_size:?}, post_compaction_size: {post_compaction_size:?} }}")
|
||||
@@ -404,21 +400,7 @@ pub fn snapshot_batch(batch: &Batch) -> String {
|
||||
|
||||
snap.push('{');
|
||||
snap.push_str(&format!("uid: {uid}, "));
|
||||
let details = if let Some(upgrade_to) = &details.upgrade_to {
|
||||
if upgrade_to.as_str()
|
||||
== format!("v{VERSION_MAJOR}.{VERSION_MINOR}.{VERSION_PATCH}").as_str()
|
||||
{
|
||||
let mut details = details.clone();
|
||||
|
||||
details.upgrade_to = Some("[current version]".into());
|
||||
serde_json::to_string(&details).unwrap()
|
||||
} else {
|
||||
serde_json::to_string(details).unwrap()
|
||||
}
|
||||
} else {
|
||||
serde_json::to_string(details).unwrap()
|
||||
};
|
||||
snap.push_str(&format!("details: {details}, "));
|
||||
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!(
|
||||
|
||||
@@ -54,6 +54,7 @@ pub use features::RoFeatures;
|
||||
use flate2::bufread::GzEncoder;
|
||||
use flate2::Compression;
|
||||
use meilisearch_types::batches::Batch;
|
||||
use meilisearch_types::enterprise_edition::network::Network;
|
||||
use meilisearch_types::features::{
|
||||
ChatCompletionSettings, InstanceTogglableFeatures, RuntimeTogglableFeatures,
|
||||
};
|
||||
@@ -66,7 +67,6 @@ 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, TaskNetwork};
|
||||
use meilisearch_types::webhooks::{Webhook, WebhooksDumpView, WebhooksView};
|
||||
|
||||
@@ -438,15 +438,12 @@ async fn multipart_stream_to_s3(
|
||||
db_name: String,
|
||||
reader: std::io::PipeReader,
|
||||
) -> Result<(), Error> {
|
||||
use std::collections::VecDeque;
|
||||
use std::io;
|
||||
use std::os::fd::OwnedFd;
|
||||
use std::path::PathBuf;
|
||||
use std::{collections::VecDeque, os::fd::OwnedFd, path::PathBuf};
|
||||
|
||||
use bytes::{Bytes, BytesMut};
|
||||
use reqwest::{Client, Response};
|
||||
use rusty_s3::actions::CreateMultipartUpload;
|
||||
use rusty_s3::{Bucket, BucketError, Credentials, S3Action as _, UrlStyle};
|
||||
use rusty_s3::S3Action as _;
|
||||
use rusty_s3::{actions::CreateMultipartUpload, Bucket, BucketError, Credentials, UrlStyle};
|
||||
use tokio::task::JoinHandle;
|
||||
|
||||
let reader = OwnedFd::from(reader);
|
||||
@@ -520,6 +517,7 @@ async fn multipart_stream_to_s3(
|
||||
while buffer.len() < (s3_multipart_part_size as usize / 2) {
|
||||
// Wait for the pipe to be readable
|
||||
|
||||
use std::io;
|
||||
reader.readable().await?;
|
||||
|
||||
match reader.try_read_buf(&mut buffer) {
|
||||
@@ -583,17 +581,15 @@ async fn multipart_stream_to_s3(
|
||||
async move {
|
||||
match client.post(url).body(body).send().await {
|
||||
Ok(resp) if resp.status().is_client_error() => {
|
||||
Err(backoff::Error::Permanent(Error::S3Error {
|
||||
status: resp.status(),
|
||||
body: resp.text().await.unwrap_or_default(),
|
||||
}))
|
||||
resp.error_for_status().map_err(backoff::Error::Permanent)
|
||||
}
|
||||
Ok(resp) => Ok(resp),
|
||||
Err(e) => Err(backoff::Error::transient(Error::S3HttpError(e))),
|
||||
Err(e) => Err(backoff::Error::transient(e)),
|
||||
}
|
||||
}
|
||||
})
|
||||
.await?;
|
||||
.await
|
||||
.map_err(Error::S3HttpError)?;
|
||||
|
||||
let status = resp.status();
|
||||
let body = resp.text().await.map_err(|e| Error::S3Error { status, body: e.to_string() })?;
|
||||
|
||||
@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
|
||||
[]
|
||||
----------------------------------------------------------------------
|
||||
### All Tasks:
|
||||
0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: [current version] }, kind: UpgradeDatabase { from: (1, 12, 0) }}
|
||||
0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: (1, 26, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
|
||||
1 {uid: 1, batch_uid: 1, status: succeeded, details: { primary_key: Some("mouse"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
|
||||
2 {uid: 2, batch_uid: 2, status: succeeded, details: { primary_key: Some("bone"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
|
||||
3 {uid: 3, batch_uid: 3, status: failed, error: ResponseError { code: 200, message: "Index `doggo` already exists.", error_code: "index_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_already_exists" }, details: { primary_key: Some("bone"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
|
||||
@@ -57,7 +57,7 @@ girafo: { number_of_documents: 0, field_distribution: {} }
|
||||
[timestamp] [4,]
|
||||
----------------------------------------------------------------------
|
||||
### All Batches:
|
||||
0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"[current version]"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
|
||||
0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.26.0"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
|
||||
1 {uid: 1, details: {"primaryKey":"mouse"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":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":"bone"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggo":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: {"primaryKey":"bone"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, stop reason: "created batch containing only task with id 3 of type `indexCreation` that cannot be batched with any other task.", }
|
||||
|
||||
@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
|
||||
[]
|
||||
----------------------------------------------------------------------
|
||||
### All Tasks:
|
||||
0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: [current version] }, kind: UpgradeDatabase { from: (1, 12, 0) }}
|
||||
0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: (1, 26, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
|
||||
----------------------------------------------------------------------
|
||||
### Status:
|
||||
enqueued [0,]
|
||||
|
||||
@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
|
||||
[]
|
||||
----------------------------------------------------------------------
|
||||
### All Tasks:
|
||||
0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: [current version] }, kind: UpgradeDatabase { from: (1, 12, 0) }}
|
||||
0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: (1, 26, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
|
||||
1 {uid: 1, status: enqueued, details: { primary_key: Some("mouse"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
|
||||
----------------------------------------------------------------------
|
||||
### Status:
|
||||
|
||||
@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
|
||||
[]
|
||||
----------------------------------------------------------------------
|
||||
### All Tasks:
|
||||
0 {uid: 0, batch_uid: 0, status: failed, error: ResponseError { code: 200, message: "Planned failure for tests.", error_code: "internal", error_type: "internal", error_link: "https://docs.meilisearch.com/errors#internal" }, details: { from: (1, 12, 0), to: [current version] }, kind: UpgradeDatabase { from: (1, 12, 0) }}
|
||||
0 {uid: 0, batch_uid: 0, status: failed, error: ResponseError { code: 200, message: "Planned failure for tests.", error_code: "internal", error_type: "internal", error_link: "https://docs.meilisearch.com/errors#internal" }, details: { from: (1, 12, 0), to: (1, 26, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
|
||||
1 {uid: 1, status: enqueued, details: { primary_key: Some("mouse"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
|
||||
----------------------------------------------------------------------
|
||||
### Status:
|
||||
@@ -37,7 +37,7 @@ catto [1,]
|
||||
[timestamp] [0,]
|
||||
----------------------------------------------------------------------
|
||||
### All Batches:
|
||||
0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"[current version]"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
|
||||
0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.26.0"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
|
||||
----------------------------------------------------------------------
|
||||
### Batch to tasks mapping:
|
||||
0 [0,]
|
||||
|
||||
@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
|
||||
[]
|
||||
----------------------------------------------------------------------
|
||||
### All Tasks:
|
||||
0 {uid: 0, batch_uid: 0, status: failed, error: ResponseError { code: 200, message: "Planned failure for tests.", error_code: "internal", error_type: "internal", error_link: "https://docs.meilisearch.com/errors#internal" }, details: { from: (1, 12, 0), to: [current version] }, kind: UpgradeDatabase { from: (1, 12, 0) }}
|
||||
0 {uid: 0, batch_uid: 0, status: failed, error: ResponseError { code: 200, message: "Planned failure for tests.", error_code: "internal", error_type: "internal", error_link: "https://docs.meilisearch.com/errors#internal" }, details: { from: (1, 12, 0), to: (1, 26, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
|
||||
1 {uid: 1, status: enqueued, details: { primary_key: Some("mouse"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
|
||||
2 {uid: 2, status: enqueued, details: { primary_key: Some("bone"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
|
||||
----------------------------------------------------------------------
|
||||
@@ -40,7 +40,7 @@ doggo [2,]
|
||||
[timestamp] [0,]
|
||||
----------------------------------------------------------------------
|
||||
### All Batches:
|
||||
0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"[current version]"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
|
||||
0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.26.0"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
|
||||
----------------------------------------------------------------------
|
||||
### Batch to tasks mapping:
|
||||
0 [0,]
|
||||
|
||||
@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
|
||||
[]
|
||||
----------------------------------------------------------------------
|
||||
### All Tasks:
|
||||
0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: [current version] }, kind: UpgradeDatabase { from: (1, 12, 0) }}
|
||||
0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: (1, 26, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
|
||||
1 {uid: 1, status: enqueued, details: { primary_key: Some("mouse"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
|
||||
2 {uid: 2, status: enqueued, details: { primary_key: Some("bone"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
|
||||
3 {uid: 3, status: enqueued, details: { primary_key: Some("bone"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
|
||||
@@ -43,7 +43,7 @@ doggo [2,3,]
|
||||
[timestamp] [0,]
|
||||
----------------------------------------------------------------------
|
||||
### All Batches:
|
||||
0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"[current version]"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
|
||||
0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.26.0"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
|
||||
----------------------------------------------------------------------
|
||||
### Batch to tasks mapping:
|
||||
0 [0,]
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
use anyhow::bail;
|
||||
use meilisearch_types::heed::{Env, RwTxn, WithoutTls};
|
||||
use meilisearch_types::tasks::{Details, KindWithContent, Status, Task};
|
||||
use meilisearch_types::versioning;
|
||||
use meilisearch_types::versioning::{VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH};
|
||||
use time::OffsetDateTime;
|
||||
use tracing::info;
|
||||
|
||||
@@ -9,82 +9,81 @@ use crate::queue::TaskQueue;
|
||||
use crate::versioning::Versioning;
|
||||
|
||||
trait UpgradeIndexScheduler {
|
||||
fn upgrade(&self, env: &Env<WithoutTls>, wtxn: &mut RwTxn) -> anyhow::Result<()>;
|
||||
/// Whether the migration should be applied, depending on the initial version of the index scheduler before
|
||||
/// any migration was applied
|
||||
fn must_upgrade(&self, initial_version: (u32, u32, u32)) -> bool;
|
||||
/// A progress-centric description of the migration
|
||||
fn description(&self) -> &'static str;
|
||||
fn upgrade(
|
||||
&self,
|
||||
env: &Env<WithoutTls>,
|
||||
wtxn: &mut RwTxn,
|
||||
original: (u32, u32, u32),
|
||||
) -> anyhow::Result<()>;
|
||||
fn target_version(&self) -> (u32, u32, u32);
|
||||
}
|
||||
|
||||
/// Upgrade the index scheduler to the binary version.
|
||||
///
|
||||
/// # Warning
|
||||
///
|
||||
/// The current implementation uses a single wtxn to the index scheduler for the whole duration of the upgrade.
|
||||
/// If migrations start taking take a long time, it might prevent tasks from being registered.
|
||||
/// If this issue manifests, then it can be mitigated by adding a `fn target_version` to `UpgradeIndexScheduler`,
|
||||
/// to be able to write intermediate versions and drop the wtxn between applying migrations.
|
||||
pub fn upgrade_index_scheduler(
|
||||
env: &Env<WithoutTls>,
|
||||
versioning: &Versioning,
|
||||
initial_version: (u32, u32, u32),
|
||||
from: (u32, u32, u32),
|
||||
to: (u32, u32, u32),
|
||||
) -> anyhow::Result<()> {
|
||||
let target_major: u32 = versioning::VERSION_MAJOR;
|
||||
let target_minor: u32 = versioning::VERSION_MINOR;
|
||||
let target_patch: u32 = versioning::VERSION_PATCH;
|
||||
let target_version = (target_major, target_minor, target_patch);
|
||||
|
||||
if initial_version == target_version {
|
||||
return Ok(());
|
||||
}
|
||||
let current_major = to.0;
|
||||
let current_minor = to.1;
|
||||
let current_patch = to.2;
|
||||
|
||||
let upgrade_functions: &[&dyn UpgradeIndexScheduler] = &[
|
||||
// List all upgrade functions to apply in order here.
|
||||
// This is the last upgrade function, it will be called when the index is up to date.
|
||||
// any other upgrade function should be added before this one.
|
||||
&ToCurrentNoOp {},
|
||||
];
|
||||
|
||||
let (initial_major, initial_minor, initial_patch) = initial_version;
|
||||
|
||||
if initial_version > target_version {
|
||||
bail!(
|
||||
"Database version {initial_major}.{initial_minor}.{initial_patch} is higher than the Meilisearch version {target_major}.{target_minor}.{target_patch}. Downgrade is not supported",
|
||||
let start = match from {
|
||||
(1, 12, _) => 0,
|
||||
(1, 13, _) => 0,
|
||||
(1, 14, _) => 0,
|
||||
(1, 15, _) => 0,
|
||||
(1, 16, _) => 0,
|
||||
(1, 17, _) => 0,
|
||||
(1, 18, _) => 0,
|
||||
(1, 19, _) => 0,
|
||||
(1, 20, _) => 0,
|
||||
(1, 21, _) => 0,
|
||||
(1, 22, _) => 0,
|
||||
(1, 23, _) => 0,
|
||||
(1, 24, _) => 0,
|
||||
(1, 25, _) => 0,
|
||||
(1, 26, _) => 0,
|
||||
(major, minor, patch) => {
|
||||
if major > current_major
|
||||
|| (major == current_major && minor > current_minor)
|
||||
|| (major == current_major && minor == current_minor && patch > current_patch)
|
||||
{
|
||||
bail!(
|
||||
"Database version {major}.{minor}.{patch} is higher than the Meilisearch version {current_major}.{current_minor}.{current_patch}. Downgrade is not supported",
|
||||
);
|
||||
} else if major < 1 || (major == current_major && minor < 12) {
|
||||
bail!(
|
||||
"Database version {major}.{minor}.{patch} is too old for the experimental dumpless upgrade feature. Please generate a dump using the v{major}.{minor}.{patch} and import it in the v{current_major}.{current_minor}.{current_patch}",
|
||||
);
|
||||
}
|
||||
|
||||
if initial_version < (1, 12, 0) {
|
||||
bail!(
|
||||
"Database version {initial_major}.{initial_minor}.{initial_patch} is too old for the experimental dumpless upgrade feature. Please generate a dump using the v{initial_major}.{initial_minor}.{initial_patch} and import it in the v{target_major}.{target_minor}.{target_patch}",
|
||||
);
|
||||
}
|
||||
} else {
|
||||
bail!("Unknown database version: v{major}.{minor}.{patch}");
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
info!("Upgrading the task queue");
|
||||
let mut wtxn = env.write_txn()?;
|
||||
let migration_count = upgrade_functions.len();
|
||||
for (migration_index, upgrade) in upgrade_functions.iter().enumerate() {
|
||||
if upgrade.must_upgrade(initial_version) {
|
||||
info!(
|
||||
"[{migration_index}/{migration_count}]Applying migration: {}",
|
||||
upgrade.description()
|
||||
);
|
||||
|
||||
upgrade.upgrade(env, &mut wtxn)?;
|
||||
|
||||
info!(
|
||||
"[{}/{migration_count}]Migration applied: {}",
|
||||
migration_index + 1,
|
||||
upgrade.description()
|
||||
)
|
||||
} else {
|
||||
info!(
|
||||
"[{migration_index}/{migration_count}]Skipping unnecessary migration: {}",
|
||||
upgrade.description()
|
||||
)
|
||||
}
|
||||
let mut local_from = from;
|
||||
for upgrade in upgrade_functions[start..].iter() {
|
||||
let target = upgrade.target_version();
|
||||
info!(
|
||||
"Upgrading from v{}.{}.{} to v{}.{}.{}",
|
||||
local_from.0, local_from.1, local_from.2, target.0, target.1, target.2
|
||||
);
|
||||
let mut wtxn = env.write_txn()?;
|
||||
upgrade.upgrade(env, &mut wtxn, local_from)?;
|
||||
versioning.set_version(&mut wtxn, target)?;
|
||||
wtxn.commit()?;
|
||||
local_from = target;
|
||||
}
|
||||
|
||||
versioning.set_version(&mut wtxn, target_version)?;
|
||||
info!("Task queue upgraded, spawning the upgrade database task");
|
||||
|
||||
let mut wtxn = env.write_txn()?;
|
||||
let queue = TaskQueue::new(env, &mut wtxn)?;
|
||||
let uid = queue.next_task_id(&wtxn)?;
|
||||
queue.register(
|
||||
@@ -97,9 +96,9 @@ pub fn upgrade_index_scheduler(
|
||||
finished_at: None,
|
||||
error: None,
|
||||
canceled_by: None,
|
||||
details: Some(Details::UpgradeDatabase { from: initial_version, to: target_version }),
|
||||
details: Some(Details::UpgradeDatabase { from, to }),
|
||||
status: Status::Enqueued,
|
||||
kind: KindWithContent::UpgradeDatabase { from: initial_version },
|
||||
kind: KindWithContent::UpgradeDatabase { from },
|
||||
network: None,
|
||||
custom_metadata: None,
|
||||
},
|
||||
@@ -108,3 +107,21 @@ pub fn upgrade_index_scheduler(
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[allow(non_camel_case_types)]
|
||||
struct ToCurrentNoOp {}
|
||||
|
||||
impl UpgradeIndexScheduler for ToCurrentNoOp {
|
||||
fn upgrade(
|
||||
&self,
|
||||
_env: &Env<WithoutTls>,
|
||||
_wtxn: &mut RwTxn,
|
||||
_original: (u32, u32, u32),
|
||||
) -> anyhow::Result<()> {
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn target_version(&self) -> (u32, u32, u32) {
|
||||
(VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -64,7 +64,14 @@ impl Versioning {
|
||||
};
|
||||
wtxn.commit()?;
|
||||
|
||||
upgrade_index_scheduler(env, &this, from)?;
|
||||
let bin_major: u32 = versioning::VERSION_MAJOR;
|
||||
let bin_minor: u32 = versioning::VERSION_MINOR;
|
||||
let bin_patch: u32 = versioning::VERSION_PATCH;
|
||||
let to = (bin_major, bin_minor, bin_patch);
|
||||
|
||||
if from != to {
|
||||
upgrade_index_scheduler(env, &this, from, to)?;
|
||||
}
|
||||
|
||||
// Once we reach this point it means the upgrade process, if there was one is entirely finished
|
||||
// we can safely say we reached the latest version of the index scheduler
|
||||
|
||||
@@ -15,7 +15,7 @@ license.workspace = true
|
||||
serde_json = "1.0"
|
||||
|
||||
[dev-dependencies]
|
||||
criterion = "0.7.0"
|
||||
criterion = "0.6.0"
|
||||
|
||||
[[bench]]
|
||||
name = "depth"
|
||||
|
||||
@@ -13,7 +13,7 @@ license.workspace = true
|
||||
[dependencies]
|
||||
# fixed version due to format breakages in v1.40
|
||||
insta = { version = "=1.39.0", features = ["json", "redactions"] }
|
||||
md5 = "0.8.0"
|
||||
md5 = "0.7.0"
|
||||
once_cell = "1.21"
|
||||
regex-lite = "0.1.8"
|
||||
uuid = { version = "1.18.1", features = ["v4"] }
|
||||
regex-lite = "0.1.6"
|
||||
uuid = { version = "1.17.0", features = ["v4"] }
|
||||
|
||||
@@ -12,15 +12,15 @@ license.workspace = true
|
||||
|
||||
[dependencies]
|
||||
base64 = "0.22.1"
|
||||
enum-iterator = "2.3.0"
|
||||
enum-iterator = "2.1.0"
|
||||
hmac = "0.12.1"
|
||||
maplit = "1.0.2"
|
||||
meilisearch-types = { path = "../meilisearch-types" }
|
||||
rand = "0.8.5"
|
||||
roaring = { version = "0.10.12", features = ["serde"] }
|
||||
serde = { version = "1.0.228", features = ["derive"] }
|
||||
serde_json = { version = "1.0.145", features = ["preserve_order"] }
|
||||
serde = { version = "1.0.219", features = ["derive"] }
|
||||
serde_json = { version = "1.0.140", features = ["preserve_order"] }
|
||||
sha2 = "0.10.9"
|
||||
thiserror = "2.0.17"
|
||||
time = { version = "0.3.44", features = ["serde-well-known", "formatting", "parsing", "macros"] }
|
||||
uuid = { version = "1.18.1", features = ["serde", "v4"] }
|
||||
thiserror = "2.0.12"
|
||||
time = { version = "0.3.41", features = ["serde-well-known", "formatting", "parsing", "macros"] }
|
||||
uuid = { version = "1.17.0", features = ["serde", "v4"] }
|
||||
|
||||
@@ -11,38 +11,38 @@ edition.workspace = true
|
||||
license.workspace = true
|
||||
|
||||
[dependencies]
|
||||
actix-web = { version = "4.12.0", default-features = false }
|
||||
anyhow = "1.0.100"
|
||||
bumpalo = "3.19.0"
|
||||
actix-web = { version = "4.11.0", default-features = false }
|
||||
anyhow = "1.0.98"
|
||||
bumpalo = "3.18.1"
|
||||
bumparaw-collections = "0.1.4"
|
||||
byte-unit = { version = "5.1.6", features = ["serde"] }
|
||||
convert_case = "0.9.0"
|
||||
csv = "1.4.0"
|
||||
deserr = { version = "0.6.4", features = ["actix-web"] }
|
||||
convert_case = "0.8.0"
|
||||
csv = "1.3.1"
|
||||
deserr = { version = "0.6.3", features = ["actix-web"] }
|
||||
either = { version = "1.15.0", features = ["serde"] }
|
||||
enum-iterator = "2.3.0"
|
||||
enum-iterator = "2.1.0"
|
||||
file-store = { path = "../file-store" }
|
||||
flate2 = "1.1.5"
|
||||
flate2 = "1.1.2"
|
||||
fst = "0.4.7"
|
||||
memmap2 = "0.9.9"
|
||||
memmap2 = "0.9.7"
|
||||
milli = { path = "../milli" }
|
||||
roaring = { version = "0.10.12", features = ["serde"] }
|
||||
rustc-hash = "2.1.1"
|
||||
serde = { version = "1.0.228", features = ["derive"] }
|
||||
serde = { version = "1.0.219", features = ["derive"] }
|
||||
serde-cs = "0.2.4"
|
||||
serde_json = { version = "1.0.145", features = ["preserve_order"] }
|
||||
serde_json = { version = "1.0.140", features = ["preserve_order"] }
|
||||
tar = "0.4.44"
|
||||
tempfile = "3.23.0"
|
||||
thiserror = "2.0.17"
|
||||
time = { version = "0.3.44", features = [
|
||||
tempfile = "3.20.0"
|
||||
thiserror = "2.0.12"
|
||||
time = { version = "0.3.41", features = [
|
||||
"serde-well-known",
|
||||
"formatting",
|
||||
"parsing",
|
||||
"macros",
|
||||
] }
|
||||
tokio = "1.48"
|
||||
tokio = "1.45"
|
||||
utoipa = { version = "5.4.0", features = ["macros"] }
|
||||
uuid = { version = "1.18.1", features = ["serde", "v4"] }
|
||||
uuid = { version = "1.17.0", features = ["serde", "v4"] }
|
||||
|
||||
[dev-dependencies]
|
||||
# fixed version due to format breakages in v1.40
|
||||
@@ -56,9 +56,6 @@ all-tokenizations = ["milli/all-tokenizations"]
|
||||
# chinese specialized tokenization
|
||||
chinese = ["milli/chinese"]
|
||||
chinese-pinyin = ["milli/chinese-pinyin"]
|
||||
|
||||
enterprise = ["milli/enterprise"]
|
||||
|
||||
# hebrew specialized tokenization
|
||||
hebrew = ["milli/hebrew"]
|
||||
# japanese specialized tokenization
|
||||
|
||||
@@ -1,16 +0,0 @@
|
||||
pub mod network {
|
||||
use milli::update::new::indexer::current_edition::sharding::Shards;
|
||||
|
||||
use crate::network::Network;
|
||||
|
||||
impl Network {
|
||||
pub fn shards(&self) -> Option<Shards> {
|
||||
None
|
||||
}
|
||||
|
||||
pub fn sharding(&self) -> bool {
|
||||
// always false in CE
|
||||
false
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -3,9 +3,21 @@
|
||||
// Use of this source code is governed by the Business Source License 1.1,
|
||||
// as found in the LICENSE-EE file or at <https://mariadb.com/bsl11>
|
||||
|
||||
use milli::update::new::indexer::enterprise_edition::sharding::Shards;
|
||||
use std::collections::BTreeMap;
|
||||
|
||||
use crate::network::Network;
|
||||
use milli::update::new::indexer::enterprise_edition::sharding::Shards;
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, Default)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct Network {
|
||||
#[serde(default, rename = "self")]
|
||||
pub local: Option<String>,
|
||||
#[serde(default)]
|
||||
pub remotes: BTreeMap<String, Remote>,
|
||||
#[serde(default)]
|
||||
pub sharding: bool,
|
||||
}
|
||||
|
||||
impl Network {
|
||||
pub fn shards(&self) -> Option<Shards> {
|
||||
@@ -22,8 +34,14 @@ impl Network {
|
||||
None
|
||||
}
|
||||
}
|
||||
|
||||
pub fn sharding(&self) -> bool {
|
||||
self.sharding
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct Remote {
|
||||
pub url: String,
|
||||
#[serde(default)]
|
||||
pub search_api_key: Option<String>,
|
||||
#[serde(default)]
|
||||
pub write_api_key: Option<String>,
|
||||
}
|
||||
|
||||
@@ -433,7 +433,6 @@ InvalidChatCompletionSearchQueryParamPrompt , InvalidRequest , BAD_REQU
|
||||
InvalidChatCompletionSearchFilterParamPrompt , InvalidRequest , BAD_REQUEST ;
|
||||
InvalidChatCompletionSearchIndexUidParamPrompt , InvalidRequest , BAD_REQUEST ;
|
||||
InvalidChatCompletionPreQueryPrompt , InvalidRequest , BAD_REQUEST ;
|
||||
RequiresEnterpriseEdition , InvalidRequest , UNAVAILABLE_FOR_LEGAL_REASONS ;
|
||||
// Webhooks
|
||||
InvalidWebhooks , InvalidRequest , BAD_REQUEST ;
|
||||
InvalidWebhookUrl , InvalidRequest , BAD_REQUEST ;
|
||||
|
||||
@@ -2,17 +2,10 @@
|
||||
|
||||
pub mod batch_view;
|
||||
pub mod batches;
|
||||
#[cfg(not(feature = "enterprise"))]
|
||||
pub mod community_edition;
|
||||
pub mod compression;
|
||||
pub mod deserr;
|
||||
pub mod document_formats;
|
||||
#[cfg(feature = "enterprise")]
|
||||
pub mod enterprise_edition;
|
||||
#[cfg(not(feature = "enterprise"))]
|
||||
pub use community_edition as current_edition;
|
||||
#[cfg(feature = "enterprise")]
|
||||
pub use enterprise_edition as current_edition;
|
||||
pub mod error;
|
||||
pub mod facet_values_sort;
|
||||
pub mod features;
|
||||
@@ -20,7 +13,6 @@ pub mod index_uid;
|
||||
pub mod index_uid_pattern;
|
||||
pub mod keys;
|
||||
pub mod locales;
|
||||
pub mod network;
|
||||
pub mod settings;
|
||||
pub mod star_or;
|
||||
pub mod task_view;
|
||||
|
||||
@@ -1,24 +0,0 @@
|
||||
use std::collections::BTreeMap;
|
||||
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, Default)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct Network {
|
||||
#[serde(default, rename = "self")]
|
||||
pub local: Option<String>,
|
||||
#[serde(default)]
|
||||
pub remotes: BTreeMap<String, Remote>,
|
||||
#[serde(default)]
|
||||
pub sharding: bool,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct Remote {
|
||||
pub url: String,
|
||||
#[serde(default)]
|
||||
pub search_api_key: Option<String>,
|
||||
#[serde(default)]
|
||||
pub write_api_key: Option<String>,
|
||||
}
|
||||
@@ -14,91 +14,91 @@ default-run = "meilisearch"
|
||||
|
||||
[dependencies]
|
||||
actix-cors = "0.7.1"
|
||||
actix-http = { version = "3.11.2", default-features = false, features = [
|
||||
actix-http = { version = "3.11.0", default-features = false, features = [
|
||||
"compress-brotli",
|
||||
"compress-gzip",
|
||||
"rustls-0_23",
|
||||
] }
|
||||
actix-utils = "3.0.1"
|
||||
actix-web = { version = "4.12.0", default-features = false, features = [
|
||||
actix-web = { version = "4.11.0", default-features = false, features = [
|
||||
"macros",
|
||||
"compress-brotli",
|
||||
"compress-gzip",
|
||||
"cookies",
|
||||
"rustls-0_23",
|
||||
] }
|
||||
anyhow = { version = "1.0.100", features = ["backtrace"] }
|
||||
bstr = "1.12.1"
|
||||
anyhow = { version = "1.0.98", features = ["backtrace"] }
|
||||
bstr = "1.12.0"
|
||||
byte-unit = { version = "5.1.6", features = ["serde"] }
|
||||
bytes = "1.11.0"
|
||||
bumpalo = "3.19.0"
|
||||
clap = { version = "4.5.52", features = ["derive", "env"] }
|
||||
bytes = "1.10.1"
|
||||
bumpalo = "3.18.1"
|
||||
clap = { version = "4.5.40", features = ["derive", "env"] }
|
||||
crossbeam-channel = "0.5.15"
|
||||
deserr = { version = "0.6.4", features = ["actix-web"] }
|
||||
deserr = { version = "0.6.3", features = ["actix-web"] }
|
||||
dump = { path = "../dump" }
|
||||
either = "1.15.0"
|
||||
file-store = { path = "../file-store" }
|
||||
flate2 = "1.1.5"
|
||||
flate2 = "1.1.2"
|
||||
fst = "0.4.7"
|
||||
futures = "0.3.31"
|
||||
futures-util = "0.3.31"
|
||||
index-scheduler = { path = "../index-scheduler" }
|
||||
indexmap = { version = "2.12.0", features = ["serde"] }
|
||||
is-terminal = "0.4.17"
|
||||
indexmap = { version = "2.9.0", features = ["serde"] }
|
||||
is-terminal = "0.4.16"
|
||||
itertools = "0.14.0"
|
||||
jsonwebtoken = "9.3.1"
|
||||
lazy_static = "1.5.0"
|
||||
meilisearch-auth = { path = "../meilisearch-auth" }
|
||||
meilisearch-types = { path = "../meilisearch-types" }
|
||||
memmap2 = "0.9.9"
|
||||
mimalloc = { version = "0.1.48", default-features = false }
|
||||
memmap2 = "0.9.7"
|
||||
mimalloc = { version = "0.1.47", default-features = false }
|
||||
mime = "0.3.17"
|
||||
num_cpus = "1.17.0"
|
||||
obkv = "0.3.0"
|
||||
once_cell = "1.21.3"
|
||||
ordered-float = "5.1.0"
|
||||
parking_lot = "0.12.5"
|
||||
ordered-float = "5.0.0"
|
||||
parking_lot = "0.12.4"
|
||||
permissive-json-pointer = { path = "../permissive-json-pointer" }
|
||||
pin-project-lite = "0.2.16"
|
||||
platform-dirs = "0.3.0"
|
||||
prometheus = { version = "0.14.0", features = ["process"] }
|
||||
rand = "0.8.5"
|
||||
rayon = "1.11.0"
|
||||
regex = "1.12.2"
|
||||
reqwest = { version = "0.12.24", features = [
|
||||
rayon = "1.10.0"
|
||||
regex = "1.11.1"
|
||||
reqwest = { version = "0.12.20", features = [
|
||||
"rustls-tls",
|
||||
"json",
|
||||
], default-features = false }
|
||||
rustls = { version = "0.23.35", features = ["ring"], default-features = false }
|
||||
rustls-pki-types = { version = "1.13.0", features = ["alloc"] }
|
||||
rustls = { version = "0.23.28", features = ["ring"], default-features = false }
|
||||
rustls-pki-types = { version = "1.12.0", features = ["alloc"] }
|
||||
rustls-pemfile = "2.2.0"
|
||||
segment = { version = "0.2.6" }
|
||||
serde = { version = "1.0.228", features = ["derive"] }
|
||||
serde_json = { version = "1.0.145", features = ["preserve_order"] }
|
||||
serde = { version = "1.0.219", features = ["derive"] }
|
||||
serde_json = { version = "1.0.140", features = ["preserve_order"] }
|
||||
sha2 = "0.10.9"
|
||||
siphasher = "1.0.1"
|
||||
slice-group-by = "0.3.1"
|
||||
static-files = { version = "0.3.1", optional = true }
|
||||
sysinfo = "0.37.2"
|
||||
static-files = { version = "0.2.5", optional = true }
|
||||
sysinfo = "0.35.2"
|
||||
tar = "0.4.44"
|
||||
tempfile = "3.23.0"
|
||||
thiserror = "2.0.17"
|
||||
time = { version = "0.3.44", features = [
|
||||
tempfile = "3.20.0"
|
||||
thiserror = "2.0.12"
|
||||
time = { version = "0.3.41", features = [
|
||||
"serde-well-known",
|
||||
"formatting",
|
||||
"parsing",
|
||||
"macros",
|
||||
] }
|
||||
tokio = { version = "1.48.0", features = ["full"] }
|
||||
toml = "0.9.8"
|
||||
uuid = { version = "1.18.1", features = ["serde", "v4", "v7"] }
|
||||
tokio = { version = "1.45.1", features = ["full"] }
|
||||
toml = "0.8.23"
|
||||
uuid = { version = "1.18.0", features = ["serde", "v4", "v7"] }
|
||||
serde_urlencoded = "0.7.1"
|
||||
termcolor = "1.4.1"
|
||||
url = { version = "2.5.7", features = ["serde"] }
|
||||
url = { version = "2.5.4", features = ["serde"] }
|
||||
tracing = "0.1.41"
|
||||
tracing-subscriber = { version = "0.3.20", features = ["json"] }
|
||||
tracing-trace = { version = "0.1.0", path = "../tracing-trace" }
|
||||
tracing-actix-web = "0.7.19"
|
||||
tracing-actix-web = "0.7.18"
|
||||
build-info = { version = "1.7.0", path = "../build-info" }
|
||||
roaring = "0.10.12"
|
||||
mopa-maintained = "0.2.3"
|
||||
@@ -114,35 +114,35 @@ utoipa = { version = "5.4.0", features = [
|
||||
utoipa-scalar = { version = "0.3.0", optional = true, features = ["actix-web"] }
|
||||
async-openai = { git = "https://github.com/meilisearch/async-openai", branch = "better-error-handling" }
|
||||
secrecy = "0.10.3"
|
||||
actix-web-lab = { version = "0.24.3", default-features = false }
|
||||
actix-web-lab = { version = "0.24.1", default-features = false }
|
||||
urlencoding = "2.1.3"
|
||||
backoff = { version = "0.4.0", features = ["tokio"] }
|
||||
humantime = { version = "2.3.0", default-features = false }
|
||||
|
||||
|
||||
[dev-dependencies]
|
||||
actix-rt = "2.11.0"
|
||||
brotli = "8.0.2"
|
||||
actix-rt = "2.10.0"
|
||||
brotli = "8.0.1"
|
||||
# fixed version due to format breakages in v1.40
|
||||
insta = { version = "=1.39.0", features = ["redactions"] }
|
||||
manifest-dir-macros = "0.1.18"
|
||||
maplit = "1.0.2"
|
||||
meili-snap = { path = "../meili-snap" }
|
||||
temp-env = "0.3.6"
|
||||
wiremock = "0.6.5"
|
||||
wiremock = "0.6.3"
|
||||
yaup = "0.3.1"
|
||||
|
||||
[build-dependencies]
|
||||
anyhow = { version = "1.0.100", optional = true }
|
||||
cargo_toml = { version = "0.22.3", optional = true }
|
||||
anyhow = { version = "1.0.98", optional = true }
|
||||
cargo_toml = { version = "0.22.1", optional = true }
|
||||
hex = { version = "0.4.3", optional = true }
|
||||
reqwest = { version = "0.12.24", features = [
|
||||
reqwest = { version = "0.12.20", features = [
|
||||
"blocking",
|
||||
"rustls-tls",
|
||||
], default-features = false, optional = true }
|
||||
sha-1 = { version = "0.10.1", optional = true }
|
||||
static-files = { version = "0.3.1", optional = true }
|
||||
tempfile = { version = "3.23.0", optional = true }
|
||||
zip = { version = "6.0.0", optional = true }
|
||||
static-files = { version = "0.2.5", optional = true }
|
||||
tempfile = { version = "3.20.0", optional = true }
|
||||
zip = { version = "4.1.0", optional = true }
|
||||
|
||||
[features]
|
||||
default = ["meilisearch-types/all-tokenizations", "mini-dashboard"]
|
||||
@@ -160,7 +160,6 @@ mini-dashboard = [
|
||||
]
|
||||
chinese = ["meilisearch-types/chinese"]
|
||||
chinese-pinyin = ["meilisearch-types/chinese-pinyin"]
|
||||
enterprise = ["meilisearch-types/enterprise"]
|
||||
hebrew = ["meilisearch-types/hebrew"]
|
||||
japanese = ["meilisearch-types/japanese"]
|
||||
korean = ["meilisearch-types/korean"]
|
||||
|
||||
@@ -195,7 +195,7 @@ struct Infos {
|
||||
experimental_enable_logs_route: bool,
|
||||
experimental_reduce_indexing_memory_usage: bool,
|
||||
experimental_max_number_of_batched_tasks: usize,
|
||||
experimental_limit_batched_tasks_total_size: Option<u64>,
|
||||
experimental_limit_batched_tasks_total_size: u64,
|
||||
experimental_network: bool,
|
||||
experimental_multimodal: bool,
|
||||
experimental_chat_completions: bool,
|
||||
@@ -359,7 +359,7 @@ impl Infos {
|
||||
http_payload_size_limit,
|
||||
experimental_max_number_of_batched_tasks,
|
||||
experimental_limit_batched_tasks_total_size:
|
||||
experimental_limit_batched_tasks_total_size.map(|size| size.as_u64()),
|
||||
experimental_limit_batched_tasks_total_size.into(),
|
||||
task_queue_webhook: task_webhook_url.is_some(),
|
||||
task_webhook_authorization_header: task_webhook_authorization_header.is_some(),
|
||||
log_level: log_level.to_string(),
|
||||
|
||||
@@ -230,17 +230,7 @@ pub fn setup_meilisearch(
|
||||
cleanup_enabled: !opt.experimental_replication_parameters,
|
||||
max_number_of_tasks: 1_000_000,
|
||||
max_number_of_batched_tasks: opt.experimental_max_number_of_batched_tasks,
|
||||
batched_tasks_size_limit: opt.experimental_limit_batched_tasks_total_size.map_or_else(
|
||||
|| {
|
||||
opt.indexer_options
|
||||
.max_indexing_memory
|
||||
// By default, we use half of the available memory to determine the size of batched tasks
|
||||
.map_or(u64::MAX, |mem| mem.as_u64() / 2)
|
||||
// And never exceed 10 GiB when we infer the limit
|
||||
.min(10 * 1024 * 1024 * 1024)
|
||||
},
|
||||
|size| size.as_u64(),
|
||||
),
|
||||
batched_tasks_size_limit: opt.experimental_limit_batched_tasks_total_size.into(),
|
||||
index_growth_amount: byte_unit::Byte::from_str("10GiB").unwrap().as_u64() as usize,
|
||||
index_count: DEFAULT_INDEX_COUNT,
|
||||
instance_features: opt.to_instance_features(),
|
||||
|
||||
@@ -1,8 +1,7 @@
|
||||
use lazy_static::lazy_static;
|
||||
use prometheus::{
|
||||
opts, register_gauge, register_gauge_vec, register_histogram_vec, register_int_counter_vec,
|
||||
register_int_gauge, register_int_gauge_vec, Gauge, GaugeVec, HistogramVec, IntCounterVec,
|
||||
IntGauge, IntGaugeVec,
|
||||
opts, register_gauge, register_histogram_vec, register_int_counter_vec, register_int_gauge,
|
||||
register_int_gauge_vec, Gauge, HistogramVec, IntCounterVec, IntGauge, IntGaugeVec,
|
||||
};
|
||||
|
||||
lazy_static! {
|
||||
@@ -74,20 +73,6 @@ lazy_static! {
|
||||
&["kind", "value"]
|
||||
)
|
||||
.expect("Can't create a metric");
|
||||
pub static ref MEILISEARCH_BATCH_RUNNING_PROGRESS_TRACE: GaugeVec = register_gauge_vec!(
|
||||
opts!("meilisearch_batch_running_progress_trace", "The currently running progress trace"),
|
||||
&["batch_uid", "step_name"]
|
||||
)
|
||||
.expect("Can't create a metric");
|
||||
pub static ref MEILISEARCH_LAST_FINISHED_BATCHES_PROGRESS_TRACE_MS: IntGaugeVec =
|
||||
register_int_gauge_vec!(
|
||||
opts!(
|
||||
"meilisearch_last_finished_batches_progress_trace_ms",
|
||||
"The last few batches progress trace in milliseconds"
|
||||
),
|
||||
&["batch_uid", "step_name"]
|
||||
)
|
||||
.expect("Can't create a metric");
|
||||
pub static ref MEILISEARCH_LAST_UPDATE: IntGauge =
|
||||
register_int_gauge!(opts!("meilisearch_last_update", "Meilisearch Last Update"))
|
||||
.expect("Can't create a metric");
|
||||
|
||||
@@ -473,14 +473,11 @@ pub struct Opt {
|
||||
#[serde(default = "default_limit_batched_tasks")]
|
||||
pub experimental_max_number_of_batched_tasks: usize,
|
||||
|
||||
/// Experimentally controls the maximum total size, in bytes, of tasks that will be processed
|
||||
/// simultaneously. When unspecified, defaults to half of the maximum indexing memory and
|
||||
/// clamped to 10 GiB.
|
||||
///
|
||||
/// See: <https://github.com/orgs/meilisearch/discussions/801>
|
||||
#[clap(long, env = MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS_TOTAL_SIZE)]
|
||||
#[serde(default)]
|
||||
pub experimental_limit_batched_tasks_total_size: Option<Byte>,
|
||||
/// Experimentally reduces the maximum total size, in bytes, of tasks that will be processed at once,
|
||||
/// see: <https://github.com/orgs/meilisearch/discussions/801>
|
||||
#[clap(long, env = MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS_TOTAL_SIZE, default_value_t = default_limit_batched_tasks_total_size())]
|
||||
#[serde(default = "default_limit_batched_tasks_total_size")]
|
||||
pub experimental_limit_batched_tasks_total_size: Byte,
|
||||
|
||||
/// Enables experimental caching of search query embeddings. The value represents the maximal number of entries in the cache of each
|
||||
/// distinct embedder.
|
||||
@@ -704,12 +701,10 @@ impl Opt {
|
||||
MEILI_EXPERIMENTAL_MAX_NUMBER_OF_BATCHED_TASKS,
|
||||
experimental_max_number_of_batched_tasks.to_string(),
|
||||
);
|
||||
if let Some(limit) = experimental_limit_batched_tasks_total_size {
|
||||
export_to_env_if_not_present(
|
||||
MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS_TOTAL_SIZE,
|
||||
limit.to_string(),
|
||||
);
|
||||
}
|
||||
export_to_env_if_not_present(
|
||||
MEILI_EXPERIMENTAL_LIMIT_BATCHED_TASKS_TOTAL_SIZE,
|
||||
experimental_limit_batched_tasks_total_size.to_string(),
|
||||
);
|
||||
export_to_env_if_not_present(
|
||||
MEILI_EXPERIMENTAL_EMBEDDING_CACHE_ENTRIES,
|
||||
experimental_embedding_cache_entries.to_string(),
|
||||
@@ -1278,6 +1273,10 @@ fn default_limit_batched_tasks() -> usize {
|
||||
usize::MAX
|
||||
}
|
||||
|
||||
fn default_limit_batched_tasks_total_size() -> Byte {
|
||||
Byte::from_u64(u64::MAX)
|
||||
}
|
||||
|
||||
fn default_embedding_cache_entries() -> usize {
|
||||
0
|
||||
}
|
||||
|
||||
@@ -1,14 +1,14 @@
|
||||
use std::time::Duration;
|
||||
|
||||
use meilisearch_types::error::{Code, ErrorCode, ResponseError};
|
||||
use meilisearch_types::milli::TimeBudget;
|
||||
use crate::search::{Personalize, SearchResult};
|
||||
use meilisearch_types::{
|
||||
error::{Code, ErrorCode, ResponseError},
|
||||
milli::TimeBudget,
|
||||
};
|
||||
use rand::Rng;
|
||||
use reqwest::Client;
|
||||
use serde::{Deserialize, Serialize};
|
||||
use std::time::Duration;
|
||||
use tracing::{debug, info, warn};
|
||||
|
||||
use crate::search::{Personalize, SearchResult};
|
||||
|
||||
const COHERE_API_URL: &str = "https://api.cohere.ai/v1/rerank";
|
||||
const MAX_RETRIES: u32 = 10;
|
||||
|
||||
|
||||
@@ -1,39 +0,0 @@
|
||||
pub mod proxy {
|
||||
|
||||
use std::fs::File;
|
||||
|
||||
use actix_web::HttpRequest;
|
||||
use index_scheduler::IndexScheduler;
|
||||
|
||||
use crate::error::MeilisearchHttpError;
|
||||
|
||||
pub enum Body<T: serde::Serialize> {
|
||||
NdJsonPayload,
|
||||
Inline(T),
|
||||
None,
|
||||
}
|
||||
|
||||
impl Body<()> {
|
||||
pub fn with_ndjson_payload(_file: File) -> Self {
|
||||
Self::NdJsonPayload
|
||||
}
|
||||
|
||||
pub fn none() -> Self {
|
||||
Self::None
|
||||
}
|
||||
}
|
||||
|
||||
pub const PROXY_ORIGIN_REMOTE_HEADER: &str = "Meili-Proxy-Origin-Remote";
|
||||
pub const PROXY_ORIGIN_TASK_UID_HEADER: &str = "Meili-Proxy-Origin-TaskUid";
|
||||
|
||||
pub async fn proxy<T: serde::Serialize>(
|
||||
_index_scheduler: &IndexScheduler,
|
||||
_index_uid: &str,
|
||||
_req: &HttpRequest,
|
||||
_network: meilisearch_types::network::Network,
|
||||
_body: Body<T>,
|
||||
_task: &meilisearch_types::tasks::Task,
|
||||
) -> Result<(), MeilisearchHttpError> {
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
@@ -45,7 +45,7 @@ use crate::extractors::authentication::policies::*;
|
||||
use crate::extractors::authentication::GuardedData;
|
||||
use crate::extractors::payload::Payload;
|
||||
use crate::extractors::sequential_extractor::SeqHandler;
|
||||
use crate::routes::indexes::current_edition::proxy::{proxy, Body};
|
||||
use crate::routes::indexes::enterprise_edition::proxy::{proxy, Body};
|
||||
use crate::routes::indexes::search::fix_sort_query_parameters;
|
||||
use crate::routes::{
|
||||
get_task_id, is_dry_run, PaginationView, SummarizedTaskView, PAGINATION_DEFAULT_LIMIT,
|
||||
@@ -367,7 +367,7 @@ pub async fn delete_document(
|
||||
.await??
|
||||
};
|
||||
|
||||
if network.sharding() && !dry_run {
|
||||
if network.sharding && !dry_run {
|
||||
proxy(&index_scheduler, &index_uid, &req, network, Body::none(), &task).await?;
|
||||
}
|
||||
|
||||
@@ -1098,7 +1098,7 @@ async fn document_addition(
|
||||
}
|
||||
};
|
||||
|
||||
if network.sharding() {
|
||||
if network.sharding {
|
||||
if let Some(file) = file {
|
||||
proxy(
|
||||
&index_scheduler,
|
||||
@@ -1222,7 +1222,7 @@ pub async fn delete_documents_batch(
|
||||
.await??
|
||||
};
|
||||
|
||||
if network.sharding() && !dry_run {
|
||||
if network.sharding && !dry_run {
|
||||
proxy(&index_scheduler, &index_uid, &req, network, Body::Inline(body), &task).await?;
|
||||
}
|
||||
|
||||
@@ -1320,7 +1320,7 @@ pub async fn delete_documents_by_filter(
|
||||
.await??
|
||||
};
|
||||
|
||||
if network.sharding() && !dry_run {
|
||||
if network.sharding && !dry_run {
|
||||
proxy(&index_scheduler, &index_uid, &req, network, Body::Inline(filter), &task).await?;
|
||||
}
|
||||
|
||||
@@ -1475,7 +1475,7 @@ pub async fn edit_documents_by_function(
|
||||
.await??
|
||||
};
|
||||
|
||||
if network.sharding() && !dry_run {
|
||||
if network.sharding && !dry_run {
|
||||
proxy(&index_scheduler, &index_uid, &req, network, Body::Inline(body), &task).await?;
|
||||
}
|
||||
|
||||
@@ -1549,7 +1549,7 @@ pub async fn clear_all_documents(
|
||||
.await??
|
||||
};
|
||||
|
||||
if network.sharding() && !dry_run {
|
||||
if network.sharding && !dry_run {
|
||||
proxy(&index_scheduler, &index_uid, &req, network, Body::none(), &task).await?;
|
||||
}
|
||||
|
||||
|
||||
@@ -52,7 +52,7 @@ pub async fn proxy<T: serde::Serialize>(
|
||||
index_scheduler: &IndexScheduler,
|
||||
index_uid: &str,
|
||||
req: &HttpRequest,
|
||||
network: meilisearch_types::network::Network,
|
||||
network: meilisearch_types::enterprise_edition::network::Network,
|
||||
body: Body<T>,
|
||||
task: &meilisearch_types::tasks::Task,
|
||||
) -> Result<(), MeilisearchHttpError> {
|
||||
|
||||
@@ -30,16 +30,7 @@ use crate::Opt;
|
||||
|
||||
pub mod compact;
|
||||
pub mod documents;
|
||||
|
||||
#[cfg(not(feature = "enterprise"))]
|
||||
mod community_edition;
|
||||
#[cfg(feature = "enterprise")]
|
||||
mod enterprise_edition;
|
||||
#[cfg(not(feature = "enterprise"))]
|
||||
use community_edition as current_edition;
|
||||
#[cfg(feature = "enterprise")]
|
||||
use enterprise_edition as current_edition;
|
||||
|
||||
pub mod facet_search;
|
||||
pub mod search;
|
||||
mod search_analytics;
|
||||
@@ -50,7 +41,7 @@ mod settings_analytics;
|
||||
pub mod similar;
|
||||
mod similar_analytics;
|
||||
|
||||
pub use current_edition::proxy::{PROXY_ORIGIN_REMOTE_HEADER, PROXY_ORIGIN_TASK_UID_HEADER};
|
||||
pub use enterprise_edition::proxy::{PROXY_ORIGIN_REMOTE_HEADER, PROXY_ORIGIN_TASK_UID_HEADER};
|
||||
|
||||
#[derive(OpenApi)]
|
||||
#[openapi(
|
||||
|
||||
@@ -4,7 +4,6 @@ use index_scheduler::{IndexScheduler, Query};
|
||||
use meilisearch_auth::AuthController;
|
||||
use meilisearch_types::error::ResponseError;
|
||||
use meilisearch_types::keys::actions;
|
||||
use meilisearch_types::milli::progress::ProgressStepView;
|
||||
use meilisearch_types::tasks::Status;
|
||||
use prometheus::{Encoder, TextEncoder};
|
||||
use time::OffsetDateTime;
|
||||
@@ -39,12 +38,6 @@ pub fn configure(config: &mut web::ServiceConfig) {
|
||||
# HELP meilisearch_db_size_bytes Meilisearch DB Size In Bytes
|
||||
# TYPE meilisearch_db_size_bytes gauge
|
||||
meilisearch_db_size_bytes 1130496
|
||||
# HELP meilisearch_batch_running_progress_trace The currently running progress trace
|
||||
# TYPE meilisearch_batch_running_progress_trace gauge
|
||||
meilisearch_batch_running_progress_trace{batch_uid="0",step_name="document"} 0.710618582519409
|
||||
meilisearch_batch_running_progress_trace{batch_uid="0",step_name="extracting word proximity"} 0.2222222222222222
|
||||
meilisearch_batch_running_progress_trace{batch_uid="0",step_name="indexing"} 0.6666666666666666
|
||||
meilisearch_batch_running_progress_trace{batch_uid="0",step_name="processing tasks"} 0
|
||||
# HELP meilisearch_http_requests_total Meilisearch HTTP requests total
|
||||
# TYPE meilisearch_http_requests_total counter
|
||||
meilisearch_http_requests_total{method="GET",path="/metrics",status="400"} 1
|
||||
@@ -68,13 +61,6 @@ meilisearch_http_response_time_seconds_bucket{method="GET",path="/metrics",le="1
|
||||
meilisearch_http_response_time_seconds_bucket{method="GET",path="/metrics",le="+Inf"} 0
|
||||
meilisearch_http_response_time_seconds_sum{method="GET",path="/metrics"} 0
|
||||
meilisearch_http_response_time_seconds_count{method="GET",path="/metrics"} 0
|
||||
# HELP meilisearch_last_finished_batches_progress_trace_ms The last few batches progress trace in milliseconds
|
||||
# TYPE meilisearch_last_finished_batches_progress_trace_ms gauge
|
||||
meilisearch_last_finished_batches_progress_trace_ms{batch_uid="0",step_name="processing tasks"} 19360
|
||||
meilisearch_last_finished_batches_progress_trace_ms{batch_uid="0",step_name="processing tasks > computing document changes"} 368
|
||||
meilisearch_last_finished_batches_progress_trace_ms{batch_uid="0",step_name="processing tasks > computing document changes > preparing payloads"} 367
|
||||
meilisearch_last_finished_batches_progress_trace_ms{batch_uid="0",step_name="processing tasks > computing document changes > preparing payloads > payload"} 367
|
||||
meilisearch_last_finished_batches_progress_trace_ms{batch_uid="0",step_name="processing tasks > indexing"} 18970
|
||||
# HELP meilisearch_index_count Meilisearch Index Count
|
||||
# TYPE meilisearch_index_count gauge
|
||||
meilisearch_index_count 1
|
||||
@@ -162,50 +148,6 @@ pub async fn get_metrics(
|
||||
}
|
||||
}
|
||||
|
||||
// Fetch and expose the current progressing step
|
||||
crate::metrics::MEILISEARCH_BATCH_RUNNING_PROGRESS_TRACE.reset();
|
||||
let (batches, _total) = index_scheduler.get_batches_from_authorized_indexes(
|
||||
&Query { statuses: Some(vec![Status::Processing]), ..Query::default() },
|
||||
auth_filters,
|
||||
)?;
|
||||
if let Some(batch) = batches.into_iter().next() {
|
||||
let batch_uid = batch.uid.to_string();
|
||||
if let Some(progress) = batch.progress {
|
||||
for ProgressStepView { current_step, finished, total } in progress.steps {
|
||||
crate::metrics::MEILISEARCH_BATCH_RUNNING_PROGRESS_TRACE
|
||||
.with_label_values(&[batch_uid.as_str(), current_step.as_ref()])
|
||||
// We return the completion ratio of the current step
|
||||
.set(finished as f64 / total as f64);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
crate::metrics::MEILISEARCH_LAST_FINISHED_BATCHES_PROGRESS_TRACE_MS.reset();
|
||||
let (batches, _total) = index_scheduler.get_batches_from_authorized_indexes(
|
||||
// Fetch the finished batches...
|
||||
&Query {
|
||||
statuses: Some(vec![Status::Succeeded, Status::Failed]),
|
||||
limit: Some(1),
|
||||
..Query::default()
|
||||
},
|
||||
auth_filters,
|
||||
)?;
|
||||
// ...and get the last batch only.
|
||||
if let Some(batch) = batches.into_iter().next() {
|
||||
let batch_uid = batch.uid.to_string();
|
||||
for (step_name, duration_str) in batch.stats.progress_trace {
|
||||
let Some(duration_str) = duration_str.as_str() else { continue };
|
||||
match humantime::parse_duration(duration_str) {
|
||||
Ok(duration) => {
|
||||
crate::metrics::MEILISEARCH_LAST_FINISHED_BATCHES_PROGRESS_TRACE_MS
|
||||
.with_label_values(&[&batch_uid, &step_name])
|
||||
.set(duration.as_millis() as i64);
|
||||
}
|
||||
Err(e) => tracing::error!("Failed to parse duration: {e}"),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if let Some(last_update) = response.last_update {
|
||||
crate::metrics::MEILISEARCH_LAST_UPDATE.set(last_update.unix_timestamp());
|
||||
}
|
||||
|
||||
@@ -7,6 +7,7 @@ use deserr::Deserr;
|
||||
use index_scheduler::IndexScheduler;
|
||||
use itertools::{EitherOrBoth, Itertools};
|
||||
use meilisearch_types::deserr::DeserrJsonError;
|
||||
use meilisearch_types::enterprise_edition::network::{Network as DbNetwork, Remote as DbRemote};
|
||||
use meilisearch_types::error::deserr_codes::{
|
||||
InvalidNetworkRemotes, InvalidNetworkSearchApiKey, InvalidNetworkSelf, InvalidNetworkSharding,
|
||||
InvalidNetworkUrl, InvalidNetworkWriteApiKey,
|
||||
@@ -14,7 +15,6 @@ use meilisearch_types::error::deserr_codes::{
|
||||
use meilisearch_types::error::ResponseError;
|
||||
use meilisearch_types::keys::actions;
|
||||
use meilisearch_types::milli::update::Setting;
|
||||
use meilisearch_types::network::{Network as DbNetwork, Remote as DbRemote};
|
||||
use serde::Serialize;
|
||||
use tracing::debug;
|
||||
use utoipa::{OpenApi, ToSchema};
|
||||
@@ -211,16 +211,6 @@ async fn patch_network(
|
||||
let old_network = index_scheduler.network();
|
||||
debug!(parameters = ?new_network, "Patch network");
|
||||
|
||||
#[cfg(not(feature = "enterprise"))]
|
||||
if new_network.sharding.set().is_some() {
|
||||
use meilisearch_types::error::Code;
|
||||
|
||||
return Err(ResponseError::from_msg(
|
||||
"Meilisearch Enterprise Edition is required to set `network.sharding`".into(),
|
||||
Code::RequiresEnterpriseEdition,
|
||||
));
|
||||
}
|
||||
|
||||
let merged_self = match new_network.local {
|
||||
Setting::Set(new_self) => Some(new_self),
|
||||
Setting::Reset => None,
|
||||
@@ -322,7 +312,6 @@ async fn patch_network(
|
||||
|
||||
let merged_network =
|
||||
DbNetwork { local: merged_self, remotes: merged_remotes, sharding: merged_sharding };
|
||||
|
||||
index_scheduler.put_network(merged_network.clone())?;
|
||||
debug!(returns = ?merged_network, "Patch network");
|
||||
Ok(HttpResponse::Ok().json(merged_network))
|
||||
|
||||
@@ -9,12 +9,12 @@ use std::vec::{IntoIter, Vec};
|
||||
use actix_http::StatusCode;
|
||||
use index_scheduler::{IndexScheduler, RoFeatures};
|
||||
use itertools::Itertools;
|
||||
use meilisearch_types::enterprise_edition::network::{Network, Remote};
|
||||
use meilisearch_types::error::ResponseError;
|
||||
use meilisearch_types::milli::order_by_map::OrderByMap;
|
||||
use meilisearch_types::milli::score_details::{ScoreDetails, WeightedScoreValue};
|
||||
use meilisearch_types::milli::vector::Embedding;
|
||||
use meilisearch_types::milli::{self, DocumentId, OrderBy, TimeBudget, DEFAULT_VALUES_PER_FACET};
|
||||
use meilisearch_types::network::{Network, Remote};
|
||||
use roaring::RoaringBitmap;
|
||||
use tokio::task::JoinHandle;
|
||||
use uuid::Uuid;
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
pub use error::ProxySearchError;
|
||||
use error::ReqwestErrorWithoutUrl;
|
||||
use meilisearch_types::network::Remote;
|
||||
use meilisearch_types::enterprise_edition::network::Remote;
|
||||
use rand::Rng as _;
|
||||
use reqwest::{Client, Response, StatusCode};
|
||||
use serde::de::DeserializeOwned;
|
||||
|
||||
@@ -18,9 +18,10 @@ use serde::{Deserialize, Serialize};
|
||||
use utoipa::ToSchema;
|
||||
use uuid::Uuid;
|
||||
|
||||
use crate::search::SearchMetadata;
|
||||
|
||||
use super::super::{ComputedFacets, FacetStats, HitsInfo, SearchHit, SearchQueryWithIndex};
|
||||
use crate::milli::vector::Embedding;
|
||||
use crate::search::SearchMetadata;
|
||||
|
||||
pub const DEFAULT_FEDERATED_WEIGHT: f64 = 1.0;
|
||||
|
||||
|
||||
@@ -1339,266 +1339,3 @@ async fn get_document_with_vectors() {
|
||||
}
|
||||
"###);
|
||||
}
|
||||
|
||||
#[actix_rt::test]
|
||||
async fn test_fetch_documents_pagination_with_sorting() {
|
||||
let server = Server::new_shared();
|
||||
let index = server.unique_index();
|
||||
let (task, _code) = index.create(None).await;
|
||||
server.wait_task(task.uid()).await.succeeded();
|
||||
|
||||
// Set name as sortable attribute
|
||||
let (task, code) = index.update_settings_sortable_attributes(json!(["name"])).await;
|
||||
assert_eq!(code, 202);
|
||||
server.wait_task(task.uid()).await.succeeded();
|
||||
|
||||
let documents = json!((0..50)
|
||||
.map(|i| json!({"id": i, "name": format!("doc_{:05}", std::cmp::min(i, 5))}))
|
||||
.collect::<Vec<_>>());
|
||||
|
||||
// Add documents as described in the bug report
|
||||
let (task, code) = index.add_documents(documents, None).await;
|
||||
assert_eq!(code, 202);
|
||||
server.wait_task(task.uid()).await.succeeded();
|
||||
|
||||
// Request 1 (first page): offset 0, limit 2
|
||||
let (response, code) = index
|
||||
.fetch_documents(json!({
|
||||
"offset": 0,
|
||||
"limit": 2,
|
||||
"sort": ["name:asc"]
|
||||
}))
|
||||
.await;
|
||||
assert_eq!(code, 200);
|
||||
let results = response["results"].as_array().unwrap();
|
||||
snapshot!(json_string!(results), @r###"
|
||||
[
|
||||
{
|
||||
"id": 0,
|
||||
"name": "doc_00000"
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"name": "doc_00001"
|
||||
}
|
||||
]
|
||||
"###);
|
||||
|
||||
// Request 2 (second page): offset 2, limit 2
|
||||
let (response, code) = index
|
||||
.fetch_documents(json!({
|
||||
"offset": 2,
|
||||
"limit": 2,
|
||||
"sort": ["name:asc"]
|
||||
}))
|
||||
.await;
|
||||
assert_eq!(code, 200);
|
||||
let results = response["results"].as_array().unwrap();
|
||||
snapshot!(json_string!(results), @r###"
|
||||
[
|
||||
{
|
||||
"id": 2,
|
||||
"name": "doc_00002"
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"name": "doc_00003"
|
||||
}
|
||||
]
|
||||
"###);
|
||||
|
||||
// Request 3 (third page): offset 4, limit 2
|
||||
let (response, code) = index
|
||||
.fetch_documents(json!({
|
||||
"offset": 4,
|
||||
"limit": 2,
|
||||
"sort": ["name:asc"]
|
||||
}))
|
||||
.await;
|
||||
assert_eq!(code, 200);
|
||||
let results = response["results"].as_array().unwrap();
|
||||
snapshot!(json_string!(results), @r###"
|
||||
[
|
||||
{
|
||||
"id": 4,
|
||||
"name": "doc_00004"
|
||||
},
|
||||
{
|
||||
"id": 5,
|
||||
"name": "doc_00005"
|
||||
}
|
||||
]
|
||||
"###);
|
||||
|
||||
// Request 4 (fourth page): offset 6, limit 2
|
||||
let (response, code) = index
|
||||
.fetch_documents(json!({
|
||||
"offset": 6,
|
||||
"limit": 2,
|
||||
"sort": ["name:asc"]
|
||||
}))
|
||||
.await;
|
||||
assert_eq!(code, 200);
|
||||
let results = response["results"].as_array().unwrap();
|
||||
snapshot!(json_string!(results), @r###"
|
||||
[
|
||||
{
|
||||
"id": 6,
|
||||
"name": "doc_00005"
|
||||
},
|
||||
{
|
||||
"id": 7,
|
||||
"name": "doc_00005"
|
||||
}
|
||||
]
|
||||
"###);
|
||||
}
|
||||
|
||||
// <https://github.com/meilisearch/meilisearch/issues/5998>
|
||||
#[actix_rt::test]
|
||||
async fn get_document_sort_field_not_in_any_document() {
|
||||
let server = Server::new_shared();
|
||||
let index = server.unique_index();
|
||||
let (task, _code) = index.create(None).await;
|
||||
server.wait_task(task.uid()).await.succeeded();
|
||||
|
||||
let (task, _code) = index.update_settings_sortable_attributes(json!(["created_at"])).await;
|
||||
server.wait_task(task.uid()).await.succeeded();
|
||||
|
||||
let documents = json!([
|
||||
{ "id": 1, "name": "Document 1" },
|
||||
{ "id": 2, "name": "Document 2" }
|
||||
]);
|
||||
let (task, _code) = index.add_documents(documents, None).await;
|
||||
server.wait_task(task.uid()).await.succeeded();
|
||||
|
||||
let (response, code) = index
|
||||
.fetch_documents(json!({
|
||||
"sort": ["created_at:asc"]
|
||||
}))
|
||||
.await;
|
||||
|
||||
snapshot!(code, @"200 OK");
|
||||
snapshot!(json_string!(response), @r###"
|
||||
{
|
||||
"results": [
|
||||
{
|
||||
"id": 1,
|
||||
"name": "Document 1"
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"name": "Document 2"
|
||||
}
|
||||
],
|
||||
"offset": 0,
|
||||
"limit": 20,
|
||||
"total": 2
|
||||
}
|
||||
"###);
|
||||
}
|
||||
|
||||
#[actix_rt::test]
|
||||
async fn get_document_sort_includes_docs_without_field() {
|
||||
let server = Server::new_shared();
|
||||
let index = server.unique_index();
|
||||
let (task, _code) = index.create(None).await;
|
||||
server.wait_task(task.uid()).await.succeeded();
|
||||
|
||||
let (task, _code) = index.update_settings_sortable_attributes(json!(["created_at"])).await;
|
||||
server.wait_task(task.uid()).await.succeeded();
|
||||
|
||||
let documents = json!([
|
||||
{ "id": 1, "name": "Doc without created_at" },
|
||||
{ "id": 2, "name": "Doc with created_at", "created_at": "2025-01-15" },
|
||||
{ "id": 3, "name": "Another doc without created_at" },
|
||||
{ "id": 4, "name": "Another doc with created_at", "created_at": "2025-01-10" }
|
||||
]);
|
||||
let (task, _code) = index.add_documents(documents, None).await;
|
||||
server.wait_task(task.uid()).await.succeeded();
|
||||
|
||||
let (response, code) = index
|
||||
.fetch_documents(json!({
|
||||
"sort": ["created_at:asc"]
|
||||
}))
|
||||
.await;
|
||||
|
||||
snapshot!(code, @"200 OK");
|
||||
snapshot!(json_string!(response), @r###"
|
||||
{
|
||||
"results": [
|
||||
{
|
||||
"id": 4,
|
||||
"name": "Another doc with created_at",
|
||||
"created_at": "2025-01-10"
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"name": "Doc with created_at",
|
||||
"created_at": "2025-01-15"
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"name": "Doc without created_at"
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"name": "Another doc without created_at"
|
||||
}
|
||||
],
|
||||
"offset": 0,
|
||||
"limit": 20,
|
||||
"total": 4
|
||||
}
|
||||
"###);
|
||||
}
|
||||
|
||||
#[actix_rt::test]
|
||||
async fn get_document_sort_desc_includes_docs_without_field() {
|
||||
let server = Server::new_shared();
|
||||
let index = server.unique_index();
|
||||
let (task, _code) = index.create(None).await;
|
||||
server.wait_task(task.uid()).await.succeeded();
|
||||
|
||||
let (task, _code) = index.update_settings_sortable_attributes(json!(["priority"])).await;
|
||||
server.wait_task(task.uid()).await.succeeded();
|
||||
|
||||
let documents = json!([
|
||||
{ "id": 1, "name": "Low priority", "priority": 1 },
|
||||
{ "id": 2, "name": "No priority" },
|
||||
{ "id": 3, "name": "High priority", "priority": 10 }
|
||||
]);
|
||||
let (task, _code) = index.add_documents(documents, None).await;
|
||||
server.wait_task(task.uid()).await.succeeded();
|
||||
|
||||
let (response, code) = index
|
||||
.fetch_documents(json!({
|
||||
"sort": ["priority:desc"]
|
||||
}))
|
||||
.await;
|
||||
|
||||
snapshot!(code, @"200 OK");
|
||||
snapshot!(json_string!(response), @r###"
|
||||
{
|
||||
"results": [
|
||||
{
|
||||
"id": 3,
|
||||
"name": "High priority",
|
||||
"priority": 10
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"name": "Low priority",
|
||||
"priority": 1
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"name": "No priority"
|
||||
}
|
||||
],
|
||||
"offset": 0,
|
||||
"limit": 20,
|
||||
"total": 3
|
||||
}
|
||||
"###);
|
||||
}
|
||||
|
||||
@@ -3142,7 +3142,6 @@ fn fail(override_response_body: Option<&str>) -> ResponseTemplate {
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(feature = "enterprise")]
|
||||
#[actix_rt::test]
|
||||
async fn remote_auto_sharding() {
|
||||
let ms0 = Server::new().await;
|
||||
@@ -3162,6 +3161,7 @@ async fn remote_auto_sharding() {
|
||||
snapshot!(json_string!(response["network"]), @"true");
|
||||
|
||||
// set self & sharding
|
||||
|
||||
let (response, code) = ms0.set_network(json!({"self": "ms0", "sharding": true})).await;
|
||||
snapshot!(code, @"200 OK");
|
||||
snapshot!(json_string!(response), @r###"
|
||||
@@ -3462,30 +3462,6 @@ async fn remote_auto_sharding() {
|
||||
"###);
|
||||
}
|
||||
|
||||
#[cfg(not(feature = "enterprise"))]
|
||||
#[actix_rt::test]
|
||||
async fn sharding_not_enterprise() {
|
||||
let ms0 = Server::new().await;
|
||||
|
||||
// enable feature
|
||||
|
||||
let (response, code) = ms0.set_features(json!({"network": true})).await;
|
||||
snapshot!(code, @"200 OK");
|
||||
snapshot!(json_string!(response["network"]), @"true");
|
||||
|
||||
let (response, code) = ms0.set_network(json!({"self": "ms0", "sharding": true})).await;
|
||||
snapshot!(code, @"451 Unavailable For Legal Reasons");
|
||||
snapshot!(json_string!(response), @r###"
|
||||
{
|
||||
"message": "Meilisearch Enterprise Edition is required to set `network.sharding`",
|
||||
"code": "requires_enterprise_edition",
|
||||
"type": "invalid_request",
|
||||
"link": "https://docs.meilisearch.com/errors#requires_enterprise_edition"
|
||||
}
|
||||
"###);
|
||||
}
|
||||
|
||||
#[cfg(feature = "enterprise")]
|
||||
#[actix_rt::test]
|
||||
async fn remote_auto_sharding_with_custom_metadata() {
|
||||
let ms0 = Server::new().await;
|
||||
|
||||
@@ -197,7 +197,7 @@ test_setting_routes!(
|
||||
{
|
||||
setting: vector_store,
|
||||
update_verb: patch,
|
||||
default_value: "experimental"
|
||||
default_value: null
|
||||
},
|
||||
);
|
||||
|
||||
|
||||
@@ -2,7 +2,6 @@ mod chat;
|
||||
mod distinct;
|
||||
mod errors;
|
||||
mod get_settings;
|
||||
mod parent_seachable_fields;
|
||||
mod prefix_search_settings;
|
||||
mod proximity_settings;
|
||||
mod tokenizer_customization;
|
||||
|
||||
@@ -1,114 +0,0 @@
|
||||
use meili_snap::{json_string, snapshot};
|
||||
use once_cell::sync::Lazy;
|
||||
|
||||
use crate::common::Server;
|
||||
use crate::json;
|
||||
|
||||
static DOCUMENTS: Lazy<crate::common::Value> = Lazy::new(|| {
|
||||
json!([
|
||||
{
|
||||
"id": 1,
|
||||
"meta": {
|
||||
"title": "Soup of the day",
|
||||
"description": "many the fish",
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"meta": {
|
||||
"title": "Soup of day",
|
||||
"description": "many the lazy fish",
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"meta": {
|
||||
"title": "the Soup of day",
|
||||
"description": "many the fish",
|
||||
}
|
||||
},
|
||||
])
|
||||
});
|
||||
|
||||
#[actix_rt::test]
|
||||
async fn nested_field_becomes_searchable() {
|
||||
let server = Server::new_shared();
|
||||
let index = server.unique_index();
|
||||
|
||||
let (task, _status_code) = index.add_documents(DOCUMENTS.clone(), None).await;
|
||||
server.wait_task(task.uid()).await.succeeded();
|
||||
|
||||
let (response, code) = index
|
||||
.update_settings(json!({
|
||||
"searchableAttributes": ["meta.title"]
|
||||
}))
|
||||
.await;
|
||||
assert_eq!("202", code.as_str(), "{response:?}");
|
||||
server.wait_task(response.uid()).await.succeeded();
|
||||
|
||||
// We expect no documents when searching for
|
||||
// a nested non-searchable field
|
||||
index
|
||||
.search(json!({"q": "many fish"}), |response, code| {
|
||||
snapshot!(code, @"200 OK");
|
||||
snapshot!(json_string!(response["hits"]), @r###"[]"###);
|
||||
})
|
||||
.await;
|
||||
|
||||
let (response, code) = index
|
||||
.update_settings(json!({
|
||||
"searchableAttributes": ["meta.title", "meta.description"]
|
||||
}))
|
||||
.await;
|
||||
assert_eq!("202", code.as_str(), "{response:?}");
|
||||
server.wait_task(response.uid()).await.succeeded();
|
||||
|
||||
// We expect all the documents when the nested field becomes searchable
|
||||
index
|
||||
.search(json!({"q": "many fish"}), |response, code| {
|
||||
snapshot!(code, @"200 OK");
|
||||
snapshot!(json_string!(response["hits"]), @r###"
|
||||
[
|
||||
{
|
||||
"id": 1,
|
||||
"meta": {
|
||||
"title": "Soup of the day",
|
||||
"description": "many the fish"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
"meta": {
|
||||
"title": "the Soup of day",
|
||||
"description": "many the fish"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"meta": {
|
||||
"title": "Soup of day",
|
||||
"description": "many the lazy fish"
|
||||
}
|
||||
}
|
||||
]
|
||||
"###);
|
||||
})
|
||||
.await;
|
||||
|
||||
let (response, code) = index
|
||||
.update_settings(json!({
|
||||
"searchableAttributes": ["meta.title"]
|
||||
}))
|
||||
.await;
|
||||
assert_eq!("202", code.as_str(), "{response:?}");
|
||||
server.wait_task(response.uid()).await.succeeded();
|
||||
|
||||
// We expect no documents when searching for
|
||||
// a nested non-searchable field
|
||||
index
|
||||
.search(json!({"q": "many fish"}), |response, code| {
|
||||
snapshot!(code, @"200 OK");
|
||||
snapshot!(json_string!(response["hits"]), @r###"[]"###);
|
||||
})
|
||||
.await;
|
||||
}
|
||||
@@ -42,16 +42,8 @@ async fn version_too_old() {
|
||||
std::fs::create_dir_all(&db_path).unwrap();
|
||||
std::fs::write(db_path.join("VERSION"), "1.11.9999").unwrap();
|
||||
let options = Opt { experimental_dumpless_upgrade: true, ..default_settings };
|
||||
let err = Server::new_with_options(options).await.map(|_| ()).unwrap_err().to_string();
|
||||
|
||||
let major = meilisearch_types::versioning::VERSION_MAJOR;
|
||||
let minor = meilisearch_types::versioning::VERSION_MINOR;
|
||||
let patch = meilisearch_types::versioning::VERSION_PATCH;
|
||||
|
||||
let current_version = format!("{major}.{minor}.{patch}");
|
||||
let err = err.replace(¤t_version, "[current version]");
|
||||
|
||||
snapshot!(err, @"Database version 1.11.9999 is too old for the experimental dumpless upgrade feature. Please generate a dump using the v1.11.9999 and import it in the v[current version]");
|
||||
let err = Server::new_with_options(options).await.map(|_| ()).unwrap_err();
|
||||
snapshot!(err, @"Database version 1.11.9999 is too old for the experimental dumpless upgrade feature. Please generate a dump using the v1.11.9999 and import it in the v1.26.0");
|
||||
}
|
||||
|
||||
#[actix_rt::test]
|
||||
@@ -62,21 +54,11 @@ async fn version_requires_downgrade() {
|
||||
std::fs::create_dir_all(&db_path).unwrap();
|
||||
let major = meilisearch_types::versioning::VERSION_MAJOR;
|
||||
let minor = meilisearch_types::versioning::VERSION_MINOR;
|
||||
let mut patch = meilisearch_types::versioning::VERSION_PATCH;
|
||||
|
||||
let current_version = format!("{major}.{minor}.{patch}");
|
||||
patch += 1;
|
||||
let future_version = format!("{major}.{minor}.{patch}");
|
||||
|
||||
std::fs::write(db_path.join("VERSION"), &future_version).unwrap();
|
||||
let patch = meilisearch_types::versioning::VERSION_PATCH + 1;
|
||||
std::fs::write(db_path.join("VERSION"), format!("{major}.{minor}.{patch}")).unwrap();
|
||||
let options = Opt { experimental_dumpless_upgrade: true, ..default_settings };
|
||||
let err = Server::new_with_options(options).await.map(|_| ()).unwrap_err();
|
||||
|
||||
let err = err.to_string();
|
||||
let err = err.replace(¤t_version, "[current version]");
|
||||
let err = err.replace(&future_version, "[future version]");
|
||||
|
||||
snapshot!(err, @"Database version [future version] is higher than the Meilisearch version [current version]. Downgrade is not supported");
|
||||
snapshot!(err, @"Database version 1.26.1 is higher than the Meilisearch version 1.26.0. Downgrade is not supported");
|
||||
}
|
||||
|
||||
#[actix_rt::test]
|
||||
|
||||
@@ -8,7 +8,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
|
||||
"progress": null,
|
||||
"details": {
|
||||
"upgradeFrom": "v1.12.0",
|
||||
"upgradeTo": "[current version]"
|
||||
"upgradeTo": "v1.26.0"
|
||||
},
|
||||
"stats": {
|
||||
"totalNbTasks": 1,
|
||||
|
||||
@@ -8,7 +8,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
|
||||
"progress": null,
|
||||
"details": {
|
||||
"upgradeFrom": "v1.12.0",
|
||||
"upgradeTo": "[current version]"
|
||||
"upgradeTo": "v1.26.0"
|
||||
},
|
||||
"stats": {
|
||||
"totalNbTasks": 1,
|
||||
|
||||
@@ -8,7 +8,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
|
||||
"progress": null,
|
||||
"details": {
|
||||
"upgradeFrom": "v1.12.0",
|
||||
"upgradeTo": "[current version]"
|
||||
"upgradeTo": "v1.26.0"
|
||||
},
|
||||
"stats": {
|
||||
"totalNbTasks": 1,
|
||||
|
||||
@@ -12,7 +12,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
|
||||
"canceledBy": null,
|
||||
"details": {
|
||||
"upgradeFrom": "v1.12.0",
|
||||
"upgradeTo": "[current version]"
|
||||
"upgradeTo": "v1.26.0"
|
||||
},
|
||||
"error": null,
|
||||
"duration": "[duration]",
|
||||
|
||||
@@ -12,7 +12,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
|
||||
"canceledBy": null,
|
||||
"details": {
|
||||
"upgradeFrom": "v1.12.0",
|
||||
"upgradeTo": "[current version]"
|
||||
"upgradeTo": "v1.26.0"
|
||||
},
|
||||
"error": null,
|
||||
"duration": "[duration]",
|
||||
|
||||
@@ -12,7 +12,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
|
||||
"canceledBy": null,
|
||||
"details": {
|
||||
"upgradeFrom": "v1.12.0",
|
||||
"upgradeTo": "[current version]"
|
||||
"upgradeTo": "v1.26.0"
|
||||
},
|
||||
"error": null,
|
||||
"duration": "[duration]",
|
||||
|
||||
@@ -8,7 +8,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
|
||||
"progress": null,
|
||||
"details": {
|
||||
"upgradeFrom": "v1.12.0",
|
||||
"upgradeTo": "[current version]"
|
||||
"upgradeTo": "v1.26.0"
|
||||
},
|
||||
"stats": {
|
||||
"totalNbTasks": 1,
|
||||
|
||||
@@ -12,7 +12,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
|
||||
"canceledBy": null,
|
||||
"details": {
|
||||
"upgradeFrom": "v1.12.0",
|
||||
"upgradeTo": "[current version]"
|
||||
"upgradeTo": "v1.26.0"
|
||||
},
|
||||
"error": null,
|
||||
"duration": "[duration]",
|
||||
|
||||
@@ -166,55 +166,55 @@ async fn check_the_index_scheduler(server: &Server) {
|
||||
// We rewrite the first task for all calls because it may be the upgrade database with unknown dates and duration.
|
||||
// The other tasks should NOT change
|
||||
let (tasks, _) = server.tasks_filter("limit=1000").await;
|
||||
snapshot!(json_string!(tasks, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "the_whole_task_queue_once_everything_has_been_processed");
|
||||
snapshot!(json_string!(tasks, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "the_whole_task_queue_once_everything_has_been_processed");
|
||||
let (batches, _) = server.batches_filter("limit=1000").await;
|
||||
snapshot!(json_string!(batches, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "the_whole_batch_queue_once_everything_has_been_processed");
|
||||
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "the_whole_batch_queue_once_everything_has_been_processed");
|
||||
|
||||
// Tests all the tasks query parameters
|
||||
let (tasks, _) = server.tasks_filter("uids=10").await;
|
||||
snapshot!(json_string!(tasks, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "tasks_filter_uids_equal_10");
|
||||
snapshot!(json_string!(tasks, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "tasks_filter_uids_equal_10");
|
||||
let (tasks, _) = server.tasks_filter("batchUids=10").await;
|
||||
snapshot!(json_string!(tasks, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "tasks_filter_batchUids_equal_10");
|
||||
snapshot!(json_string!(tasks, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "tasks_filter_batchUids_equal_10");
|
||||
let (tasks, _) = server.tasks_filter("statuses=canceled").await;
|
||||
snapshot!(json_string!(tasks, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "tasks_filter_statuses_equal_canceled");
|
||||
snapshot!(json_string!(tasks, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "tasks_filter_statuses_equal_canceled");
|
||||
// types has already been tested above to retrieve the upgrade database
|
||||
let (tasks, _) = server.tasks_filter("canceledBy=19").await;
|
||||
snapshot!(json_string!(tasks, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "tasks_filter_canceledBy_equal_19");
|
||||
snapshot!(json_string!(tasks, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "tasks_filter_canceledBy_equal_19");
|
||||
let (tasks, _) = server.tasks_filter("beforeEnqueuedAt=2025-01-16T16:47:41Z").await;
|
||||
snapshot!(json_string!(tasks, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "tasks_filter_beforeEnqueuedAt_equal_2025-01-16T16_47_41");
|
||||
snapshot!(json_string!(tasks, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "tasks_filter_beforeEnqueuedAt_equal_2025-01-16T16_47_41");
|
||||
let (tasks, _) = server.tasks_filter("afterEnqueuedAt=2025-01-16T16:47:41Z").await;
|
||||
snapshot!(json_string!(tasks, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "tasks_filter_afterEnqueuedAt_equal_2025-01-16T16_47_41");
|
||||
snapshot!(json_string!(tasks, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "tasks_filter_afterEnqueuedAt_equal_2025-01-16T16_47_41");
|
||||
let (tasks, _) = server.tasks_filter("beforeStartedAt=2025-01-16T16:47:41Z").await;
|
||||
snapshot!(json_string!(tasks, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "tasks_filter_beforeStartedAt_equal_2025-01-16T16_47_41");
|
||||
snapshot!(json_string!(tasks, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "tasks_filter_beforeStartedAt_equal_2025-01-16T16_47_41");
|
||||
let (tasks, _) = server.tasks_filter("afterStartedAt=2025-01-16T16:47:41Z").await;
|
||||
snapshot!(json_string!(tasks, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "tasks_filter_afterStartedAt_equal_2025-01-16T16_47_41");
|
||||
snapshot!(json_string!(tasks, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "tasks_filter_afterStartedAt_equal_2025-01-16T16_47_41");
|
||||
let (tasks, _) = server.tasks_filter("beforeFinishedAt=2025-01-16T16:47:41Z").await;
|
||||
snapshot!(json_string!(tasks, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "tasks_filter_beforeFinishedAt_equal_2025-01-16T16_47_41");
|
||||
snapshot!(json_string!(tasks, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "tasks_filter_beforeFinishedAt_equal_2025-01-16T16_47_41");
|
||||
let (tasks, _) = server.tasks_filter("afterFinishedAt=2025-01-16T16:47:41Z").await;
|
||||
snapshot!(json_string!(tasks, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "tasks_filter_afterFinishedAt_equal_2025-01-16T16_47_41");
|
||||
snapshot!(json_string!(tasks, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]" }), name: "tasks_filter_afterFinishedAt_equal_2025-01-16T16_47_41");
|
||||
|
||||
// Tests all the batches query parameters
|
||||
let (batches, _) = server.batches_filter("uids=10").await;
|
||||
snapshot!(json_string!(batches, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_uids_equal_10");
|
||||
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_uids_equal_10");
|
||||
let (batches, _) = server.batches_filter("batchUids=10").await;
|
||||
snapshot!(json_string!(batches, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_batchUids_equal_10");
|
||||
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_batchUids_equal_10");
|
||||
let (batches, _) = server.batches_filter("statuses=canceled").await;
|
||||
snapshot!(json_string!(batches, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_statuses_equal_canceled");
|
||||
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_statuses_equal_canceled");
|
||||
// types has already been tested above to retrieve the upgrade database
|
||||
let (batches, _) = server.batches_filter("canceledBy=19").await;
|
||||
snapshot!(json_string!(batches, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_canceledBy_equal_19");
|
||||
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_canceledBy_equal_19");
|
||||
let (batches, _) = server.batches_filter("beforeEnqueuedAt=2025-01-16T16:47:41Z").await;
|
||||
snapshot!(json_string!(batches, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_beforeEnqueuedAt_equal_2025-01-16T16_47_41");
|
||||
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_beforeEnqueuedAt_equal_2025-01-16T16_47_41");
|
||||
let (batches, _) = server.batches_filter("afterEnqueuedAt=2025-01-16T16:47:41Z").await;
|
||||
snapshot!(json_string!(batches, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_afterEnqueuedAt_equal_2025-01-16T16_47_41");
|
||||
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_afterEnqueuedAt_equal_2025-01-16T16_47_41");
|
||||
let (batches, _) = server.batches_filter("beforeStartedAt=2025-01-16T16:47:41Z").await;
|
||||
snapshot!(json_string!(batches, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_beforeStartedAt_equal_2025-01-16T16_47_41");
|
||||
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_beforeStartedAt_equal_2025-01-16T16_47_41");
|
||||
let (batches, _) = server.batches_filter("afterStartedAt=2025-01-16T16:47:41Z").await;
|
||||
snapshot!(json_string!(batches, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_afterStartedAt_equal_2025-01-16T16_47_41");
|
||||
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_afterStartedAt_equal_2025-01-16T16_47_41");
|
||||
let (batches, _) = server.batches_filter("beforeFinishedAt=2025-01-16T16:47:41Z").await;
|
||||
snapshot!(json_string!(batches, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_beforeFinishedAt_equal_2025-01-16T16_47_41");
|
||||
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_beforeFinishedAt_equal_2025-01-16T16_47_41");
|
||||
let (batches, _) = server.batches_filter("afterFinishedAt=2025-01-16T16:47:41Z").await;
|
||||
snapshot!(json_string!(batches, { ".results[0].details.upgradeTo" => "[current version]", ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_afterFinishedAt_equal_2025-01-16T16_47_41");
|
||||
snapshot!(json_string!(batches, { ".results[0].duration" => "[duration]", ".results[0].enqueuedAt" => "[date]", ".results[0].startedAt" => "[date]", ".results[0].finishedAt" => "[date]", ".results[0].stats.progressTrace" => "[progressTrace]", ".results[0].stats.internalDatabaseSizes" => "[internalDatabaseSizes]", ".results[0].stats.writeChannelCongestion" => "[writeChannelCongestion]" }), name: "batches_filter_afterFinishedAt_equal_2025-01-16T16_47_41");
|
||||
|
||||
let (stats, _) = server.stats().await;
|
||||
assert_json_snapshot!(stats, {
|
||||
|
||||
@@ -104,8 +104,8 @@ async fn binary_quantize_before_sending_documents() {
|
||||
"manual": {
|
||||
"embeddings": [
|
||||
[
|
||||
0.0,
|
||||
0.0,
|
||||
-1.0,
|
||||
-1.0,
|
||||
1.0
|
||||
]
|
||||
],
|
||||
@@ -122,7 +122,7 @@ async fn binary_quantize_before_sending_documents() {
|
||||
[
|
||||
1.0,
|
||||
1.0,
|
||||
0.0
|
||||
-1.0
|
||||
]
|
||||
],
|
||||
"regenerate": false
|
||||
@@ -191,8 +191,8 @@ async fn binary_quantize_after_sending_documents() {
|
||||
"manual": {
|
||||
"embeddings": [
|
||||
[
|
||||
0.0,
|
||||
0.0,
|
||||
-1.0,
|
||||
-1.0,
|
||||
1.0
|
||||
]
|
||||
],
|
||||
@@ -209,7 +209,7 @@ async fn binary_quantize_after_sending_documents() {
|
||||
[
|
||||
1.0,
|
||||
1.0,
|
||||
0.0
|
||||
-1.0
|
||||
]
|
||||
],
|
||||
"regenerate": false
|
||||
|
||||
@@ -1,43 +0,0 @@
|
||||
use meili_snap::snapshot;
|
||||
|
||||
use crate::common::{GetAllDocumentsOptions, Server};
|
||||
use crate::json;
|
||||
|
||||
#[actix_rt::test]
|
||||
async fn hf_bge_m3_force_cls_settings() {
|
||||
let server = Server::new_shared();
|
||||
let index = server.unique_index();
|
||||
|
||||
let (response, code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"default": {
|
||||
"source": "huggingFace",
|
||||
"model": "baai/bge-m3",
|
||||
"revision": "5617a9f61b028005a4858fdac845db406aefb181",
|
||||
"pooling": "forceCls",
|
||||
// minimal template to allow potential document embedding if used later
|
||||
"documentTemplate": "{{doc.title}}"
|
||||
}
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
snapshot!(code, @"202 Accepted");
|
||||
server.wait_task(response.uid()).await.succeeded();
|
||||
|
||||
// Try to embed one simple document
|
||||
let (task, code) =
|
||||
index.add_documents(json!([{ "id": 1, "title": "Hello world" }]), None).await;
|
||||
snapshot!(code, @"202 Accepted");
|
||||
server.wait_task(task.uid()).await.succeeded();
|
||||
|
||||
// Retrieve the document with vectors and assert embeddings were produced
|
||||
let (documents, _code) = index
|
||||
.get_all_documents(GetAllDocumentsOptions { retrieve_vectors: true, ..Default::default() })
|
||||
.await;
|
||||
let has_vectors = documents["results"][0]["_vectors"]["default"]["embeddings"]
|
||||
.as_array()
|
||||
.map(|a| !a.is_empty())
|
||||
.unwrap_or(false);
|
||||
snapshot!(has_vectors, @"true");
|
||||
}
|
||||
@@ -1,6 +1,5 @@
|
||||
mod binary_quantized;
|
||||
mod fragments;
|
||||
mod huggingface;
|
||||
#[cfg(feature = "test-ollama")]
|
||||
mod ollama;
|
||||
mod openai;
|
||||
|
||||
@@ -500,6 +500,13 @@ async fn test_both_apis() {
|
||||
snapshot!(code, @"200 OK");
|
||||
snapshot!(json_string!(response["hits"]), @r###"
|
||||
[
|
||||
{
|
||||
"id": 0,
|
||||
"name": "kefir",
|
||||
"gender": "M",
|
||||
"birthyear": 2023,
|
||||
"breed": "Patou"
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"name": "Vénus",
|
||||
@@ -520,13 +527,6 @@ async fn test_both_apis() {
|
||||
"gender": "M",
|
||||
"birthyear": 1995,
|
||||
"breed": "Labrador Retriever"
|
||||
},
|
||||
{
|
||||
"id": 0,
|
||||
"name": "kefir",
|
||||
"gender": "M",
|
||||
"birthyear": 2023,
|
||||
"breed": "Patou"
|
||||
}
|
||||
]
|
||||
"###);
|
||||
@@ -540,6 +540,13 @@ async fn test_both_apis() {
|
||||
snapshot!(code, @"200 OK");
|
||||
snapshot!(json_string!(response["hits"]), @r###"
|
||||
[
|
||||
{
|
||||
"id": 0,
|
||||
"name": "kefir",
|
||||
"gender": "M",
|
||||
"birthyear": 2023,
|
||||
"breed": "Patou"
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"name": "Vénus",
|
||||
@@ -560,13 +567,6 @@ async fn test_both_apis() {
|
||||
"gender": "M",
|
||||
"birthyear": 1995,
|
||||
"breed": "Labrador Retriever"
|
||||
},
|
||||
{
|
||||
"id": 0,
|
||||
"name": "kefir",
|
||||
"gender": "M",
|
||||
"birthyear": 2023,
|
||||
"breed": "Patou"
|
||||
}
|
||||
]
|
||||
"###);
|
||||
@@ -581,18 +581,11 @@ async fn test_both_apis() {
|
||||
snapshot!(json_string!(response["hits"]), @r###"
|
||||
[
|
||||
{
|
||||
"id": 1,
|
||||
"name": "Intel",
|
||||
"id": 0,
|
||||
"name": "kefir",
|
||||
"gender": "M",
|
||||
"birthyear": 2011,
|
||||
"breed": "Beagle"
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"name": "Vénus",
|
||||
"gender": "F",
|
||||
"birthyear": 2003,
|
||||
"breed": "Jack Russel Terrier"
|
||||
"birthyear": 2023,
|
||||
"breed": "Patou"
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
@@ -602,11 +595,18 @@ async fn test_both_apis() {
|
||||
"breed": "Labrador Retriever"
|
||||
},
|
||||
{
|
||||
"id": 0,
|
||||
"name": "kefir",
|
||||
"id": 2,
|
||||
"name": "Vénus",
|
||||
"gender": "F",
|
||||
"birthyear": 2003,
|
||||
"breed": "Jack Russel Terrier"
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"name": "Intel",
|
||||
"gender": "M",
|
||||
"birthyear": 2023,
|
||||
"breed": "Patou"
|
||||
"birthyear": 2011,
|
||||
"breed": "Beagle"
|
||||
}
|
||||
]
|
||||
"###);
|
||||
@@ -621,18 +621,11 @@ async fn test_both_apis() {
|
||||
snapshot!(json_string!(response["hits"]), @r###"
|
||||
[
|
||||
{
|
||||
"id": 1,
|
||||
"name": "Intel",
|
||||
"id": 0,
|
||||
"name": "kefir",
|
||||
"gender": "M",
|
||||
"birthyear": 2011,
|
||||
"breed": "Beagle"
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"name": "Vénus",
|
||||
"gender": "F",
|
||||
"birthyear": 2003,
|
||||
"breed": "Jack Russel Terrier"
|
||||
"birthyear": 2023,
|
||||
"breed": "Patou"
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
@@ -642,11 +635,18 @@ async fn test_both_apis() {
|
||||
"breed": "Labrador Retriever"
|
||||
},
|
||||
{
|
||||
"id": 0,
|
||||
"name": "kefir",
|
||||
"id": 2,
|
||||
"name": "Vénus",
|
||||
"gender": "F",
|
||||
"birthyear": 2003,
|
||||
"breed": "Jack Russel Terrier"
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"name": "Intel",
|
||||
"gender": "M",
|
||||
"birthyear": 2023,
|
||||
"breed": "Patou"
|
||||
"birthyear": 2011,
|
||||
"breed": "Beagle"
|
||||
}
|
||||
]
|
||||
"###);
|
||||
@@ -661,18 +661,11 @@ async fn test_both_apis() {
|
||||
snapshot!(json_string!(response["hits"]), @r###"
|
||||
[
|
||||
{
|
||||
"id": 1,
|
||||
"name": "Intel",
|
||||
"id": 0,
|
||||
"name": "kefir",
|
||||
"gender": "M",
|
||||
"birthyear": 2011,
|
||||
"breed": "Beagle"
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"name": "Vénus",
|
||||
"gender": "F",
|
||||
"birthyear": 2003,
|
||||
"breed": "Jack Russel Terrier"
|
||||
"birthyear": 2023,
|
||||
"breed": "Patou"
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
@@ -682,11 +675,18 @@ async fn test_both_apis() {
|
||||
"breed": "Labrador Retriever"
|
||||
},
|
||||
{
|
||||
"id": 0,
|
||||
"name": "kefir",
|
||||
"id": 2,
|
||||
"name": "Vénus",
|
||||
"gender": "F",
|
||||
"birthyear": 2003,
|
||||
"breed": "Jack Russel Terrier"
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"name": "Intel",
|
||||
"gender": "M",
|
||||
"birthyear": 2023,
|
||||
"breed": "Patou"
|
||||
"birthyear": 2011,
|
||||
"breed": "Beagle"
|
||||
}
|
||||
]
|
||||
"###);
|
||||
@@ -701,18 +701,11 @@ async fn test_both_apis() {
|
||||
snapshot!(json_string!(response["hits"]), @r###"
|
||||
[
|
||||
{
|
||||
"id": 1,
|
||||
"name": "Intel",
|
||||
"id": 0,
|
||||
"name": "kefir",
|
||||
"gender": "M",
|
||||
"birthyear": 2011,
|
||||
"breed": "Beagle"
|
||||
},
|
||||
{
|
||||
"id": 2,
|
||||
"name": "Vénus",
|
||||
"gender": "F",
|
||||
"birthyear": 2003,
|
||||
"breed": "Jack Russel Terrier"
|
||||
"birthyear": 2023,
|
||||
"breed": "Patou"
|
||||
},
|
||||
{
|
||||
"id": 3,
|
||||
@@ -722,11 +715,18 @@ async fn test_both_apis() {
|
||||
"breed": "Labrador Retriever"
|
||||
},
|
||||
{
|
||||
"id": 0,
|
||||
"name": "kefir",
|
||||
"id": 2,
|
||||
"name": "Vénus",
|
||||
"gender": "F",
|
||||
"birthyear": 2003,
|
||||
"breed": "Jack Russel Terrier"
|
||||
},
|
||||
{
|
||||
"id": 1,
|
||||
"name": "Intel",
|
||||
"gender": "M",
|
||||
"birthyear": 2023,
|
||||
"breed": "Patou"
|
||||
"birthyear": 2011,
|
||||
"breed": "Beagle"
|
||||
}
|
||||
]
|
||||
"###);
|
||||
|
||||
@@ -9,15 +9,15 @@ edition.workspace = true
|
||||
license.workspace = true
|
||||
|
||||
[dependencies]
|
||||
anyhow = "1.0.100"
|
||||
clap = { version = "4.5.52", features = ["derive"] }
|
||||
anyhow = "1.0.98"
|
||||
clap = { version = "4.5.40", features = ["derive"] }
|
||||
dump = { path = "../dump" }
|
||||
file-store = { path = "../file-store" }
|
||||
indexmap = { version = "2.12.0", features = ["serde"] }
|
||||
indexmap = { version = "2.9.0", features = ["serde"] }
|
||||
meilisearch-auth = { path = "../meilisearch-auth" }
|
||||
meilisearch-types = { path = "../meilisearch-types" }
|
||||
serde = { version = "1.0.228", features = ["derive"] }
|
||||
serde_json = { version = "1.0.145", features = ["preserve_order"] }
|
||||
tempfile = "3.23.0"
|
||||
time = { version = "0.3.44", features = ["formatting", "parsing", "alloc"] }
|
||||
uuid = { version = "1.18.1", features = ["v4"], default-features = false }
|
||||
serde = { version = "1.0.219", features = ["derive"] }
|
||||
serde_json = { version = "1.0.140", features = ["preserve_order"] }
|
||||
tempfile = "3.20.0"
|
||||
time = { version = "0.3.41", features = ["formatting", "parsing", "alloc"] }
|
||||
uuid = { version = "1.17.0", features = ["v4"], default-features = false }
|
||||
|
||||
@@ -15,15 +15,15 @@ license.workspace = true
|
||||
big_s = "1.0.2"
|
||||
bimap = { version = "0.6.3", features = ["serde"] }
|
||||
bincode = "1.3.3"
|
||||
bstr = "1.12.1"
|
||||
bytemuck = { version = "1.24.0", features = ["extern_crate_alloc"] }
|
||||
bstr = "1.12.0"
|
||||
bytemuck = { version = "1.23.1", features = ["extern_crate_alloc"] }
|
||||
byteorder = "1.5.0"
|
||||
charabia = { version = "0.9.9", default-features = false }
|
||||
charabia = { version = "0.9.8", default-features = false }
|
||||
cellulite = "0.3.1-nested-rtxns-2"
|
||||
concat-arrays = "0.1.2"
|
||||
convert_case = "0.9.0"
|
||||
convert_case = "0.8.0"
|
||||
crossbeam-channel = "0.5.15"
|
||||
deserr = "0.6.4"
|
||||
deserr = "0.6.3"
|
||||
either = { version = "1.15.0", features = ["serde"] }
|
||||
flatten-serde-json = { path = "../flatten-serde-json" }
|
||||
fst = "0.4.7"
|
||||
@@ -38,39 +38,39 @@ heed = { version = "0.22.1-nested-rtxns-6", default-features = false, features =
|
||||
"serde-json",
|
||||
"serde-bincode",
|
||||
] }
|
||||
indexmap = { version = "2.12.0", features = ["serde"] }
|
||||
indexmap = { version = "2.9.0", features = ["serde"] }
|
||||
json-depth-checker = { path = "../json-depth-checker" }
|
||||
levenshtein_automata = { version = "0.2.1", features = ["fst_automaton"] }
|
||||
memchr = "2.7.6"
|
||||
memmap2 = "0.9.9"
|
||||
memchr = "2.7.5"
|
||||
memmap2 = "0.9.7"
|
||||
obkv = "0.3.0"
|
||||
once_cell = "1.21.3"
|
||||
ordered-float = "5.1.0"
|
||||
rayon = "1.11.0"
|
||||
ordered-float = "5.0.0"
|
||||
rayon = "1.10.0"
|
||||
roaring = { version = "0.10.12", features = ["serde"] }
|
||||
rstar = { version = "0.12.2", features = ["serde"] }
|
||||
serde = { version = "1.0.228", features = ["derive"] }
|
||||
serde_json = { version = "1.0.145", features = ["preserve_order", "raw_value"] }
|
||||
serde = { version = "1.0.219", features = ["derive"] }
|
||||
serde_json = { version = "1.0.140", features = ["preserve_order", "raw_value"] }
|
||||
slice-group-by = "0.3.1"
|
||||
smallstr = { version = "0.3.1", features = ["serde"] }
|
||||
smallstr = { version = "0.3.0", features = ["serde"] }
|
||||
smallvec = "1.15.1"
|
||||
smartstring = "1.0.1"
|
||||
tempfile = "3.23.0"
|
||||
thiserror = "2.0.17"
|
||||
time = { version = "0.3.44", features = [
|
||||
tempfile = "3.20.0"
|
||||
thiserror = "2.0.12"
|
||||
time = { version = "0.3.41", features = [
|
||||
"serde-well-known",
|
||||
"formatting",
|
||||
"parsing",
|
||||
"macros",
|
||||
] }
|
||||
uuid = { version = "1.18.1", features = ["v4"] }
|
||||
uuid = { version = "1.17.0", features = ["v4"] }
|
||||
|
||||
filter-parser = { path = "../filter-parser" }
|
||||
|
||||
# documents words self-join
|
||||
itertools = "0.14.0"
|
||||
|
||||
csv = "1.4.0"
|
||||
csv = "1.3.1"
|
||||
candle-core = { version = "0.9.1" }
|
||||
candle-transformers = { version = "0.9.1" }
|
||||
candle-nn = { version = "0.9.1" }
|
||||
@@ -81,9 +81,9 @@ hf-hub = { git = "https://github.com/dureuill/hf-hub.git", branch = "rust_tls",
|
||||
"online",
|
||||
] }
|
||||
safetensors = "0.6.2"
|
||||
tiktoken-rs = "0.9.1"
|
||||
tiktoken-rs = "0.7.0"
|
||||
liquid = "0.26.11"
|
||||
rhai = { version = "1.23.6", features = [
|
||||
rhai = { version = "1.22.2", features = [
|
||||
"serde",
|
||||
"no_module",
|
||||
"no_custom_syntax",
|
||||
@@ -91,18 +91,18 @@ rhai = { version = "1.23.6", features = [
|
||||
"sync",
|
||||
] }
|
||||
arroy = "0.6.4-nested-rtxns"
|
||||
hannoy = { version = "0.1.0-nested-rtxns", features = ["arroy"] }
|
||||
hannoy = { version = "0.0.9-nested-rtxns-2", features = ["arroy"] }
|
||||
rand = "0.8.5"
|
||||
tracing = "0.1.41"
|
||||
ureq = { version = "2.12.1", features = ["json"] }
|
||||
url = "2.5.7"
|
||||
hashbrown = "0.15.5"
|
||||
bumpalo = "3.19.0"
|
||||
url = "2.5.4"
|
||||
hashbrown = "0.15.4"
|
||||
bumpalo = "3.18.1"
|
||||
bumparaw-collections = "0.1.4"
|
||||
steppe = { version = "0.4", default-features = false }
|
||||
thread_local = "1.1.9"
|
||||
rustc-hash = "2.1.1"
|
||||
enum-iterator = "2.3.0"
|
||||
enum-iterator = "2.1.0"
|
||||
bbqueue = { git = "https://github.com/meilisearch/bbqueue" }
|
||||
flume = { version = "0.11.1", default-features = false }
|
||||
utoipa = { version = "5.4.0", features = [
|
||||
@@ -112,21 +112,21 @@ utoipa = { version = "5.4.0", features = [
|
||||
"time",
|
||||
"openapi_extensions",
|
||||
] }
|
||||
lru = "0.16.2"
|
||||
twox-hash = { version = "2.1.2", default-features = false, features = [
|
||||
lru = "0.14.0"
|
||||
twox-hash = { version = "2.1.1", default-features = false, features = [
|
||||
"std",
|
||||
"xxhash3_64",
|
||||
"xxhash64",
|
||||
] }
|
||||
geo-types = "0.7.17"
|
||||
geo-types = "0.7.16"
|
||||
zerometry = "0.3.0"
|
||||
|
||||
[dev-dependencies]
|
||||
mimalloc = { version = "0.1.48", default-features = false }
|
||||
mimalloc = { version = "0.1.47", default-features = false }
|
||||
# fixed version due to format breakages in v1.40
|
||||
insta = "=1.39.0"
|
||||
maplit = "1.0.2"
|
||||
md5 = "0.8.0"
|
||||
md5 = "0.7.0"
|
||||
meili-snap = { path = "../meili-snap" }
|
||||
rand = { version = "0.8.5", features = ["small_rng"] }
|
||||
|
||||
@@ -141,8 +141,6 @@ lmdb-posix-sem = ["heed/posix-sem"]
|
||||
chinese = ["charabia/chinese"]
|
||||
chinese-pinyin = ["chinese", "charabia/chinese-normalization-pinyin"]
|
||||
|
||||
enterprise = []
|
||||
|
||||
# allow hebrew specialized tokenization
|
||||
hebrew = ["charabia/hebrew"]
|
||||
|
||||
|
||||
@@ -87,7 +87,7 @@ impl Iterator for SortedDocumentsIterator<'_> {
|
||||
};
|
||||
|
||||
// Otherwise don't directly iterate over children, skip them if we know we will go further
|
||||
let mut to_skip = n;
|
||||
let mut to_skip = n - 1;
|
||||
while to_skip > 0 {
|
||||
if let Err(e) = SortedDocumentsIterator::update_current(
|
||||
current_child,
|
||||
@@ -108,7 +108,7 @@ impl Iterator for SortedDocumentsIterator<'_> {
|
||||
continue;
|
||||
} else {
|
||||
// The current iterator is large enough, so we can forward the call to it.
|
||||
return inner.nth(to_skip);
|
||||
return inner.nth(to_skip + 1);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -240,25 +240,15 @@ impl<'ctx> SortedDocumentsIteratorBuilder<'ctx> {
|
||||
) -> crate::Result<SortedDocumentsIterator<'ctx>> {
|
||||
let size = candidates.len() as usize;
|
||||
|
||||
// Get documents that have this facet field
|
||||
let faceted_candidates = index.exists_faceted_documents_ids(rtxn, field_id)?;
|
||||
// Documents that don't have this facet field should be returned at the end
|
||||
let not_faceted_candidates = &candidates - &faceted_candidates;
|
||||
// Only sort candidates that have the facet field
|
||||
let faceted_candidates = candidates & faceted_candidates;
|
||||
let mut not_faceted_candidates = Some(not_faceted_candidates);
|
||||
|
||||
// Perform the sort on the first field
|
||||
let (number_iter, string_iter) = if ascending {
|
||||
let number_iter =
|
||||
ascending_facet_sort(rtxn, number_db, field_id, faceted_candidates.clone())?;
|
||||
let string_iter = ascending_facet_sort(rtxn, string_db, field_id, faceted_candidates)?;
|
||||
let number_iter = ascending_facet_sort(rtxn, number_db, field_id, candidates.clone())?;
|
||||
let string_iter = ascending_facet_sort(rtxn, string_db, field_id, candidates)?;
|
||||
|
||||
(itertools::Either::Left(number_iter), itertools::Either::Left(string_iter))
|
||||
} else {
|
||||
let number_iter =
|
||||
descending_facet_sort(rtxn, number_db, field_id, faceted_candidates.clone())?;
|
||||
let string_iter = descending_facet_sort(rtxn, string_db, field_id, faceted_candidates)?;
|
||||
let number_iter = descending_facet_sort(rtxn, number_db, field_id, candidates.clone())?;
|
||||
let string_iter = descending_facet_sort(rtxn, string_db, field_id, candidates)?;
|
||||
|
||||
(itertools::Either::Right(number_iter), itertools::Either::Right(string_iter))
|
||||
};
|
||||
@@ -266,37 +256,17 @@ impl<'ctx> SortedDocumentsIteratorBuilder<'ctx> {
|
||||
// Create builders for the next level of the tree
|
||||
let number_iter = number_iter.map(|r| r.map(|(d, _)| d));
|
||||
let string_iter = string_iter.map(|r| r.map(|(d, _)| d));
|
||||
// Chain faceted documents with non-faceted documents at the end
|
||||
let next_children = number_iter
|
||||
.chain(string_iter)
|
||||
.map(move |r| {
|
||||
Ok(SortedDocumentsIteratorBuilder {
|
||||
index,
|
||||
rtxn,
|
||||
number_db,
|
||||
string_db,
|
||||
fields: next_fields,
|
||||
candidates: r?,
|
||||
geo_candidates,
|
||||
})
|
||||
let next_children = number_iter.chain(string_iter).map(move |r| {
|
||||
Ok(SortedDocumentsIteratorBuilder {
|
||||
index,
|
||||
rtxn,
|
||||
number_db,
|
||||
string_db,
|
||||
fields: next_fields,
|
||||
candidates: r?,
|
||||
geo_candidates,
|
||||
})
|
||||
.chain(std::iter::from_fn(move || {
|
||||
// Once all faceted candidates have been processed, return the non-faceted ones
|
||||
if let Some(not_faceted) = not_faceted_candidates.take() {
|
||||
if !not_faceted.is_empty() {
|
||||
return Some(Ok(SortedDocumentsIteratorBuilder {
|
||||
index,
|
||||
rtxn,
|
||||
number_db,
|
||||
string_db,
|
||||
fields: next_fields,
|
||||
candidates: not_faceted,
|
||||
geo_candidates,
|
||||
}));
|
||||
}
|
||||
}
|
||||
None
|
||||
}));
|
||||
});
|
||||
|
||||
Ok(SortedDocumentsIterator::Branch {
|
||||
current_child: None,
|
||||
@@ -428,14 +398,10 @@ pub fn recursive_sort<'ctx>(
|
||||
};
|
||||
if let Some((field, ascending)) = field {
|
||||
if is_faceted(&field, &sortable_fields) {
|
||||
// The field may be in sortable_fields but not in fields_ids_map if no document
|
||||
// has ever contained this field. In that case, we just skip this sort criterion
|
||||
// since there are no values to sort by. Documents will be returned in their
|
||||
// default order for this field.
|
||||
if let Some(field_id) = fields_ids_map.id(&field) {
|
||||
fields.push(AscDescId::Facet { field_id, ascending });
|
||||
continue;
|
||||
}
|
||||
continue;
|
||||
}
|
||||
return Err(UserError::InvalidDocumentSortableAttribute {
|
||||
field: field.to_string(),
|
||||
|
||||
@@ -18,8 +18,6 @@ use crate::{
|
||||
pub struct Metadata {
|
||||
/// The weight as defined in the FieldidsWeightsMap of the searchable attribute if it is searchable.
|
||||
pub searchable: Option<Weight>,
|
||||
/// The field is part of the exact attributes.
|
||||
pub exact: bool,
|
||||
/// The field is part of the sortable attributes.
|
||||
pub sortable: bool,
|
||||
/// The field is defined as the distinct attribute.
|
||||
@@ -211,7 +209,6 @@ impl Metadata {
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct MetadataBuilder {
|
||||
searchable_attributes: Option<Vec<String>>,
|
||||
exact_searchable_attributes: Vec<String>,
|
||||
filterable_attributes: Vec<FilterableAttributesRule>,
|
||||
sortable_attributes: HashSet<String>,
|
||||
localized_attributes: Option<Vec<LocalizedAttributesRule>>,
|
||||
@@ -223,18 +220,15 @@ impl MetadataBuilder {
|
||||
pub fn from_index(index: &Index, rtxn: &RoTxn) -> Result<Self> {
|
||||
let searchable_attributes = index
|
||||
.user_defined_searchable_fields(rtxn)?
|
||||
.map(|fields| fields.into_iter().map(String::from).collect());
|
||||
let exact_searchable_attributes =
|
||||
index.exact_attributes(rtxn)?.into_iter().map(String::from).collect();
|
||||
.map(|fields| fields.into_iter().map(|s| s.to_string()).collect());
|
||||
let filterable_attributes = index.filterable_attributes_rules(rtxn)?;
|
||||
let sortable_attributes = index.sortable_fields(rtxn)?;
|
||||
let localized_attributes = index.localized_attributes_rules(rtxn)?;
|
||||
let distinct_attribute = index.distinct_field(rtxn)?.map(String::from);
|
||||
let distinct_attribute = index.distinct_field(rtxn)?.map(|s| s.to_string());
|
||||
let asc_desc_attributes = index.asc_desc_fields(rtxn)?;
|
||||
|
||||
Ok(Self::new(
|
||||
searchable_attributes,
|
||||
exact_searchable_attributes,
|
||||
filterable_attributes,
|
||||
sortable_attributes,
|
||||
localized_attributes,
|
||||
@@ -248,7 +242,6 @@ impl MetadataBuilder {
|
||||
/// This is used for testing, prefer using `MetadataBuilder::from_index` instead.
|
||||
pub fn new(
|
||||
searchable_attributes: Option<Vec<String>>,
|
||||
exact_searchable_attributes: Vec<String>,
|
||||
filterable_attributes: Vec<FilterableAttributesRule>,
|
||||
sortable_attributes: HashSet<String>,
|
||||
localized_attributes: Option<Vec<LocalizedAttributesRule>>,
|
||||
@@ -263,7 +256,6 @@ impl MetadataBuilder {
|
||||
|
||||
Self {
|
||||
searchable_attributes,
|
||||
exact_searchable_attributes,
|
||||
filterable_attributes,
|
||||
sortable_attributes,
|
||||
localized_attributes,
|
||||
@@ -277,7 +269,6 @@ impl MetadataBuilder {
|
||||
// Vectors fields are not searchable, filterable, distinct or asc_desc
|
||||
return Metadata {
|
||||
searchable: None,
|
||||
exact: false,
|
||||
sortable: false,
|
||||
distinct: false,
|
||||
asc_desc: false,
|
||||
@@ -305,7 +296,6 @@ impl MetadataBuilder {
|
||||
// Geo fields are not searchable, distinct or asc_desc
|
||||
return Metadata {
|
||||
searchable: None,
|
||||
exact: false,
|
||||
sortable,
|
||||
distinct: false,
|
||||
asc_desc: false,
|
||||
@@ -319,7 +309,6 @@ impl MetadataBuilder {
|
||||
debug_assert!(!sortable, "geojson fields should not be sortable");
|
||||
return Metadata {
|
||||
searchable: None,
|
||||
exact: false,
|
||||
sortable,
|
||||
distinct: false,
|
||||
asc_desc: false,
|
||||
@@ -340,8 +329,6 @@ impl MetadataBuilder {
|
||||
None => Some(0),
|
||||
};
|
||||
|
||||
let exact = self.exact_searchable_attributes.iter().any(|attr| is_faceted_by(field, attr));
|
||||
|
||||
let distinct =
|
||||
self.distinct_attribute.as_ref().is_some_and(|distinct_field| field == distinct_field);
|
||||
let asc_desc = self.asc_desc_attributes.contains(field);
|
||||
@@ -356,7 +343,6 @@ impl MetadataBuilder {
|
||||
|
||||
Metadata {
|
||||
searchable,
|
||||
exact,
|
||||
sortable,
|
||||
distinct,
|
||||
asc_desc,
|
||||
|
||||
@@ -281,9 +281,6 @@ impl Index {
|
||||
&mut wtxn,
|
||||
(constants::VERSION_MAJOR, constants::VERSION_MINOR, constants::VERSION_PATCH),
|
||||
)?;
|
||||
// The database before v1.29 defaulted to using arroy, so we
|
||||
// need to set it explicitly because the new default is hannoy.
|
||||
this.put_vector_store(&mut wtxn, VectorStoreBackend::Hannoy)?;
|
||||
}
|
||||
wtxn.commit()?;
|
||||
|
||||
|
||||
@@ -806,10 +806,6 @@ mod tests {
|
||||
use crate::vector::db::IndexEmbeddingConfig;
|
||||
use crate::{all_obkv_to_json, db_snap, Filter, FilterableAttributesRule, Search, UserError};
|
||||
|
||||
fn no_cancel() -> bool {
|
||||
false
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn simple_document_replacement() {
|
||||
let index = TempIndex::new();
|
||||
@@ -1989,7 +1985,7 @@ mod tests {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -2042,7 +2038,7 @@ mod tests {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -2061,7 +2057,7 @@ mod tests {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -2131,7 +2127,7 @@ mod tests {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -2150,7 +2146,7 @@ mod tests {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
RuntimeEmbedders::default(),
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -2321,7 +2317,7 @@ mod tests {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -2337,7 +2333,7 @@ mod tests {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
embedders,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -2385,7 +2381,7 @@ mod tests {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -2401,7 +2397,7 @@ mod tests {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
embedders,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -2440,7 +2436,7 @@ mod tests {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -2456,7 +2452,7 @@ mod tests {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
embedders,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -2494,7 +2490,7 @@ mod tests {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -2510,7 +2506,7 @@ mod tests {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
embedders,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -2550,7 +2546,7 @@ mod tests {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -2566,7 +2562,7 @@ mod tests {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
embedders,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -2611,7 +2607,7 @@ mod tests {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -2627,7 +2623,7 @@ mod tests {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
embedders,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -2665,7 +2661,7 @@ mod tests {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -2681,7 +2677,7 @@ mod tests {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
embedders,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -2719,7 +2715,7 @@ mod tests {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -2735,7 +2731,7 @@ mod tests {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
embedders,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -2931,7 +2927,7 @@ mod tests {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -2947,7 +2943,7 @@ mod tests {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
embedders,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -2992,7 +2988,7 @@ mod tests {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -3008,7 +3004,7 @@ mod tests {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
embedders,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
@@ -3050,7 +3046,7 @@ mod tests {
|
||||
&rtxn,
|
||||
None,
|
||||
&mut new_fields_ids_map,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
Progress::default(),
|
||||
None,
|
||||
)
|
||||
@@ -3066,7 +3062,7 @@ mod tests {
|
||||
primary_key,
|
||||
&document_changes,
|
||||
embedders,
|
||||
&no_cancel,
|
||||
&|| false,
|
||||
&Progress::default(),
|
||||
&Default::default(),
|
||||
)
|
||||
|
||||
@@ -8,26 +8,17 @@ use bumpalo::Bump;
|
||||
|
||||
use super::match_searchable_field;
|
||||
use super::tokenize_document::{tokenizer_builder, DocumentTokenizer};
|
||||
use crate::fields_ids_map::metadata::Metadata;
|
||||
use crate::update::new::document::DocumentContext;
|
||||
use crate::update::new::extract::cache::BalancedCaches;
|
||||
use crate::update::new::extract::perm_json_p::contained_in;
|
||||
use crate::update::new::extract::searchable::has_searchable_children;
|
||||
use crate::update::new::indexer::document_changes::{
|
||||
extract, DocumentChanges, Extractor, IndexingContext,
|
||||
};
|
||||
use crate::update::new::indexer::settings_changes::{
|
||||
settings_change_extract, DocumentsIndentifiers, SettingsChangeExtractor,
|
||||
};
|
||||
use crate::update::new::ref_cell_ext::RefCellExt as _;
|
||||
use crate::update::new::steps::IndexingStep;
|
||||
use crate::update::new::thread_local::{FullySend, MostlySend, ThreadLocal};
|
||||
use crate::update::new::{DocumentChange, DocumentIdentifiers};
|
||||
use crate::update::settings::SettingsDelta;
|
||||
use crate::{
|
||||
bucketed_position, DocumentId, FieldId, PatternMatch, Result, UserError,
|
||||
MAX_POSITION_PER_ATTRIBUTE,
|
||||
};
|
||||
use crate::update::new::DocumentChange;
|
||||
use crate::{bucketed_position, DocumentId, FieldId, Result, MAX_POSITION_PER_ATTRIBUTE};
|
||||
|
||||
const MAX_COUNTED_WORDS: usize = 30;
|
||||
|
||||
@@ -43,15 +34,6 @@ pub struct WordDocidsBalancedCaches<'extractor> {
|
||||
|
||||
unsafe impl MostlySend for WordDocidsBalancedCaches<'_> {}
|
||||
|
||||
/// Whether to extract or skip fields during word extraction.
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
||||
enum FieldDbExtraction {
|
||||
/// Extract the word and put it in to the fid-based databases.
|
||||
Extract,
|
||||
/// Do not store the word in the fid-based databases.
|
||||
Skip,
|
||||
}
|
||||
|
||||
impl<'extractor> WordDocidsBalancedCaches<'extractor> {
|
||||
pub fn new_in(buckets: usize, max_memory: Option<usize>, alloc: &'extractor Bump) -> Self {
|
||||
Self {
|
||||
@@ -65,14 +47,12 @@ impl<'extractor> WordDocidsBalancedCaches<'extractor> {
|
||||
}
|
||||
}
|
||||
|
||||
#[allow(clippy::too_many_arguments)]
|
||||
fn insert_add_u32(
|
||||
&mut self,
|
||||
field_id: FieldId,
|
||||
position: u16,
|
||||
word: &str,
|
||||
exact: bool,
|
||||
field_db_extraction: FieldDbExtraction,
|
||||
docid: u32,
|
||||
bump: &Bump,
|
||||
) -> Result<()> {
|
||||
@@ -86,13 +66,11 @@ impl<'extractor> WordDocidsBalancedCaches<'extractor> {
|
||||
let buffer_size = word_bytes.len() + 1 + size_of::<FieldId>();
|
||||
let mut buffer = BumpVec::with_capacity_in(buffer_size, bump);
|
||||
|
||||
if field_db_extraction == FieldDbExtraction::Extract {
|
||||
buffer.clear();
|
||||
buffer.extend_from_slice(word_bytes);
|
||||
buffer.push(0);
|
||||
buffer.extend_from_slice(&field_id.to_be_bytes());
|
||||
self.word_fid_docids.insert_add_u32(&buffer, docid)?;
|
||||
}
|
||||
buffer.clear();
|
||||
buffer.extend_from_slice(word_bytes);
|
||||
buffer.push(0);
|
||||
buffer.extend_from_slice(&field_id.to_be_bytes());
|
||||
self.word_fid_docids.insert_add_u32(&buffer, docid)?;
|
||||
|
||||
let position = bucketed_position(position);
|
||||
buffer.clear();
|
||||
@@ -105,26 +83,21 @@ impl<'extractor> WordDocidsBalancedCaches<'extractor> {
|
||||
self.flush_fid_word_count(&mut buffer)?;
|
||||
}
|
||||
|
||||
if field_db_extraction == FieldDbExtraction::Extract {
|
||||
self.fid_word_count
|
||||
.entry(field_id)
|
||||
.and_modify(|(_current_count, new_count)| *new_count.get_or_insert(0) += 1)
|
||||
.or_insert((None, Some(1)));
|
||||
}
|
||||
|
||||
self.fid_word_count
|
||||
.entry(field_id)
|
||||
.and_modify(|(_current_count, new_count)| *new_count.get_or_insert(0) += 1)
|
||||
.or_insert((None, Some(1)));
|
||||
self.current_docid = Some(docid);
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[allow(clippy::too_many_arguments)]
|
||||
fn insert_del_u32(
|
||||
&mut self,
|
||||
field_id: FieldId,
|
||||
position: u16,
|
||||
word: &str,
|
||||
exact: bool,
|
||||
field_db_extraction: FieldDbExtraction,
|
||||
docid: u32,
|
||||
bump: &Bump,
|
||||
) -> Result<()> {
|
||||
@@ -138,13 +111,11 @@ impl<'extractor> WordDocidsBalancedCaches<'extractor> {
|
||||
let buffer_size = word_bytes.len() + 1 + size_of::<FieldId>();
|
||||
let mut buffer = BumpVec::with_capacity_in(buffer_size, bump);
|
||||
|
||||
if field_db_extraction == FieldDbExtraction::Extract {
|
||||
buffer.clear();
|
||||
buffer.extend_from_slice(word_bytes);
|
||||
buffer.push(0);
|
||||
buffer.extend_from_slice(&field_id.to_be_bytes());
|
||||
self.word_fid_docids.insert_del_u32(&buffer, docid)?;
|
||||
}
|
||||
buffer.clear();
|
||||
buffer.extend_from_slice(word_bytes);
|
||||
buffer.push(0);
|
||||
buffer.extend_from_slice(&field_id.to_be_bytes());
|
||||
self.word_fid_docids.insert_del_u32(&buffer, docid)?;
|
||||
|
||||
let position = bucketed_position(position);
|
||||
buffer.clear();
|
||||
@@ -157,12 +128,10 @@ impl<'extractor> WordDocidsBalancedCaches<'extractor> {
|
||||
self.flush_fid_word_count(&mut buffer)?;
|
||||
}
|
||||
|
||||
if field_db_extraction == FieldDbExtraction::Extract {
|
||||
self.fid_word_count
|
||||
.entry(field_id)
|
||||
.and_modify(|(current_count, _new_count)| *current_count.get_or_insert(0) += 1)
|
||||
.or_insert((Some(1), None));
|
||||
}
|
||||
self.fid_word_count
|
||||
.entry(field_id)
|
||||
.and_modify(|(current_count, _new_count)| *current_count.get_or_insert(0) += 1)
|
||||
.or_insert((Some(1), None));
|
||||
|
||||
self.current_docid = Some(docid);
|
||||
|
||||
@@ -356,24 +325,6 @@ impl WordDocidsExtractors {
|
||||
exact_attributes.iter().any(|attr| contained_in(fname, attr))
|
||||
|| disabled_typos_terms.is_exact(word)
|
||||
};
|
||||
|
||||
let mut should_tokenize = |field_name: &str| {
|
||||
let Some((field_id, meta)) = new_fields_ids_map.id_with_metadata_or_insert(field_name)
|
||||
else {
|
||||
return Err(UserError::AttributeLimitReached.into());
|
||||
};
|
||||
|
||||
let pattern_match = if meta.is_searchable() {
|
||||
PatternMatch::Match
|
||||
} else {
|
||||
// TODO: should be a match on the field_name using `match_field_legacy` function,
|
||||
// but for legacy reasons we iterate over all the fields to fill the field_id_map.
|
||||
PatternMatch::Parent
|
||||
};
|
||||
|
||||
Ok((field_id, pattern_match))
|
||||
};
|
||||
|
||||
match document_change {
|
||||
DocumentChange::Deletion(inner) => {
|
||||
let mut token_fn = |fname: &str, fid, pos, word: &str| {
|
||||
@@ -382,14 +333,13 @@ impl WordDocidsExtractors {
|
||||
pos,
|
||||
word,
|
||||
is_exact(fname, word),
|
||||
FieldDbExtraction::Extract,
|
||||
inner.docid(),
|
||||
doc_alloc,
|
||||
)
|
||||
};
|
||||
document_tokenizer.tokenize_document(
|
||||
inner.current(rtxn, index, context.db_fields_ids_map)?,
|
||||
&mut should_tokenize,
|
||||
new_fields_ids_map,
|
||||
&mut token_fn,
|
||||
)?;
|
||||
}
|
||||
@@ -411,14 +361,13 @@ impl WordDocidsExtractors {
|
||||
pos,
|
||||
word,
|
||||
is_exact(fname, word),
|
||||
FieldDbExtraction::Extract,
|
||||
inner.docid(),
|
||||
doc_alloc,
|
||||
)
|
||||
};
|
||||
document_tokenizer.tokenize_document(
|
||||
inner.current(rtxn, index, context.db_fields_ids_map)?,
|
||||
&mut should_tokenize,
|
||||
new_fields_ids_map,
|
||||
&mut token_fn,
|
||||
)?;
|
||||
|
||||
@@ -428,14 +377,13 @@ impl WordDocidsExtractors {
|
||||
pos,
|
||||
word,
|
||||
is_exact(fname, word),
|
||||
FieldDbExtraction::Extract,
|
||||
inner.docid(),
|
||||
doc_alloc,
|
||||
)
|
||||
};
|
||||
document_tokenizer.tokenize_document(
|
||||
inner.merged(rtxn, index, context.db_fields_ids_map)?,
|
||||
&mut should_tokenize,
|
||||
new_fields_ids_map,
|
||||
&mut token_fn,
|
||||
)?;
|
||||
}
|
||||
@@ -446,14 +394,13 @@ impl WordDocidsExtractors {
|
||||
pos,
|
||||
word,
|
||||
is_exact(fname, word),
|
||||
FieldDbExtraction::Extract,
|
||||
inner.docid(),
|
||||
doc_alloc,
|
||||
)
|
||||
};
|
||||
document_tokenizer.tokenize_document(
|
||||
inner.inserted(),
|
||||
&mut should_tokenize,
|
||||
new_fields_ids_map,
|
||||
&mut token_fn,
|
||||
)?;
|
||||
}
|
||||
@@ -464,292 +411,3 @@ impl WordDocidsExtractors {
|
||||
cached_sorter.flush_fid_word_count(&mut buffer)
|
||||
}
|
||||
}
|
||||
|
||||
pub struct WordDocidsSettingsExtractorsData<'a, SD> {
|
||||
tokenizer: DocumentTokenizer<'a>,
|
||||
max_memory_by_thread: Option<usize>,
|
||||
buckets: usize,
|
||||
settings_delta: &'a SD,
|
||||
}
|
||||
|
||||
impl<'extractor, SD: SettingsDelta + Sync> SettingsChangeExtractor<'extractor>
|
||||
for WordDocidsSettingsExtractorsData<'_, SD>
|
||||
{
|
||||
type Data = RefCell<Option<WordDocidsBalancedCaches<'extractor>>>;
|
||||
|
||||
fn init_data<'doc>(&'doc self, extractor_alloc: &'extractor Bump) -> crate::Result<Self::Data> {
|
||||
Ok(RefCell::new(Some(WordDocidsBalancedCaches::new_in(
|
||||
self.buckets,
|
||||
self.max_memory_by_thread,
|
||||
extractor_alloc,
|
||||
))))
|
||||
}
|
||||
|
||||
fn process<'doc>(
|
||||
&'doc self,
|
||||
documents: impl Iterator<Item = crate::Result<DocumentIdentifiers<'doc>>>,
|
||||
context: &'doc DocumentContext<Self::Data>,
|
||||
) -> crate::Result<()> {
|
||||
for document in documents {
|
||||
let document = document?;
|
||||
SettingsChangeWordDocidsExtractors::extract_document_from_settings_change(
|
||||
document,
|
||||
context,
|
||||
&self.tokenizer,
|
||||
self.settings_delta,
|
||||
)?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
pub struct SettingsChangeWordDocidsExtractors;
|
||||
|
||||
impl SettingsChangeWordDocidsExtractors {
|
||||
pub fn run_extraction<'fid, 'indexer, 'index, 'extractor, SD, MSP>(
|
||||
settings_delta: &SD,
|
||||
documents: &'indexer DocumentsIndentifiers<'indexer>,
|
||||
indexing_context: IndexingContext<'fid, 'indexer, 'index, MSP>,
|
||||
extractor_allocs: &'extractor mut ThreadLocal<FullySend<Bump>>,
|
||||
step: IndexingStep,
|
||||
) -> Result<WordDocidsCaches<'extractor>>
|
||||
where
|
||||
SD: SettingsDelta + Sync,
|
||||
MSP: Fn() -> bool + Sync,
|
||||
{
|
||||
// Warning: this is duplicated code from extract_word_pair_proximity_docids.rs
|
||||
// TODO we need to read the new AND old settings to support changing global parameters
|
||||
let rtxn = indexing_context.index.read_txn()?;
|
||||
let stop_words = indexing_context.index.stop_words(&rtxn)?;
|
||||
let allowed_separators = indexing_context.index.allowed_separators(&rtxn)?;
|
||||
let allowed_separators: Option<Vec<_>> =
|
||||
allowed_separators.as_ref().map(|s| s.iter().map(String::as_str).collect());
|
||||
let dictionary = indexing_context.index.dictionary(&rtxn)?;
|
||||
let dictionary: Option<Vec<_>> =
|
||||
dictionary.as_ref().map(|s| s.iter().map(String::as_str).collect());
|
||||
let mut builder = tokenizer_builder(
|
||||
stop_words.as_ref(),
|
||||
allowed_separators.as_deref(),
|
||||
dictionary.as_deref(),
|
||||
);
|
||||
let tokenizer = builder.build();
|
||||
let localized_attributes_rules =
|
||||
indexing_context.index.localized_attributes_rules(&rtxn)?.unwrap_or_default();
|
||||
let document_tokenizer = DocumentTokenizer {
|
||||
tokenizer: &tokenizer,
|
||||
localized_attributes_rules: &localized_attributes_rules,
|
||||
max_positions_per_attributes: MAX_POSITION_PER_ATTRIBUTE,
|
||||
};
|
||||
let extractor_data = WordDocidsSettingsExtractorsData {
|
||||
tokenizer: document_tokenizer,
|
||||
max_memory_by_thread: indexing_context.grenad_parameters.max_memory_by_thread(),
|
||||
buckets: rayon::current_num_threads(),
|
||||
settings_delta,
|
||||
};
|
||||
let datastore = ThreadLocal::new();
|
||||
{
|
||||
let span = tracing::debug_span!(target: "indexing::documents::extract", "vectors");
|
||||
let _entered = span.enter();
|
||||
|
||||
settings_change_extract(
|
||||
documents,
|
||||
&extractor_data,
|
||||
indexing_context,
|
||||
extractor_allocs,
|
||||
&datastore,
|
||||
step,
|
||||
)?;
|
||||
}
|
||||
|
||||
let mut merger = WordDocidsCaches::new();
|
||||
for cache in datastore.into_iter().flat_map(RefCell::into_inner) {
|
||||
merger.push(cache)?;
|
||||
}
|
||||
|
||||
Ok(merger)
|
||||
}
|
||||
|
||||
/// Extracts document words from a settings change.
|
||||
fn extract_document_from_settings_change<SD: SettingsDelta>(
|
||||
document: DocumentIdentifiers<'_>,
|
||||
context: &DocumentContext<RefCell<Option<WordDocidsBalancedCaches>>>,
|
||||
document_tokenizer: &DocumentTokenizer,
|
||||
settings_delta: &SD,
|
||||
) -> Result<()> {
|
||||
let mut cached_sorter_ref = context.data.borrow_mut_or_yield();
|
||||
let cached_sorter = cached_sorter_ref.as_mut().unwrap();
|
||||
let doc_alloc = &context.doc_alloc;
|
||||
|
||||
let new_fields_ids_map = settings_delta.new_fields_ids_map();
|
||||
let old_fields_ids_map = context.index.fields_ids_map_with_metadata(&context.rtxn)?;
|
||||
let old_searchable = settings_delta.old_searchable_attributes().as_ref();
|
||||
let new_searchable = settings_delta.new_searchable_attributes().as_ref();
|
||||
|
||||
let current_document = document.current(
|
||||
&context.rtxn,
|
||||
context.index,
|
||||
old_fields_ids_map.as_fields_ids_map(),
|
||||
)?;
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq)]
|
||||
enum ActionToOperate {
|
||||
ReindexAllFields,
|
||||
// TODO improve by listing field prefixes
|
||||
IndexAddedFields,
|
||||
SkipDocument,
|
||||
}
|
||||
|
||||
let mut action = ActionToOperate::SkipDocument;
|
||||
// Here we do a preliminary check to determine the action to take.
|
||||
// This check doesn't trigger the tokenizer as we never return
|
||||
// PatternMatch::Match.
|
||||
document_tokenizer.tokenize_document(
|
||||
current_document,
|
||||
&mut |field_name| {
|
||||
let fid = new_fields_ids_map.id(field_name).expect("All fields IDs must exist");
|
||||
|
||||
// If the document must be reindexed, early return NoMatch to stop the scanning process.
|
||||
if action == ActionToOperate::ReindexAllFields {
|
||||
return Ok((fid, PatternMatch::NoMatch));
|
||||
}
|
||||
|
||||
let old_field_metadata = old_fields_ids_map.metadata(fid).unwrap();
|
||||
let new_field_metadata = new_fields_ids_map.metadata(fid).unwrap();
|
||||
|
||||
action = match (old_field_metadata, new_field_metadata) {
|
||||
// At least one field is added or removed from the exact fields => ReindexAllFields
|
||||
(Metadata { exact: old_exact, .. }, Metadata { exact: new_exact, .. })
|
||||
if old_exact != new_exact =>
|
||||
{
|
||||
ActionToOperate::ReindexAllFields
|
||||
}
|
||||
// At least one field is removed from the searchable fields => ReindexAllFields
|
||||
(Metadata { searchable: Some(_), .. }, Metadata { searchable: None, .. }) => {
|
||||
ActionToOperate::ReindexAllFields
|
||||
}
|
||||
// At least one field is added in the searchable fields => IndexAddedFields
|
||||
(Metadata { searchable: None, .. }, Metadata { searchable: Some(_), .. }) => {
|
||||
// We can safely overwrite the action, because we early return when action is ReindexAllFields.
|
||||
ActionToOperate::IndexAddedFields
|
||||
}
|
||||
_ => action,
|
||||
};
|
||||
|
||||
Ok((fid, PatternMatch::Parent))
|
||||
},
|
||||
&mut |_, _, _, _| Ok(()),
|
||||
)?;
|
||||
|
||||
// Early return when we don't need to index the document
|
||||
if action == ActionToOperate::SkipDocument {
|
||||
return Ok(());
|
||||
}
|
||||
|
||||
let mut should_tokenize = |field_name: &str| {
|
||||
let field_id = new_fields_ids_map.id(field_name).expect("All fields IDs must exist");
|
||||
let old_field_metadata = old_fields_ids_map.metadata(field_id).unwrap();
|
||||
let new_field_metadata = new_fields_ids_map.metadata(field_id).unwrap();
|
||||
|
||||
let pattern_match = match action {
|
||||
ActionToOperate::ReindexAllFields => {
|
||||
if old_field_metadata.is_searchable() || new_field_metadata.is_searchable() {
|
||||
PatternMatch::Match
|
||||
// If any old or new field is searchable then we need to iterate over all fields
|
||||
// else if any field matches we need to iterate over all fields
|
||||
} else if has_searchable_children(
|
||||
field_name,
|
||||
old_searchable.zip(new_searchable).map(|(old, new)| old.iter().chain(new)),
|
||||
) {
|
||||
PatternMatch::Parent
|
||||
} else {
|
||||
PatternMatch::NoMatch
|
||||
}
|
||||
}
|
||||
ActionToOperate::IndexAddedFields => {
|
||||
// Was not searchable but now is
|
||||
if !old_field_metadata.is_searchable() && new_field_metadata.is_searchable() {
|
||||
PatternMatch::Match
|
||||
// If the field is now a parent of a searchable field
|
||||
} else if has_searchable_children(field_name, new_searchable) {
|
||||
PatternMatch::Parent
|
||||
} else {
|
||||
PatternMatch::NoMatch
|
||||
}
|
||||
}
|
||||
ActionToOperate::SkipDocument => unreachable!(),
|
||||
};
|
||||
|
||||
Ok((field_id, pattern_match))
|
||||
};
|
||||
|
||||
let old_disabled_typos_terms = settings_delta.old_disabled_typos_terms();
|
||||
let new_disabled_typos_terms = settings_delta.new_disabled_typos_terms();
|
||||
let mut token_fn = |_field_name: &str, field_id, pos, word: &str| {
|
||||
let old_field_metadata = old_fields_ids_map.metadata(field_id).unwrap();
|
||||
let new_field_metadata = new_fields_ids_map.metadata(field_id).unwrap();
|
||||
|
||||
match (old_field_metadata, new_field_metadata) {
|
||||
(
|
||||
Metadata { searchable: Some(_), exact: old_exact, .. },
|
||||
Metadata { searchable: None, .. },
|
||||
) => cached_sorter.insert_del_u32(
|
||||
field_id,
|
||||
pos,
|
||||
word,
|
||||
old_exact || old_disabled_typos_terms.is_exact(word),
|
||||
// We deleted the field globally
|
||||
FieldDbExtraction::Skip,
|
||||
document.docid(),
|
||||
doc_alloc,
|
||||
),
|
||||
(
|
||||
Metadata { searchable: None, .. },
|
||||
Metadata { searchable: Some(_), exact: new_exact, .. },
|
||||
) => cached_sorter.insert_add_u32(
|
||||
field_id,
|
||||
pos,
|
||||
word,
|
||||
new_exact || new_disabled_typos_terms.is_exact(word),
|
||||
FieldDbExtraction::Extract,
|
||||
document.docid(),
|
||||
doc_alloc,
|
||||
),
|
||||
(Metadata { searchable: None, .. }, Metadata { searchable: None, .. }) => {
|
||||
unreachable!()
|
||||
}
|
||||
(Metadata { exact: old_exact, .. }, Metadata { exact: new_exact, .. }) => {
|
||||
cached_sorter.insert_del_u32(
|
||||
field_id,
|
||||
pos,
|
||||
word,
|
||||
old_exact || old_disabled_typos_terms.is_exact(word),
|
||||
// The field has already been extracted
|
||||
FieldDbExtraction::Skip,
|
||||
document.docid(),
|
||||
doc_alloc,
|
||||
)?;
|
||||
cached_sorter.insert_add_u32(
|
||||
field_id,
|
||||
pos,
|
||||
word,
|
||||
new_exact || new_disabled_typos_terms.is_exact(word),
|
||||
// The field has already been extracted
|
||||
FieldDbExtraction::Skip,
|
||||
document.docid(),
|
||||
doc_alloc,
|
||||
)
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
// TODO we must tokenize twice when we change global parameters like stop words,
|
||||
// the language settings, dictionary, separators, non-separators...
|
||||
document_tokenizer.tokenize_document(
|
||||
current_document,
|
||||
&mut should_tokenize,
|
||||
&mut token_fn,
|
||||
)?;
|
||||
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
@@ -6,24 +6,17 @@ use bumpalo::Bump;
|
||||
|
||||
use super::match_searchable_field;
|
||||
use super::tokenize_document::{tokenizer_builder, DocumentTokenizer};
|
||||
use crate::fields_ids_map::metadata::Metadata;
|
||||
use crate::proximity::ProximityPrecision::*;
|
||||
use crate::proximity::{index_proximity, MAX_DISTANCE};
|
||||
use crate::update::new::document::{Document, DocumentContext};
|
||||
use crate::update::new::extract::cache::BalancedCaches;
|
||||
use crate::update::new::indexer::document_changes::{
|
||||
extract, DocumentChanges, Extractor, IndexingContext,
|
||||
};
|
||||
use crate::update::new::indexer::settings_change_extract;
|
||||
use crate::update::new::indexer::settings_changes::{
|
||||
DocumentsIndentifiers, SettingsChangeExtractor,
|
||||
};
|
||||
use crate::update::new::ref_cell_ext::RefCellExt as _;
|
||||
use crate::update::new::steps::IndexingStep;
|
||||
use crate::update::new::thread_local::{FullySend, ThreadLocal};
|
||||
use crate::update::new::{DocumentChange, DocumentIdentifiers};
|
||||
use crate::update::settings::SettingsDelta;
|
||||
use crate::{FieldId, PatternMatch, Result, UserError, MAX_POSITION_PER_ATTRIBUTE};
|
||||
use crate::update::new::DocumentChange;
|
||||
use crate::{FieldId, GlobalFieldsIdsMap, Result, MAX_POSITION_PER_ATTRIBUTE};
|
||||
|
||||
pub struct WordPairProximityDocidsExtractorData<'a> {
|
||||
tokenizer: DocumentTokenizer<'a>,
|
||||
@@ -123,7 +116,7 @@ impl WordPairProximityDocidsExtractor {
|
||||
// and to store the docids of the documents that have a number of words in a given field
|
||||
// equal to or under than MAX_COUNTED_WORDS.
|
||||
fn extract_document_change(
|
||||
context: &DocumentContext<RefCell<BalancedCaches<'_>>>,
|
||||
context: &DocumentContext<RefCell<BalancedCaches>>,
|
||||
document_tokenizer: &DocumentTokenizer,
|
||||
searchable_attributes: Option<&[&str]>,
|
||||
document_change: DocumentChange,
|
||||
@@ -154,12 +147,8 @@ impl WordPairProximityDocidsExtractor {
|
||||
process_document_tokens(
|
||||
document,
|
||||
document_tokenizer,
|
||||
new_fields_ids_map,
|
||||
&mut word_positions,
|
||||
&mut |field_name| {
|
||||
new_fields_ids_map
|
||||
.id_with_metadata_or_insert(field_name)
|
||||
.ok_or(UserError::AttributeLimitReached.into())
|
||||
},
|
||||
&mut |(w1, w2), prox| {
|
||||
del_word_pair_proximity.push(((w1, w2), prox));
|
||||
},
|
||||
@@ -181,12 +170,8 @@ impl WordPairProximityDocidsExtractor {
|
||||
process_document_tokens(
|
||||
document,
|
||||
document_tokenizer,
|
||||
new_fields_ids_map,
|
||||
&mut word_positions,
|
||||
&mut |field_name| {
|
||||
new_fields_ids_map
|
||||
.id_with_metadata_or_insert(field_name)
|
||||
.ok_or(UserError::AttributeLimitReached.into())
|
||||
},
|
||||
&mut |(w1, w2), prox| {
|
||||
del_word_pair_proximity.push(((w1, w2), prox));
|
||||
},
|
||||
@@ -195,12 +180,8 @@ impl WordPairProximityDocidsExtractor {
|
||||
process_document_tokens(
|
||||
document,
|
||||
document_tokenizer,
|
||||
new_fields_ids_map,
|
||||
&mut word_positions,
|
||||
&mut |field_name| {
|
||||
new_fields_ids_map
|
||||
.id_with_metadata_or_insert(field_name)
|
||||
.ok_or(UserError::AttributeLimitReached.into())
|
||||
},
|
||||
&mut |(w1, w2), prox| {
|
||||
add_word_pair_proximity.push(((w1, w2), prox));
|
||||
},
|
||||
@@ -211,12 +192,8 @@ impl WordPairProximityDocidsExtractor {
|
||||
process_document_tokens(
|
||||
document,
|
||||
document_tokenizer,
|
||||
new_fields_ids_map,
|
||||
&mut word_positions,
|
||||
&mut |field_name| {
|
||||
new_fields_ids_map
|
||||
.id_with_metadata_or_insert(field_name)
|
||||
.ok_or(UserError::AttributeLimitReached.into())
|
||||
},
|
||||
&mut |(w1, w2), prox| {
|
||||
add_word_pair_proximity.push(((w1, w2), prox));
|
||||
},
|
||||
@@ -280,8 +257,8 @@ fn drain_word_positions(
|
||||
fn process_document_tokens<'doc>(
|
||||
document: impl Document<'doc>,
|
||||
document_tokenizer: &DocumentTokenizer,
|
||||
fields_ids_map: &mut GlobalFieldsIdsMap,
|
||||
word_positions: &mut VecDeque<(Rc<str>, u16)>,
|
||||
field_id_and_metadata: &mut impl FnMut(&str) -> Result<(FieldId, Metadata)>,
|
||||
word_pair_proximity: &mut impl FnMut((Rc<str>, Rc<str>), u8),
|
||||
) -> Result<()> {
|
||||
let mut field_id = None;
|
||||
@@ -302,248 +279,8 @@ fn process_document_tokens<'doc>(
|
||||
word_positions.push_back((Rc::from(word), pos));
|
||||
Ok(())
|
||||
};
|
||||
|
||||
let mut should_tokenize = |field_name: &str| {
|
||||
let (field_id, meta) = field_id_and_metadata(field_name)?;
|
||||
|
||||
let pattern_match = if meta.is_searchable() {
|
||||
PatternMatch::Match
|
||||
} else {
|
||||
// TODO: should be a match on the field_name using `match_field_legacy` function,
|
||||
// but for legacy reasons we iterate over all the fields to fill the field_id_map.
|
||||
PatternMatch::Parent
|
||||
};
|
||||
|
||||
Ok((field_id, pattern_match))
|
||||
};
|
||||
|
||||
document_tokenizer.tokenize_document(document, &mut should_tokenize, &mut token_fn)?;
|
||||
document_tokenizer.tokenize_document(document, fields_ids_map, &mut token_fn)?;
|
||||
|
||||
drain_word_positions(word_positions, word_pair_proximity);
|
||||
Ok(())
|
||||
}
|
||||
|
||||
pub struct WordPairProximityDocidsSettingsExtractorsData<'a, SD> {
|
||||
tokenizer: DocumentTokenizer<'a>,
|
||||
max_memory_by_thread: Option<usize>,
|
||||
buckets: usize,
|
||||
settings_delta: &'a SD,
|
||||
}
|
||||
|
||||
impl<'extractor, SD: SettingsDelta + Sync> SettingsChangeExtractor<'extractor>
|
||||
for WordPairProximityDocidsSettingsExtractorsData<'_, SD>
|
||||
{
|
||||
type Data = RefCell<BalancedCaches<'extractor>>;
|
||||
|
||||
fn init_data<'doc>(&'doc self, extractor_alloc: &'extractor Bump) -> crate::Result<Self::Data> {
|
||||
Ok(RefCell::new(BalancedCaches::new_in(
|
||||
self.buckets,
|
||||
self.max_memory_by_thread,
|
||||
extractor_alloc,
|
||||
)))
|
||||
}
|
||||
|
||||
fn process<'doc>(
|
||||
&'doc self,
|
||||
documents: impl Iterator<Item = crate::Result<DocumentIdentifiers<'doc>>>,
|
||||
context: &'doc DocumentContext<Self::Data>,
|
||||
) -> crate::Result<()> {
|
||||
for document in documents {
|
||||
let document = document?;
|
||||
SettingsChangeWordPairProximityDocidsExtractors::extract_document_from_settings_change(
|
||||
document,
|
||||
context,
|
||||
&self.tokenizer,
|
||||
self.settings_delta,
|
||||
)?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
pub struct SettingsChangeWordPairProximityDocidsExtractors;
|
||||
|
||||
impl SettingsChangeWordPairProximityDocidsExtractors {
|
||||
pub fn run_extraction<'fid, 'indexer, 'index, 'extractor, SD, MSP>(
|
||||
settings_delta: &SD,
|
||||
documents: &'indexer DocumentsIndentifiers<'indexer>,
|
||||
indexing_context: IndexingContext<'fid, 'indexer, 'index, MSP>,
|
||||
extractor_allocs: &'extractor mut ThreadLocal<FullySend<Bump>>,
|
||||
step: IndexingStep,
|
||||
) -> Result<Vec<BalancedCaches<'extractor>>>
|
||||
where
|
||||
SD: SettingsDelta + Sync,
|
||||
MSP: Fn() -> bool + Sync,
|
||||
{
|
||||
// Warning: this is duplicated code from extract_word_docids.rs
|
||||
let rtxn = indexing_context.index.read_txn()?;
|
||||
let stop_words = indexing_context.index.stop_words(&rtxn)?;
|
||||
let allowed_separators = indexing_context.index.allowed_separators(&rtxn)?;
|
||||
let allowed_separators: Option<Vec<_>> =
|
||||
allowed_separators.as_ref().map(|s| s.iter().map(String::as_str).collect());
|
||||
let dictionary = indexing_context.index.dictionary(&rtxn)?;
|
||||
let dictionary: Option<Vec<_>> =
|
||||
dictionary.as_ref().map(|s| s.iter().map(String::as_str).collect());
|
||||
let mut builder = tokenizer_builder(
|
||||
stop_words.as_ref(),
|
||||
allowed_separators.as_deref(),
|
||||
dictionary.as_deref(),
|
||||
);
|
||||
let tokenizer = builder.build();
|
||||
let localized_attributes_rules =
|
||||
indexing_context.index.localized_attributes_rules(&rtxn)?.unwrap_or_default();
|
||||
let document_tokenizer = DocumentTokenizer {
|
||||
tokenizer: &tokenizer,
|
||||
localized_attributes_rules: &localized_attributes_rules,
|
||||
max_positions_per_attributes: MAX_POSITION_PER_ATTRIBUTE,
|
||||
};
|
||||
let extractor_data = WordPairProximityDocidsSettingsExtractorsData {
|
||||
tokenizer: document_tokenizer,
|
||||
max_memory_by_thread: indexing_context.grenad_parameters.max_memory_by_thread(),
|
||||
buckets: rayon::current_num_threads(),
|
||||
settings_delta,
|
||||
};
|
||||
let datastore = ThreadLocal::new();
|
||||
{
|
||||
let span = tracing::trace_span!(target: "indexing::documents::extract", "word_pair_proximity_docids_extraction");
|
||||
let _entered = span.enter();
|
||||
|
||||
settings_change_extract(
|
||||
documents,
|
||||
&extractor_data,
|
||||
indexing_context,
|
||||
extractor_allocs,
|
||||
&datastore,
|
||||
step,
|
||||
)?;
|
||||
}
|
||||
|
||||
Ok(datastore.into_iter().map(RefCell::into_inner).collect())
|
||||
}
|
||||
|
||||
/// Extracts document words from a settings change.
|
||||
fn extract_document_from_settings_change<SD: SettingsDelta>(
|
||||
document: DocumentIdentifiers<'_>,
|
||||
context: &DocumentContext<RefCell<BalancedCaches<'_>>>,
|
||||
document_tokenizer: &DocumentTokenizer,
|
||||
settings_delta: &SD,
|
||||
) -> Result<()> {
|
||||
let mut cached_sorter = context.data.borrow_mut_or_yield();
|
||||
let doc_alloc = &context.doc_alloc;
|
||||
|
||||
let new_fields_ids_map = settings_delta.new_fields_ids_map();
|
||||
let old_fields_ids_map = settings_delta.old_fields_ids_map();
|
||||
let old_proximity_precision = *settings_delta.old_proximity_precision();
|
||||
let new_proximity_precision = *settings_delta.new_proximity_precision();
|
||||
|
||||
let current_document = document.current(
|
||||
&context.rtxn,
|
||||
context.index,
|
||||
old_fields_ids_map.as_fields_ids_map(),
|
||||
)?;
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq)]
|
||||
enum ActionToOperate {
|
||||
ReindexAllFields,
|
||||
SkipDocument,
|
||||
}
|
||||
|
||||
// TODO prefix_fid delete_old_fid_based_databases
|
||||
let mut action = match (old_proximity_precision, new_proximity_precision) {
|
||||
(ByAttribute, ByWord) => ActionToOperate::ReindexAllFields,
|
||||
(_, _) => ActionToOperate::SkipDocument,
|
||||
};
|
||||
|
||||
// Here we do a preliminary check to determine the action to take.
|
||||
// This check doesn't trigger the tokenizer as we never return
|
||||
// PatternMatch::Match.
|
||||
if action != ActionToOperate::ReindexAllFields {
|
||||
document_tokenizer.tokenize_document(
|
||||
current_document,
|
||||
&mut |field_name| {
|
||||
let fid = new_fields_ids_map.id(field_name).expect("All fields IDs must exist");
|
||||
|
||||
// If the document must be reindexed, early return NoMatch to stop the scanning process.
|
||||
if action == ActionToOperate::ReindexAllFields {
|
||||
return Ok((fid, PatternMatch::NoMatch));
|
||||
}
|
||||
|
||||
let old_field_metadata = old_fields_ids_map.metadata(fid).unwrap();
|
||||
let new_field_metadata = new_fields_ids_map.metadata(fid).unwrap();
|
||||
|
||||
action = match (old_field_metadata, new_field_metadata) {
|
||||
// At least one field is removed or added from the searchable fields
|
||||
(
|
||||
Metadata { searchable: Some(_), .. },
|
||||
Metadata { searchable: None, .. },
|
||||
)
|
||||
| (
|
||||
Metadata { searchable: None, .. },
|
||||
Metadata { searchable: Some(_), .. },
|
||||
) => ActionToOperate::ReindexAllFields,
|
||||
_ => action,
|
||||
};
|
||||
|
||||
Ok((fid, PatternMatch::Parent))
|
||||
},
|
||||
&mut |_, _, _, _| Ok(()),
|
||||
)?;
|
||||
}
|
||||
|
||||
// Early return when we don't need to index the document
|
||||
if action == ActionToOperate::SkipDocument {
|
||||
return Ok(());
|
||||
}
|
||||
|
||||
let mut del_word_pair_proximity = bumpalo::collections::Vec::new_in(doc_alloc);
|
||||
let mut add_word_pair_proximity = bumpalo::collections::Vec::new_in(doc_alloc);
|
||||
|
||||
// is a vecdequeue, and will be smol, so can stay on the heap for now
|
||||
let mut word_positions: VecDeque<(Rc<str>, u16)> =
|
||||
VecDeque::with_capacity(MAX_DISTANCE as usize);
|
||||
|
||||
process_document_tokens(
|
||||
current_document,
|
||||
// TODO Tokenize must be based on old settings
|
||||
document_tokenizer,
|
||||
&mut word_positions,
|
||||
&mut |field_name| {
|
||||
Ok(old_fields_ids_map.id_with_metadata(field_name).expect("All fields must exist"))
|
||||
},
|
||||
&mut |(w1, w2), prox| {
|
||||
del_word_pair_proximity.push(((w1, w2), prox));
|
||||
},
|
||||
)?;
|
||||
|
||||
process_document_tokens(
|
||||
current_document,
|
||||
// TODO Tokenize must be based on new settings
|
||||
document_tokenizer,
|
||||
&mut word_positions,
|
||||
&mut |field_name| {
|
||||
Ok(new_fields_ids_map.id_with_metadata(field_name).expect("All fields must exist"))
|
||||
},
|
||||
&mut |(w1, w2), prox| {
|
||||
add_word_pair_proximity.push(((w1, w2), prox));
|
||||
},
|
||||
)?;
|
||||
|
||||
let mut key_buffer = bumpalo::collections::Vec::new_in(doc_alloc);
|
||||
|
||||
del_word_pair_proximity.sort_unstable();
|
||||
del_word_pair_proximity.dedup_by(|(k1, _), (k2, _)| k1 == k2);
|
||||
for ((w1, w2), prox) in del_word_pair_proximity.iter() {
|
||||
let key = build_key(*prox, w1, w2, &mut key_buffer);
|
||||
cached_sorter.insert_del_u32(key, document.docid())?;
|
||||
}
|
||||
|
||||
add_word_pair_proximity.sort_unstable();
|
||||
add_word_pair_proximity.dedup_by(|(k1, _), (k2, _)| k1 == k2);
|
||||
for ((w1, w2), prox) in add_word_pair_proximity.iter() {
|
||||
let key = build_key(*prox, w1, w2, &mut key_buffer);
|
||||
cached_sorter.insert_add_u32(key, document.docid())?;
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
@@ -2,12 +2,8 @@ mod extract_word_docids;
|
||||
mod extract_word_pair_proximity_docids;
|
||||
mod tokenize_document;
|
||||
|
||||
pub use extract_word_docids::{
|
||||
SettingsChangeWordDocidsExtractors, WordDocidsCaches, WordDocidsExtractors,
|
||||
};
|
||||
pub use extract_word_pair_proximity_docids::{
|
||||
SettingsChangeWordPairProximityDocidsExtractors, WordPairProximityDocidsExtractor,
|
||||
};
|
||||
pub use extract_word_docids::{WordDocidsCaches, WordDocidsExtractors};
|
||||
pub use extract_word_pair_proximity_docids::WordPairProximityDocidsExtractor;
|
||||
|
||||
use crate::attribute_patterns::{match_field_legacy, PatternMatch};
|
||||
|
||||
@@ -31,17 +27,3 @@ pub fn match_searchable_field(
|
||||
|
||||
selection
|
||||
}
|
||||
|
||||
/// return `true` if the provided `field_name` is a parent of at least one of the fields contained in `searchable`,
|
||||
/// or if `searchable` is `None`.
|
||||
fn has_searchable_children<I, A>(field_name: &str, searchable: Option<I>) -> bool
|
||||
where
|
||||
I: IntoIterator<Item = A>,
|
||||
A: AsRef<str>,
|
||||
{
|
||||
searchable.is_none_or(|fields| {
|
||||
fields
|
||||
.into_iter()
|
||||
.any(|attr| match_field_legacy(attr.as_ref(), field_name) == PatternMatch::Parent)
|
||||
})
|
||||
}
|
||||
|
||||
@@ -8,7 +8,10 @@ use crate::update::new::document::Document;
|
||||
use crate::update::new::extract::perm_json_p::{
|
||||
seek_leaf_values_in_array, seek_leaf_values_in_object, Depth,
|
||||
};
|
||||
use crate::{FieldId, InternalError, LocalizedAttributesRule, Result, MAX_WORD_LENGTH};
|
||||
use crate::{
|
||||
FieldId, GlobalFieldsIdsMap, InternalError, LocalizedAttributesRule, Result, UserError,
|
||||
MAX_WORD_LENGTH,
|
||||
};
|
||||
|
||||
// todo: should be crate::proximity::MAX_DISTANCE but it has been forgotten
|
||||
const MAX_DISTANCE: u32 = 8;
|
||||
@@ -23,25 +26,26 @@ impl DocumentTokenizer<'_> {
|
||||
pub fn tokenize_document<'doc>(
|
||||
&self,
|
||||
document: impl Document<'doc>,
|
||||
should_tokenize: &mut impl FnMut(&str) -> Result<(FieldId, PatternMatch)>,
|
||||
field_id_map: &mut GlobalFieldsIdsMap,
|
||||
token_fn: &mut impl FnMut(&str, FieldId, u16, &str) -> Result<()>,
|
||||
) -> Result<()> {
|
||||
let mut field_position = HashMap::new();
|
||||
for entry in document.iter_top_level_fields() {
|
||||
let (field_name, value) = entry?;
|
||||
|
||||
if let (_, PatternMatch::NoMatch) = should_tokenize(field_name)? {
|
||||
continue;
|
||||
}
|
||||
|
||||
let mut tokenize_field = |field_name: &str, _depth, value: &Value| {
|
||||
let (fid, pattern_match) = should_tokenize(field_name)?;
|
||||
if pattern_match == PatternMatch::Match {
|
||||
self.tokenize_field(fid, field_name, value, token_fn, &mut field_position)?;
|
||||
}
|
||||
Ok(pattern_match)
|
||||
let mut tokenize_field = |field_name: &str, _depth, value: &Value| {
|
||||
let Some((field_id, meta)) = field_id_map.id_with_metadata_or_insert(field_name) else {
|
||||
return Err(UserError::AttributeLimitReached.into());
|
||||
};
|
||||
|
||||
if meta.is_searchable() {
|
||||
self.tokenize_field(field_id, field_name, value, token_fn, &mut field_position)?;
|
||||
}
|
||||
|
||||
// todo: should be a match on the field_name using `match_field_legacy` function,
|
||||
// but for legacy reasons we iterate over all the fields to fill the field_id_map.
|
||||
Ok(PatternMatch::Match)
|
||||
};
|
||||
|
||||
for entry in document.iter_top_level_fields() {
|
||||
let (field_name, value) = entry?;
|
||||
// parse json.
|
||||
match serde_json::to_value(value).map_err(InternalError::SerdeJson)? {
|
||||
Value::Object(object) => seek_leaf_values_in_object(
|
||||
@@ -188,7 +192,7 @@ mod test {
|
||||
use super::*;
|
||||
use crate::fields_ids_map::metadata::{FieldIdMapWithMetadata, MetadataBuilder};
|
||||
use crate::update::new::document::{DocumentFromVersions, Versions};
|
||||
use crate::{FieldsIdsMap, GlobalFieldsIdsMap, UserError};
|
||||
use crate::FieldsIdsMap;
|
||||
|
||||
#[test]
|
||||
fn test_tokenize_document() {
|
||||
@@ -227,7 +231,6 @@ mod test {
|
||||
Default::default(),
|
||||
Default::default(),
|
||||
Default::default(),
|
||||
Default::default(),
|
||||
None,
|
||||
None,
|
||||
Default::default(),
|
||||
@@ -248,19 +251,15 @@ mod test {
|
||||
let document = Versions::single(document);
|
||||
let document = DocumentFromVersions::new(&document);
|
||||
|
||||
let mut should_tokenize = |field_name: &str| {
|
||||
let Some(field_id) = global_fields_ids_map.id_or_insert(field_name) else {
|
||||
return Err(UserError::AttributeLimitReached.into());
|
||||
};
|
||||
|
||||
Ok((field_id, PatternMatch::Match))
|
||||
};
|
||||
|
||||
document_tokenizer
|
||||
.tokenize_document(document, &mut should_tokenize, &mut |_fname, fid, pos, word| {
|
||||
words.insert([fid, pos], word.to_string());
|
||||
Ok(())
|
||||
})
|
||||
.tokenize_document(
|
||||
document,
|
||||
&mut global_fields_ids_map,
|
||||
&mut |_fname, fid, pos, word| {
|
||||
words.insert([fid, pos], word.to_string());
|
||||
Ok(())
|
||||
},
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
snapshot!(format!("{:#?}", words), @r###"
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
use std::cell::RefCell;
|
||||
use std::fmt::Debug;
|
||||
use std::sync::RwLock;
|
||||
|
||||
use bumpalo::collections::Vec as BVec;
|
||||
use bumpalo::Bump;
|
||||
@@ -28,10 +27,7 @@ use crate::vector::extractor::{
|
||||
use crate::vector::session::{EmbedSession, Input, Metadata, OnEmbed};
|
||||
use crate::vector::settings::ReindexAction;
|
||||
use crate::vector::{Embedding, RuntimeEmbedder, RuntimeEmbedders, RuntimeFragment};
|
||||
use crate::{
|
||||
DocumentId, FieldDistribution, GlobalFieldsIdsMap, InternalError, Result, ThreadPoolNoAbort,
|
||||
UserError,
|
||||
};
|
||||
use crate::{DocumentId, FieldDistribution, InternalError, Result, ThreadPoolNoAbort, UserError};
|
||||
|
||||
pub struct EmbeddingExtractor<'a, 'b> {
|
||||
embedders: &'a RuntimeEmbedders,
|
||||
@@ -325,15 +321,6 @@ impl<'extractor, SD: SettingsDelta + Sync> SettingsChangeExtractor<'extractor>
|
||||
let old_embedders = self.settings_delta.old_embedders();
|
||||
let unused_vectors_distribution = UnusedVectorsDistributionBump::new_in(&context.doc_alloc);
|
||||
|
||||
// We get a reference to the new and old fields ids maps but
|
||||
// note that those are local versions where updates to them
|
||||
// will not be reflected in the database. It's not an issue
|
||||
// because new settings do not generate new fields.
|
||||
let new_fields_ids_map = RwLock::new(self.settings_delta.new_fields_ids_map().clone());
|
||||
let new_fields_ids_map = RefCell::new(GlobalFieldsIdsMap::new(&new_fields_ids_map));
|
||||
let old_fields_ids_map = RwLock::new(self.settings_delta.old_fields_ids_map().clone());
|
||||
let old_fields_ids_map = RefCell::new(GlobalFieldsIdsMap::new(&old_fields_ids_map));
|
||||
|
||||
let mut all_chunks = BVec::with_capacity_in(embedders.len(), &context.doc_alloc);
|
||||
let embedder_configs = context.index.embedding_configs();
|
||||
for (embedder_name, action) in self.settings_delta.embedder_actions().iter() {
|
||||
@@ -409,7 +396,6 @@ impl<'extractor, SD: SettingsDelta + Sync> SettingsChangeExtractor<'extractor>
|
||||
if !must_regenerate {
|
||||
continue;
|
||||
}
|
||||
|
||||
// we need to regenerate the prompts for the document
|
||||
chunks.settings_change_autogenerated(
|
||||
document.docid(),
|
||||
@@ -420,8 +406,7 @@ impl<'extractor, SD: SettingsDelta + Sync> SettingsChangeExtractor<'extractor>
|
||||
context.db_fields_ids_map,
|
||||
)?,
|
||||
self.settings_delta,
|
||||
&old_fields_ids_map,
|
||||
&new_fields_ids_map,
|
||||
context.new_fields_ids_map,
|
||||
&unused_vectors_distribution,
|
||||
old_is_user_provided,
|
||||
fragments_changed,
|
||||
@@ -457,8 +442,7 @@ impl<'extractor, SD: SettingsDelta + Sync> SettingsChangeExtractor<'extractor>
|
||||
context.db_fields_ids_map,
|
||||
)?,
|
||||
self.settings_delta,
|
||||
&old_fields_ids_map,
|
||||
&new_fields_ids_map,
|
||||
context.new_fields_ids_map,
|
||||
&unused_vectors_distribution,
|
||||
old_is_user_provided,
|
||||
true,
|
||||
@@ -654,8 +638,7 @@ impl<'a, 'b, 'extractor> Chunks<'a, 'b, 'extractor> {
|
||||
external_docid: &'a str,
|
||||
document: D,
|
||||
settings_delta: &SD,
|
||||
old_fields_ids_map: &'a RefCell<GlobalFieldsIdsMap<'a>>,
|
||||
new_fields_ids_map: &'a RefCell<GlobalFieldsIdsMap<'a>>,
|
||||
fields_ids_map: &'a RefCell<crate::GlobalFieldsIdsMap>,
|
||||
unused_vectors_distribution: &UnusedVectorsDistributionBump<'a>,
|
||||
old_is_user_provided: bool,
|
||||
full_reindex: bool,
|
||||
@@ -750,17 +733,10 @@ impl<'a, 'b, 'extractor> Chunks<'a, 'b, 'extractor> {
|
||||
old_embedder.as_ref().map(|old_embedder| &old_embedder.document_template)
|
||||
};
|
||||
|
||||
let extractor = DocumentTemplateExtractor::new(
|
||||
document_template,
|
||||
doc_alloc,
|
||||
new_fields_ids_map,
|
||||
);
|
||||
let extractor =
|
||||
DocumentTemplateExtractor::new(document_template, doc_alloc, fields_ids_map);
|
||||
let old_extractor = old_document_template.map(|old_document_template| {
|
||||
DocumentTemplateExtractor::new(
|
||||
old_document_template,
|
||||
doc_alloc,
|
||||
old_fields_ids_map,
|
||||
)
|
||||
DocumentTemplateExtractor::new(old_document_template, doc_alloc, fields_ids_map)
|
||||
});
|
||||
let metadata =
|
||||
Metadata { docid, external_docid, extractor_id: extractor.extractor_id() };
|
||||
|
||||
@@ -1,9 +0,0 @@
|
||||
pub mod sharding {
|
||||
pub struct Shards;
|
||||
|
||||
impl Shards {
|
||||
pub fn must_process(&self, _docid: &str) -> bool {
|
||||
true
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -17,7 +17,7 @@ use super::guess_primary_key::retrieve_or_guess_primary_key;
|
||||
use crate::documents::PrimaryKey;
|
||||
use crate::progress::{AtomicPayloadStep, Progress};
|
||||
use crate::update::new::document::{DocumentContext, Versions};
|
||||
use crate::update::new::indexer::current_edition::sharding::Shards;
|
||||
use crate::update::new::indexer::enterprise_edition::sharding::Shards;
|
||||
use crate::update::new::steps::IndexingStep;
|
||||
use crate::update::new::thread_local::MostlySend;
|
||||
use crate::update::new::{DocumentIdentifiers, Insertion, Update};
|
||||
|
||||
@@ -372,10 +372,11 @@ where
|
||||
SD: SettingsDelta + Sync,
|
||||
{
|
||||
// Create the list of document ids to extract
|
||||
let index = indexing_context.index;
|
||||
let rtxn = index.read_txn()?;
|
||||
let all_document_ids = index.documents_ids(&rtxn)?.into_iter().collect::<Vec<_>>();
|
||||
let primary_key = primary_key_from_db(index, &rtxn, &indexing_context.db_fields_ids_map)?;
|
||||
let rtxn = indexing_context.index.read_txn()?;
|
||||
let all_document_ids =
|
||||
indexing_context.index.documents_ids(&rtxn)?.into_iter().collect::<Vec<_>>();
|
||||
let primary_key =
|
||||
primary_key_from_db(indexing_context.index, &rtxn, &indexing_context.db_fields_ids_map)?;
|
||||
let documents = DocumentsIndentifiers::new(&all_document_ids, primary_key);
|
||||
|
||||
let span =
|
||||
@@ -390,133 +391,6 @@ where
|
||||
extractor_allocs,
|
||||
)?;
|
||||
|
||||
{
|
||||
let WordDocidsCaches {
|
||||
word_docids,
|
||||
word_fid_docids,
|
||||
exact_word_docids,
|
||||
word_position_docids,
|
||||
fid_word_count_docids,
|
||||
} = {
|
||||
let span = tracing::trace_span!(target: "indexing::documents::extract", "word_docids");
|
||||
let _entered = span.enter();
|
||||
SettingsChangeWordDocidsExtractors::run_extraction(
|
||||
settings_delta,
|
||||
&documents,
|
||||
indexing_context,
|
||||
extractor_allocs,
|
||||
IndexingStep::ExtractingWords,
|
||||
)?
|
||||
};
|
||||
|
||||
indexing_context.progress.update_progress(IndexingStep::MergingWordCaches);
|
||||
|
||||
{
|
||||
let span = tracing::trace_span!(target: "indexing::documents::merge", "word_docids");
|
||||
let _entered = span.enter();
|
||||
indexing_context.progress.update_progress(MergingWordCache::WordDocids);
|
||||
|
||||
merge_and_send_docids(
|
||||
word_docids,
|
||||
index.word_docids.remap_types(),
|
||||
index,
|
||||
extractor_sender.docids::<WordDocids>(),
|
||||
&indexing_context.must_stop_processing,
|
||||
)?;
|
||||
}
|
||||
|
||||
{
|
||||
let span =
|
||||
tracing::trace_span!(target: "indexing::documents::merge", "word_fid_docids");
|
||||
let _entered = span.enter();
|
||||
indexing_context.progress.update_progress(MergingWordCache::WordFieldIdDocids);
|
||||
|
||||
merge_and_send_docids(
|
||||
word_fid_docids,
|
||||
index.word_fid_docids.remap_types(),
|
||||
index,
|
||||
extractor_sender.docids::<WordFidDocids>(),
|
||||
&indexing_context.must_stop_processing,
|
||||
)?;
|
||||
}
|
||||
|
||||
{
|
||||
let span =
|
||||
tracing::trace_span!(target: "indexing::documents::merge", "exact_word_docids");
|
||||
let _entered = span.enter();
|
||||
indexing_context.progress.update_progress(MergingWordCache::ExactWordDocids);
|
||||
|
||||
merge_and_send_docids(
|
||||
exact_word_docids,
|
||||
index.exact_word_docids.remap_types(),
|
||||
index,
|
||||
extractor_sender.docids::<ExactWordDocids>(),
|
||||
&indexing_context.must_stop_processing,
|
||||
)?;
|
||||
}
|
||||
|
||||
{
|
||||
let span =
|
||||
tracing::trace_span!(target: "indexing::documents::merge", "word_position_docids");
|
||||
let _entered = span.enter();
|
||||
indexing_context.progress.update_progress(MergingWordCache::WordPositionDocids);
|
||||
|
||||
merge_and_send_docids(
|
||||
word_position_docids,
|
||||
index.word_position_docids.remap_types(),
|
||||
index,
|
||||
extractor_sender.docids::<WordPositionDocids>(),
|
||||
&indexing_context.must_stop_processing,
|
||||
)?;
|
||||
}
|
||||
|
||||
{
|
||||
let span =
|
||||
tracing::trace_span!(target: "indexing::documents::merge", "fid_word_count_docids");
|
||||
let _entered = span.enter();
|
||||
indexing_context.progress.update_progress(MergingWordCache::FieldIdWordCountDocids);
|
||||
|
||||
merge_and_send_docids(
|
||||
fid_word_count_docids,
|
||||
index.field_id_word_count_docids.remap_types(),
|
||||
index,
|
||||
extractor_sender.docids::<FidWordCountDocids>(),
|
||||
&indexing_context.must_stop_processing,
|
||||
)?;
|
||||
}
|
||||
}
|
||||
|
||||
// Run the proximity extraction only if the precision is ByWord.
|
||||
let new_proximity_precision = settings_delta.new_proximity_precision();
|
||||
if *new_proximity_precision == ProximityPrecision::ByWord {
|
||||
let caches = {
|
||||
let span = tracing::trace_span!(target: "indexing::documents::extract", "word_pair_proximity_docids");
|
||||
let _entered = span.enter();
|
||||
|
||||
SettingsChangeWordPairProximityDocidsExtractors::run_extraction(
|
||||
settings_delta,
|
||||
&documents,
|
||||
indexing_context,
|
||||
extractor_allocs,
|
||||
IndexingStep::ExtractingWordProximity,
|
||||
)?
|
||||
};
|
||||
|
||||
{
|
||||
let span = tracing::trace_span!(target: "indexing::documents::merge", "word_pair_proximity_docids");
|
||||
let _entered = span.enter();
|
||||
indexing_context.progress.update_progress(IndexingStep::MergingWordProximity);
|
||||
|
||||
merge_and_send_docids(
|
||||
caches,
|
||||
index.word_pair_proximity_docids.remap_types(),
|
||||
index,
|
||||
extractor_sender.docids::<WordPairProximityDocids>(),
|
||||
&indexing_context.must_stop_processing,
|
||||
)?;
|
||||
}
|
||||
}
|
||||
|
||||
'vectors: {
|
||||
if settings_delta.embedder_actions().is_empty() {
|
||||
break 'vectors;
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user