Compare commits

..

23 Commits

Author SHA1 Message Date
Clément Renault
5e1af30b42 Improve the way we create the snapshot path 2025-10-20 16:48:14 +02:00
Clément Renault
d298b21a95 Remove useless dependencies 2025-10-20 16:48:14 +02:00
Kerollmops
a4ad87febf Make it finaly work but without async on the write side 2025-10-20 16:48:14 +02:00
Kerollmops
2caa2be441 Seeking the tasks/data.mdb file to the begining made the trick 2025-10-20 16:48:14 +02:00
Kerollmops
a829ded023 Improve understanding of S3-related errors 2025-10-20 16:48:14 +02:00
Kerollmops
98be43b66b Retrieve the bytesMut only when released 2025-10-20 16:48:14 +02:00
Kerollmops
3ec4750426 Fix minimum part size 2025-10-20 16:48:14 +02:00
Kerollmops
d717ec3486 Improve error messaging when missing env var 2025-10-20 16:48:14 +02:00
Clément Renault
0c06bdefac WIP 2025-10-20 16:48:13 +02:00
Kerollmops
62a8133bcd WIP Do more tests 2025-10-20 16:48:13 +02:00
Clément Renault
c1f7542dfa WIP sending multiparts of 250MiB 2025-10-20 16:48:13 +02:00
Clément Renault
9105e8bb8c Rename the update_path function 2025-10-20 16:48:13 +02:00
Clément Renault
59e2394e69 Geenrate an async tarball 2025-10-20 16:48:13 +02:00
Kerollmops
430bc91c4c WIP 2025-10-20 16:48:13 +02:00
Kerollmops
1172dce093 Make max in flights parts fro upload configurable 2025-10-20 16:48:13 +02:00
Kerollmops
21140a33e6 Use a good mem advice for uploads 2025-10-20 16:48:13 +02:00
Kerollmops
9ed7a81495 Move the S3 snapshots to disk into a dedicated method 2025-10-20 16:48:13 +02:00
Clément Renault
c8c1d95efd Upload ten parts at a time 2025-10-20 16:48:13 +02:00
Clément Renault
10d1e26478 Use the Bytes crate to send the parts 2025-10-20 16:48:13 +02:00
Clément Renault
cd781d267b Upload indexes under their uuids 2025-10-20 16:48:13 +02:00
Clément Renault
b16af4a763 Initial working S3 uploads to RustFS 2025-10-20 16:48:13 +02:00
Louis Dureuil
1514d13ab3 Pass tokio handle to index-scheduler 2025-10-20 16:48:13 +02:00
Kerollmops
d51f13a59e Use the latest version of heed 2025-10-20 16:48:13 +02:00
199 changed files with 3128 additions and 10681 deletions

View File

@@ -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:

View File

@@ -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: |

View File

@@ -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 }}

View File

@@ -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:

View File

@@ -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

View File

@@ -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

View File

@@ -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

View File

@@ -14,105 +14,10 @@ on:
workflow_dispatch:
jobs:
build:
runs-on: ${{ matrix.runner }}
strategy:
matrix:
platform: [amd64, arm64]
edition: [community, enterprise]
include:
- platform: amd64
runner: ubuntu-24.04
- platform: arm64
runner: ubuntu-24.04-arm
- edition: community
registry: getmeili/meilisearch
feature-flag: ""
- edition: enterprise
registry: getmeili/meilisearch-enterprise
feature-flag: "--features enterprise"
permissions: {}
steps:
- uses: actions/checkout@v5
- name: Prepare
run: |
platform=linux/${{ matrix.platform }}
echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
with:
platforms: linux/${{ matrix.platform }}
install: true
- name: Login to Docker Hub
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Docker meta
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ matrix.registry }}
# Prevent `latest` to be updated for each new tag pushed.
# We need latest and `vX.Y` tags to only be pushed for the stable Meilisearch releases.
flavor: latest=false
tags: |
type=ref,event=tag
type=raw,value=nightly,enable=${{ github.event_name != 'push' }}
type=semver,pattern=v{{major}}.{{minor}},enable=${{ steps.check-tag-format.outputs.stable == 'true' }}
type=semver,pattern=v{{major}},enable=${{ steps.check-tag-format.outputs.stable == 'true' }}
type=raw,value=latest,enable=${{ steps.check-tag-format.outputs.stable == 'true' && steps.check-tag-format.outputs.latest == 'true' }}
- name: Build and push by digest
uses: docker/build-push-action@v6
id: build-and-push
with:
platforms: linux/${{ matrix.platform }}
labels: ${{ steps.meta.outputs.labels }}
tags: ${{ matrix.registry }}
outputs: type=image,push-by-digest=true,name-canonical=true,push=true
build-args: |
COMMIT_SHA=${{ github.sha }}
COMMIT_DATE=${{ steps.build-metadata.outputs.date }}
GIT_TAG=${{ github.ref_name }}
EXTRA_ARGS=${{ matrix.feature-flag }}
- name: Export digest
run: |
mkdir -p ${{ runner.temp }}/digests
digest="${{ steps.build-and-push.outputs.digest }}"
touch "${{ runner.temp }}/digests/${digest#sha256:}"
- name: Upload digest
uses: actions/upload-artifact@v4
with:
name: digests-${{ matrix.edition }}-${{ env.PLATFORM_PAIR }}
path: ${{ runner.temp }}/digests/*
if-no-files-found: error
retention-days: 1
merge:
runs-on: ubuntu-latest
strategy:
matrix:
edition: [community, enterprise]
include:
- edition: community
registry: getmeili/meilisearch
- edition: enterprise
registry: getmeili/meilisearch-enterprise
needs:
- build
docker:
runs-on: docker
permissions:
id-token: write # This is needed to use Cosign in keyless mode
steps:
- uses: actions/checkout@v5
@@ -153,30 +58,26 @@ jobs:
echo "date=$commit_date" >> $GITHUB_OUTPUT
- name: Set up QEMU
uses: docker/setup-qemu-action@v3
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Install cosign
uses: sigstore/cosign-installer@d7543c93d881b35a8faa02e8e3605f69b7a1ce62 # tag=v3.10.0
- name: Download digests
uses: actions/download-artifact@v4
with:
path: ${{ runner.temp }}/digests
pattern: digests-${{ matrix.edition }}-*
merge-multiple: true
- name: Login to Docker Hub
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Docker meta
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ matrix.registry }}
images: getmeili/meilisearch
# Prevent `latest` to be updated for each new tag pushed.
# We need latest and `vX.Y` tags to only be pushed for the stable Meilisearch releases.
flavor: latest=false
@@ -187,31 +88,33 @@ jobs:
type=semver,pattern=v{{major}},enable=${{ steps.check-tag-format.outputs.stable == 'true' }}
type=raw,value=latest,enable=${{ steps.check-tag-format.outputs.stable == 'true' && steps.check-tag-format.outputs.latest == 'true' }}
- name: Create manifest list and push
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 ' *)
- name: Inspect image to fetch digest to sign
run: |
digest=$(docker buildx imagetools inspect --format='{{ json .Manifest }}' ${{ matrix.registry }}:${{ steps.meta.outputs.version }} | jq -r '.digest')
echo "DIGEST=${digest}" >> $GITHUB_ENV
- name: Build and push
uses: docker/build-push-action@v6
id: build-and-push
with:
push: true
platforms: linux/amd64,linux/arm64
tags: ${{ steps.meta.outputs.tags }}
build-args: |
COMMIT_SHA=${{ github.sha }}
COMMIT_DATE=${{ steps.build-metadata.outputs.date }}
GIT_TAG=${{ github.ref_name }}
- name: Sign the images with GitHub OIDC Token
env:
DIGEST: ${{ steps.build-and-push.outputs.digest }}
TAGS: ${{ steps.meta.outputs.tags }}
run: |
images=""
for tag in ${TAGS}; do
images+="${tag}@${{ env.DIGEST }} "
images+="${tag}@${DIGEST} "
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: ${{ secrets.MEILI_BOT_GH_PAT }}
@@ -219,13 +122,21 @@ jobs:
event-type: cloud-docker-build
client-payload: '{ "meilisearch_version": "${{ 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

View File

@@ -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:
@@ -104,13 +200,13 @@ jobs:
- name: Generate OpenAPI file
run: |
cd crates/openapi-generator
cargo run --release -- --pretty --output ../../meilisearch-openapi.json
cargo run --release -- --pretty --output ../../meilisearch.json
- name: Upload OpenAPI to Release
# No need to upload 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: ./meilisearch-openapi.json
file: ./meilisearch.json
asset_name: meilisearch-openapi.json
tag: ${{ github.ref }}

View File

@@ -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 }}

View File

@@ -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

View File

@@ -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

3
.gitignore vendored
View File

@@ -29,6 +29,3 @@ crates/meilisearch/db.snapshot
# Fuzzcheck data for the facet indexing fuzz test
crates/milli/fuzz/update::facet::incremental::fuzz::fuzz/
# OpenAPI generator
**/meilisearch-openapi.json

View 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.

View File

@@ -117,7 +117,7 @@ With swagger:
With the internal crate:
```bash
cd crates/openapi-generator
cargo run --release -- --pretty
cargo run --release -- --pretty --output meilisearch.json
```
### Logging

2176
Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -23,7 +23,7 @@ members = [
]
[workspace.package]
version = "1.28.2"
version = "1.24.0"
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
View File

@@ -0,0 +1,7 @@
[build.env]
passthrough = [
"RUST_BACKTRACE",
"CARGO_TERM_COLOR",
"RUSTFLAGS",
"JEMALLOC_SYS_WITH_LG_PAGE"
]

View File

@@ -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

View File

@@ -39,7 +39,6 @@
## 🖥 Examples
- [**Movies**](https://where2watch.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=organization) — An application to help you find streaming platforms to watch movies using [hybrid search](https://www.meilisearch.com/solutions/hybrid-search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos).
- [**Flickr**](https://flickr.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=organization) — Search and explore one hundred million Flickr images with semantic search.
- [**Ecommerce**](https://ecommerce.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Ecommerce website using disjunctive [facets](https://www.meilisearch.com/docs/learn/fine_tuning_results/faceted_search?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos), range and rating filtering, and pagination.
- [**Songs**](https://music.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Search through 47 million of songs.
- [**SaaS**](https://saas.meilisearch.com/?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) — Search for contacts, deals, and companies in this [multi-tenant](https://www.meilisearch.com/docs/learn/security/multitenancy_tenant_tokens?utm_campaign=oss&utm_source=github&utm_medium=meilisearch&utm_content=demos) CRM application.

View File

@@ -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
}
```

View File

@@ -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"]

View File

@@ -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(),
)

View File

@@ -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"

View File

@@ -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()
}

View File

@@ -1,6 +0,0 @@
use build_info::BuildInfo;
fn main() {
let info = BuildInfo::from_build();
dbg!(info);
}

View File

@@ -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"]

View File

@@ -96,8 +96,6 @@ pub struct TaskDump {
pub finished_at: Option<OffsetDateTime>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub network: Option<TaskNetwork>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub custom_metadata: Option<String>,
}
// A `Kind` specific version made for the dump. If modified you may break the dump.
@@ -180,7 +178,6 @@ impl From<Task> for TaskDump {
started_at: task.started_at,
finished_at: task.finished_at,
network: task.network,
custom_metadata: task.custom_metadata,
}
}
}
@@ -262,13 +259,13 @@ 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};
@@ -399,7 +396,6 @@ pub(crate) mod test {
started_at: Some(datetime!(2022-11-20 0:00 UTC)),
finished_at: Some(datetime!(2022-11-21 0:00 UTC)),
network: None,
custom_metadata: None,
},
None,
),
@@ -425,7 +421,6 @@ pub(crate) mod test {
started_at: None,
finished_at: None,
network: None,
custom_metadata: None,
},
Some(vec![
json!({ "id": 4, "race": "leonberg" }).as_object().unwrap().clone(),
@@ -446,7 +441,6 @@ pub(crate) mod test {
started_at: None,
finished_at: None,
network: None,
custom_metadata: None,
},
None,
),

View File

@@ -164,7 +164,6 @@ impl CompatV5ToV6 {
started_at: task_view.started_at,
finished_at: task_view.finished_at,
network: None,
custom_metadata: None,
};
(task, content_file)

View File

@@ -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

View File

@@ -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};

View File

@@ -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"] }

View File

@@ -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"

View File

@@ -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"

View File

@@ -11,33 +11,34 @@ 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"
path-slash = "0.2.1"
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 +46,11 @@ 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"

View File

@@ -150,7 +150,6 @@ impl<'a> Dump<'a> {
details: task.details,
status: task.status,
network: task.network,
custom_metadata: task.custom_metadata,
kind: match task.kind {
KindDump::DocumentImport {
primary_key,

View File

@@ -5,7 +5,6 @@ use meilisearch_types::error::{Code, ErrorCode};
use meilisearch_types::milli::index::RollbackOutcome;
use meilisearch_types::tasks::{Kind, Status};
use meilisearch_types::{heed, milli};
use reqwest::StatusCode;
use thiserror::Error;
use crate::TaskId;
@@ -128,14 +127,6 @@ pub enum Error {
#[error("Aborted task")]
AbortedTask,
#[error("S3 error: status: {status}, body: {body}")]
S3Error { status: StatusCode, body: String },
#[error("S3 HTTP error: {0}")]
S3HttpError(reqwest::Error),
#[error("S3 XML error: {0}")]
S3XmlError(Box<dyn std::error::Error + Send + Sync>),
#[error("S3 bucket error: {0}")]
S3BucketError(rusty_s3::BucketError),
#[error(transparent)]
Dump(#[from] dump::Error),
#[error(transparent)]
@@ -235,10 +226,6 @@ impl Error {
| Error::TaskCancelationWithEmptyQuery
| Error::FromRemoteWhenExporting { .. }
| Error::AbortedTask
| Error::S3Error { .. }
| Error::S3HttpError(_)
| Error::S3XmlError(_)
| Error::S3BucketError(_)
| Error::Dump(_)
| Error::Heed(_)
| Error::Milli { .. }
@@ -306,14 +293,8 @@ impl ErrorCode for Error {
Error::BatchNotFound(_) => Code::BatchNotFound,
Error::TaskDeletionWithEmptyQuery => Code::MissingTaskFilters,
Error::TaskCancelationWithEmptyQuery => Code::MissingTaskFilters,
// TODO: not sure of the Code to use
Error::NoSpaceLeftInTaskQueue => Code::NoSpaceLeftOnDevice,
Error::S3Error { status, .. } if status.is_client_error() => {
Code::InvalidS3SnapshotRequest
}
Error::S3Error { .. } => Code::S3SnapshotServerError,
Error::S3HttpError(_) => Code::S3SnapshotServerError,
Error::S3XmlError(_) => Code::S3SnapshotServerError,
Error::S3BucketError(_) => Code::InvalidS3SnapshotParameters,
Error::Dump(e) => e.error_code(),
Error::Milli { error, .. } => error.error_code(),
Error::ProcessBatchPanicked(_) => Code::Internal,

View File

@@ -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;

View File

@@ -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;
@@ -232,7 +232,6 @@ pub fn snapshot_task(task: &Task) -> String {
status,
kind,
network,
custom_metadata,
} = task;
snap.push('{');
snap.push_str(&format!("uid: {uid}, "));
@@ -253,9 +252,6 @@ pub fn snapshot_task(task: &Task) -> String {
if let Some(network) = network {
snap.push_str(&format!("network: {network:?}, "))
}
if let Some(custom_metadata) = custom_metadata {
snap.push_str(&format!("custom_metadata: {custom_metadata:?}"))
}
snap.push('}');
snap
@@ -320,11 +316,7 @@ 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 +396,7 @@ 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!(

View File

@@ -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};
@@ -217,7 +217,6 @@ pub struct IndexScheduler {
#[cfg(test)]
run_loop_iteration: Arc<RwLock<usize>>,
/// The tokio runtime used for asynchronous tasks.
runtime: Option<tokio::runtime::Handle>,
}
@@ -259,23 +258,14 @@ impl IndexScheduler {
}
/// Create an index scheduler and start its run loop.
#[allow(private_interfaces)] // because test_utils is private
pub fn new(
options: IndexSchedulerOptions,
auth_env: Env<WithoutTls>,
from_db_version: (u32, u32, u32),
runtime: Option<tokio::runtime::Handle>,
) -> Result<Self> {
let this = Self::new_without_run(options, auth_env, from_db_version, runtime)?;
this.run();
Ok(this)
}
fn new_without_run(
options: IndexSchedulerOptions,
auth_env: Env<WithoutTls>,
from_db_version: (u32, u32, u32),
runtime: Option<tokio::runtime::Handle>,
#[cfg(test)] test_breakpoint_sdr: crossbeam_channel::Sender<(test_utils::Breakpoint, bool)>,
#[cfg(test)] planned_failures: Vec<(usize, test_utils::FailureLocation)>,
) -> Result<Self> {
std::fs::create_dir_all(&options.tasks_path)?;
std::fs::create_dir_all(&options.update_file_path)?;
@@ -330,7 +320,8 @@ impl IndexScheduler {
wtxn.commit()?;
Ok(Self {
// allow unreachable_code to get rids of the warning in the case of a test build.
let this = Self {
processing_tasks: Arc::new(RwLock::new(ProcessingTasks::new())),
version,
queue,
@@ -346,32 +337,16 @@ impl IndexScheduler {
webhooks: Arc::new(webhooks),
embedders: Default::default(),
#[cfg(test)] // Will be replaced in `new_tests` in test environments
test_breakpoint_sdr: crossbeam_channel::bounded(0).0,
#[cfg(test)] // Will be replaced in `new_tests` in test environments
planned_failures: Default::default(),
#[cfg(test)]
test_breakpoint_sdr,
#[cfg(test)]
planned_failures,
#[cfg(test)]
run_loop_iteration: Arc::new(RwLock::new(0)),
features,
chat_settings,
runtime,
})
}
/// Create an index scheduler and start its run loop.
#[cfg(test)]
fn new_test(
options: IndexSchedulerOptions,
auth_env: Env<WithoutTls>,
from_db_version: (u32, u32, u32),
runtime: Option<tokio::runtime::Handle>,
test_breakpoint_sdr: crossbeam_channel::Sender<(test_utils::Breakpoint, bool)>,
planned_failures: Vec<(usize, test_utils::FailureLocation)>,
) -> Result<Self> {
let mut this = Self::new_without_run(options, auth_env, from_db_version, runtime)?;
this.test_breakpoint_sdr = test_breakpoint_sdr;
this.planned_failures = planned_failures;
};
this.run();
Ok(this)
@@ -756,19 +731,6 @@ impl IndexScheduler {
kind: KindWithContent,
task_id: Option<TaskId>,
dry_run: bool,
) -> Result<Task> {
self.register_with_custom_metadata(kind, task_id, None, dry_run)
}
/// Register a new task in the scheduler, with metadata.
///
/// If it fails and data was associated with the task, it tries to delete the associated data.
pub fn register_with_custom_metadata(
&self,
kind: KindWithContent,
task_id: Option<TaskId>,
custom_metadata: Option<String>,
dry_run: bool,
) -> Result<Task> {
// if the task doesn't delete or cancel anything and 40% of the task queue is full, we must refuse to enqueue the incoming task
if !matches!(&kind, KindWithContent::TaskDeletion { tasks, .. } | KindWithContent::TaskCancelation { tasks, .. } if !tasks.is_empty())
@@ -779,7 +741,7 @@ impl IndexScheduler {
}
let mut wtxn = self.env.write_txn()?;
let task = self.queue.register(&mut wtxn, &kind, task_id, custom_metadata, dry_run)?;
let task = self.queue.register(&mut wtxn, &kind, task_id, dry_run)?;
// If the registered task is a task cancelation
// we inform the processing tasks to stop (if necessary).

View File

@@ -257,7 +257,6 @@ impl Queue {
wtxn: &mut RwTxn,
kind: &KindWithContent,
task_id: Option<TaskId>,
custom_metadata: Option<String>,
dry_run: bool,
) -> Result<Task> {
let next_task_id = self.tasks.next_task_id(wtxn)?;
@@ -281,7 +280,6 @@ impl Queue {
status: Status::Enqueued,
kind: kind.clone(),
network: None,
custom_metadata,
};
// For deletion and cancelation tasks, we want to make extra sure that they
// don't attempt to delete/cancel tasks that are newer than themselves.
@@ -346,7 +344,6 @@ impl Queue {
tasks: to_delete,
},
None,
None,
false,
)?;

View File

@@ -25,7 +25,6 @@ use convert_case::{Case, Casing as _};
use meilisearch_types::error::ResponseError;
use meilisearch_types::heed::{Env, WithoutTls};
use meilisearch_types::milli;
use meilisearch_types::milli::update::S3SnapshotOptions;
use meilisearch_types::tasks::Status;
use process_batch::ProcessBatchInfo;
use rayon::current_num_threads;
@@ -88,14 +87,11 @@ pub struct Scheduler {
/// Snapshot compaction status.
pub(crate) experimental_no_snapshot_compaction: bool,
/// S3 Snapshot options.
pub(crate) s3_snapshot_options: Option<S3SnapshotOptions>,
}
impl Scheduler {
pub(crate) fn private_clone(&self) -> Self {
Self {
pub(crate) fn private_clone(&self) -> Scheduler {
Scheduler {
must_stop_processing: self.must_stop_processing.clone(),
wake_up: self.wake_up.clone(),
autobatching_enabled: self.autobatching_enabled,
@@ -107,52 +103,23 @@ impl Scheduler {
version_file_path: self.version_file_path.clone(),
embedding_cache_cap: self.embedding_cache_cap,
experimental_no_snapshot_compaction: self.experimental_no_snapshot_compaction,
s3_snapshot_options: self.s3_snapshot_options.clone(),
}
}
pub fn new(options: &IndexSchedulerOptions, auth_env: Env<WithoutTls>) -> Scheduler {
let IndexSchedulerOptions {
version_file_path,
auth_path: _,
tasks_path: _,
update_file_path: _,
indexes_path: _,
snapshots_path,
dumps_path,
cli_webhook_url: _,
cli_webhook_authorization: _,
task_db_size: _,
index_base_map_size: _,
enable_mdb_writemap: _,
index_growth_amount: _,
index_count: _,
indexer_config,
autobatching_enabled,
cleanup_enabled: _,
max_number_of_tasks: _,
max_number_of_batched_tasks,
batched_tasks_size_limit,
instance_features: _,
auto_upgrade: _,
embedding_cache_cap,
experimental_no_snapshot_compaction,
} = options;
Scheduler {
must_stop_processing: MustStopProcessing::default(),
// we want to start the loop right away in case meilisearch was ctrl+Ced while processing things
wake_up: Arc::new(SignalEvent::auto(true)),
autobatching_enabled: *autobatching_enabled,
max_number_of_batched_tasks: *max_number_of_batched_tasks,
batched_tasks_size_limit: *batched_tasks_size_limit,
dumps_path: dumps_path.clone(),
snapshots_path: snapshots_path.clone(),
autobatching_enabled: options.autobatching_enabled,
max_number_of_batched_tasks: options.max_number_of_batched_tasks,
batched_tasks_size_limit: options.batched_tasks_size_limit,
dumps_path: options.dumps_path.clone(),
snapshots_path: options.snapshots_path.clone(),
auth_env,
version_file_path: version_file_path.clone(),
embedding_cache_cap: *embedding_cache_cap,
experimental_no_snapshot_compaction: *experimental_no_snapshot_compaction,
s3_snapshot_options: indexer_config.s3_snapshot_options.clone(),
version_file_path: options.version_file_path.clone(),
embedding_cache_cap: options.embedding_cache_cap,
experimental_no_snapshot_compaction: options.experimental_no_snapshot_compaction,
}
}
}

View File

@@ -1,19 +1,26 @@
use std::collections::VecDeque;
use std::env::VarError;
use std::ffi::OsStr;
use std::fs;
use std::path::PathBuf;
use std::sync::atomic::Ordering;
use std::time::Duration;
use meilisearch_types::heed::CompactionOption;
use meilisearch_types::milli::progress::{Progress, VariableNameStep};
use meilisearch_types::tasks::{Status, Task};
use meilisearch_types::{compression, VERSION_FILE_NAME};
use path_slash::PathBufExt;
use reqwest::header::ETAG;
use reqwest::Client;
use rusty_s3::actions::{CreateMultipartUpload, S3Action as _};
use rusty_s3::{Bucket, Credentials, UrlStyle};
use crate::heed::EnvOpenOptions;
use crate::processing::{AtomicUpdateFileStep, SnapshotCreationProgress};
use crate::queue::TaskQueue;
use crate::{Error, IndexScheduler, Result};
const UPDATE_FILES_DIR_NAME: &str = "update_files";
/// # Safety
///
/// See [`EnvOpenOptions::open`].
@@ -84,20 +91,61 @@ impl IndexScheduler {
) -> Result<Vec<Task>> {
progress.update_progress(SnapshotCreationProgress::StartTheSnapshotCreation);
match self.scheduler.s3_snapshot_options.clone() {
Some(options) => {
const S3_BUCKET_URL: &str = "MEILI_S3_BUCKET_URL";
const S3_BUCKET_REGION: &str = "MEILI_S3_BUCKET_REGION";
const S3_BUCKET_NAME: &str = "MEILI_S3_BUCKET_NAME";
const S3_SNAPSHOT_PREFIX: &str = "MEILI_S3_SNAPSHOT_PREFIX";
const S3_ACCESS_KEY: &str = "MEILI_S3_ACCESS_KEY";
const S3_SECRET_KEY: &str = "MEILI_S3_SECRET_KEY";
let bucket_url = std::env::var(S3_BUCKET_URL).map_err(|e| (S3_BUCKET_URL, e));
let bucket_region = std::env::var(S3_BUCKET_REGION).map_err(|e| (S3_BUCKET_REGION, e));
let bucket_name = std::env::var(S3_BUCKET_NAME).map_err(|e| (S3_BUCKET_NAME, e));
let snapshot_prefix =
std::env::var(S3_SNAPSHOT_PREFIX).map_err(|e| (S3_SNAPSHOT_PREFIX, e));
let access_key = std::env::var(S3_ACCESS_KEY).map_err(|e| (S3_ACCESS_KEY, e));
let secret_key = std::env::var(S3_SECRET_KEY).map_err(|e| (S3_SECRET_KEY, e));
match (bucket_url, bucket_region, bucket_name, snapshot_prefix, access_key, secret_key) {
(
Ok(bucket_url),
Ok(bucket_region),
Ok(bucket_name),
Ok(snapshot_prefix),
Ok(access_key),
Ok(secret_key),
) => {
let runtime = self.runtime.as_ref().expect("Runtime not initialized");
#[cfg(not(unix))]
{
let _ = options;
panic!("Non-unix platform does not support S3 snapshotting");
}
panic!("Non-unix platform does not support S3 snapshotting");
#[cfg(unix)]
self.runtime
.as_ref()
.expect("Runtime not initialized")
.block_on(self.process_snapshot_to_s3(progress, options, tasks))
runtime.block_on(self.process_snapshot_to_s3(
progress,
bucket_url,
bucket_region,
bucket_name,
PathBuf::from_slash(snapshot_prefix),
access_key,
secret_key,
tasks,
))
}
(
Err((_, VarError::NotPresent)),
Err((_, VarError::NotPresent)),
Err((_, VarError::NotPresent)),
Err((_, VarError::NotPresent)),
Err((_, VarError::NotPresent)),
Err((_, VarError::NotPresent)),
) => self.process_snapshots_to_disk(progress, tasks),
(Err((var, e)), _, _, _, _, _)
| (_, Err((var, e)), _, _, _, _)
| (_, _, Err((var, e)), _, _, _)
| (_, _, _, Err((var, e)), _, _)
| (_, _, _, _, Err((var, e)), _)
| (_, _, _, _, _, Err((var, e))) => {
// TODO: Handle error gracefully
panic!("Error while reading environment variables: {}: {}", var, e);
}
None => self.process_snapshots_to_disk(progress, tasks),
}
}
@@ -152,7 +200,7 @@ impl IndexScheduler {
let rtxn = self.env.read_txn()?;
// 2.4 Create the update files directory
let update_files_dir = temp_snapshot_dir.path().join(UPDATE_FILES_DIR_NAME);
let update_files_dir = temp_snapshot_dir.path().join("update_files");
fs::create_dir_all(&update_files_dir)?;
// 2.5 Only copy the update files of the enqueued tasks
@@ -235,60 +283,273 @@ impl IndexScheduler {
pub(super) async fn process_snapshot_to_s3(
&self,
progress: Progress,
opts: meilisearch_types::milli::update::S3SnapshotOptions,
bucket_url: String,
bucket_region: String,
bucket_name: String,
snapshot_prefix: PathBuf,
access_key: String,
secret_key: String,
mut tasks: Vec<Task>,
) -> Result<Vec<Task>> {
use meilisearch_types::milli::update::S3SnapshotOptions;
use std::fs::File;
use std::io::{self, Seek as _, SeekFrom, Write as _};
use std::os::fd::OwnedFd;
use std::path::Path;
let S3SnapshotOptions {
s3_bucket_url,
s3_bucket_region,
s3_bucket_name,
s3_snapshot_prefix,
s3_access_key,
s3_secret_key,
s3_max_in_flight_parts,
s3_compression_level: level,
s3_signature_duration,
s3_multipart_part_size,
} = opts;
use bytes::{Bytes, BytesMut};
use reqwest::Response;
use tokio::task::JoinHandle;
let must_stop_processing = self.scheduler.must_stop_processing.clone();
let retry_backoff = backoff::ExponentialBackoff::default();
let db_name = {
let mut base_path = self.env.path().to_owned();
base_path.pop();
base_path.file_name().and_then(OsStr::to_str).unwrap_or("data.ms").to_string()
const ONE_HOUR: Duration = Duration::from_secs(3600);
// default part size is 250MiB
// TODO use 375MiB
// It must be at least 2x5MiB
const PART_SIZE: usize = 10 * 1024 * 1024;
// The maximum number of parts that can be uploaded in parallel.
const S3_MAX_IN_FLIGHT_PARTS: &str = "MEILI_S3_MAX_IN_FLIGHT_PARTS";
let max_in_flight_parts: usize = match std::env::var(S3_MAX_IN_FLIGHT_PARTS) {
Ok(val) => val.parse().expect("Failed to parse MEILI_S3_MAX_IN_FLIGHT_PARTS"),
Err(_) => 10,
};
let (reader, writer) = std::io::pipe()?;
let uploader_task = tokio::spawn(multipart_stream_to_s3(
s3_bucket_url,
s3_bucket_region,
s3_bucket_name,
s3_snapshot_prefix,
s3_access_key,
s3_secret_key,
s3_max_in_flight_parts,
s3_signature_duration,
s3_multipart_part_size,
must_stop_processing,
retry_backoff,
db_name,
reader,
));
let client = Client::new();
// TODO Remove this unwrap
let url = bucket_url.parse().unwrap();
let bucket = Bucket::new(url, UrlStyle::Path, bucket_name, bucket_region).unwrap();
let credential = Credentials::new(access_key, secret_key);
// TODO change this and use the database name like in the original version
let object_path = snapshot_prefix.join("data.ms.snapshot");
let object = object_path.to_slash().expect("Invalid UTF-8 path").into_owned();
eprintln!("Starting the upload of the snapshot to {object}");
// TODO implement exponential backoff on upload requests: https://docs.rs/backoff
// TODO return a result with actual errors
// TODO sign for longer than an hour?
// NOTE to make it work on Windows we could try using std::io::pipe instead.
// However, we are still using the tokio unix pipe in the async upload loop.
let (reader, writer) = std::io::pipe()?;
let uploader_task = tokio::spawn(async move {
let reader = OwnedFd::from(reader);
let reader = tokio::net::unix::pipe::Receiver::from_owned_fd(reader)?;
let action = bucket.create_multipart_upload(Some(&credential), &object);
// TODO Question: If it is only signed for an hour and a snapshot takes longer than an hour, what happens?
// If the part is deleted (like a TTL) we should sign it for at least 24 hours.
let url = action.sign(ONE_HOUR);
let resp = client.post(url).send().await.unwrap().error_for_status().unwrap();
let body = resp.text().await.unwrap();
let multipart = CreateMultipartUpload::parse_response(&body).unwrap();
let mut etags = Vec::<String>::new();
let mut in_flight =
VecDeque::<(JoinHandle<reqwest::Result<Response>>, Bytes)>::with_capacity(
max_in_flight_parts,
);
for part_number in 1u16.. {
let part_upload = bucket.upload_part(
Some(&credential),
&object,
part_number,
multipart.upload_id(),
);
let url = part_upload.sign(ONE_HOUR);
// Wait for a buffer to be ready if there are in-flight parts that landed
let mut buffer = if in_flight.len() >= max_in_flight_parts {
let (request, buffer) = in_flight.pop_front().unwrap();
let resp = request.await.unwrap().unwrap().error_for_status().unwrap();
let etag =
resp.headers().get(ETAG).expect("every UploadPart request returns an Etag");
let mut buffer = match buffer.try_into_mut() {
Ok(buffer) => buffer,
Err(_) => panic!("Valid to convert into BytesMut"),
};
// TODO use bumpalo to reduce the number of allocations
etags.push(etag.to_str().unwrap().to_owned());
buffer.clear();
buffer
} else {
// TODO Base this on the available memory
BytesMut::with_capacity(PART_SIZE)
};
while buffer.len() < (PART_SIZE / 2) {
eprintln!(
"buffer is {:.2}% full, trying to read more",
buffer.len() as f32 / buffer.capacity() as f32 * 100.0
);
// Wait for the pipe to be readable
reader.readable().await?;
match reader.try_read_buf(&mut buffer) {
Ok(0) => break,
// We read some bytes but maybe not enough
Ok(n) => {
eprintln!("Read {} bytes from pipe, continuing", n);
continue;
}
// The readiness event is a false positive.
Err(ref e) if e.kind() == io::ErrorKind::WouldBlock => {
eprintln!("received a WouldBlock");
continue;
}
Err(e) => return Err(e.into()),
}
}
eprintln!(
"buffer is {:.2}% full",
buffer.len() as f32 / buffer.capacity() as f32 * 100.0
);
if buffer.is_empty() {
eprintln!("buffer is empty, breaking part number loop");
// Break the loop if the buffer is empty
// after we tried to read bytes
break;
}
let body = buffer.freeze();
eprintln!("Sending part {}", part_number);
let task = tokio::spawn(client.put(url).body(body.clone()).send());
in_flight.push_back((task, body));
}
for (join_handle, _buffer) in in_flight {
let resp = join_handle.await.unwrap().unwrap().error_for_status().unwrap();
let etag =
resp.headers().get(ETAG).expect("every UploadPart request returns an Etag");
// TODO use bumpalo to reduce the number of allocations
etags.push(etag.to_str().unwrap().to_owned());
}
eprintln!("Finalizing the multipart upload");
let action = bucket.complete_multipart_upload(
Some(&credential),
&object,
multipart.upload_id(),
etags.iter().map(AsRef::as_ref),
);
let url = action.sign(ONE_HOUR);
let resp = client.post(url).body(action.body()).send().await.unwrap();
let status = resp.status();
let text = resp.text().await.unwrap();
eprintln!("Status: {status}, Text: {text}");
// TODO do a better check and do not assert
// assert!(resp.status().is_success());
Result::<_, Error>::Ok(())
});
// TODO not a big fan of this clone
// remove it and get all the necessary data from the scheduler
let index_scheduler = IndexScheduler::private_clone(self);
let builder_task = tokio::task::spawn_blocking(move || {
stream_tarball_into_pipe(progress, level, writer, index_scheduler)
// NOTE enabling compression still generates a corrupted tarball
let writer = flate2::write::GzEncoder::new(writer, flate2::Compression::fast());
let mut tarball = tar::Builder::new(writer);
// 1. Snapshot the version file
tarball.append_path_with_name(
&index_scheduler.scheduler.version_file_path,
VERSION_FILE_NAME,
)?;
// 2. Snapshot the index scheduler LMDB env
progress.update_progress(SnapshotCreationProgress::SnapshotTheIndexScheduler);
let mut tasks_env_file = index_scheduler.env.try_clone_inner_file()?;
// NOTE That made the trick !!! Should I memory map instead?
tasks_env_file.seek(SeekFrom::Start(0))?;
let path = Path::new("tasks").join("data.mdb");
// NOTE when commenting this line, the tarball works better
tarball.append_file(path, &mut tasks_env_file)?;
drop(tasks_env_file);
// 2.3 Create a read transaction on the index-scheduler
let rtxn = index_scheduler.env.read_txn()?;
// 2.4 Create the update files directory
// And only copy the update files of the enqueued tasks
progress.update_progress(SnapshotCreationProgress::SnapshotTheUpdateFiles);
let enqueued = index_scheduler.queue.tasks.get_status(&rtxn, Status::Enqueued)?;
let (atomic, update_file_progress) = AtomicUpdateFileStep::new(enqueued.len() as u32);
progress.update_progress(update_file_progress);
// TODO I need to create the update files directory (even if empty)
// I should probably simply use the append_dir_all method
// but I'll loose the progression.
let update_files_dir = Path::new("update_files");
for task_id in enqueued {
let task = index_scheduler
.queue
.tasks
.get_task(&rtxn, task_id)?
.ok_or(Error::CorruptedTaskQueue)?;
if let Some(content_uuid) = task.content_uuid() {
let src = index_scheduler.queue.file_store.update_path(content_uuid);
let mut update_file = File::open(src)?;
let path = update_files_dir.join(content_uuid.to_string());
tarball.append_file(path, &mut update_file)?;
}
atomic.fetch_add(1, Ordering::Relaxed);
}
// 3. Snapshot every indexes
progress.update_progress(SnapshotCreationProgress::SnapshotTheIndexes);
let index_mapping = index_scheduler.index_mapper.index_mapping;
let nb_indexes = index_mapping.len(&rtxn)? as u32;
let indexes_dir = Path::new("indexes");
let indexes_references: Vec<_> = index_scheduler
.index_mapper
.index_mapping
.iter(&rtxn)?
.map(|res| res.map_err(Error::from).map(|(name, uuid)| (name.to_string(), uuid)))
.collect::<Result<_, Error>>()?;
dbg!(&indexes_references);
// Note that we need to collect and open all of the indexes files because
// otherwise, using a for loop, we would have to have a Send rtxn.
// TODO I don't need to do this trick if my writer is NOT async
for (i, (name, uuid)) in indexes_references.into_iter().enumerate() {
progress.update_progress(VariableNameStep::<SnapshotCreationProgress>::new(
&name, i as u32, nb_indexes,
));
let path = indexes_dir.join(uuid.to_string()).join("data.mdb");
let index = index_scheduler.index_mapper.index(&rtxn, &name)?;
let mut index_file = index.try_clone_inner_file().unwrap();
index_file.seek(SeekFrom::Start(0))?;
eprintln!("Appending index file for {} in {}", name, path.display());
tarball.append_file(path, &mut index_file)?;
}
drop(rtxn);
// 4. Snapshot the auth LMDB env
progress.update_progress(SnapshotCreationProgress::SnapshotTheApiKeys);
let mut auth_env_file =
index_scheduler.scheduler.auth_env.try_clone_inner_file().unwrap();
auth_env_file.seek(SeekFrom::Start(0))?;
let path = Path::new("auth").join("data.mdb");
tarball.append_file(path, &mut auth_env_file)?;
let mut gzencoder = tarball.into_inner()?;
gzencoder.flush()?;
gzencoder.try_finish()?;
let mut writer = gzencoder.finish()?;
writer.flush()?;
Result::<_, Error>::Ok(())
});
let (uploader_result, builder_result) = tokio::join!(uploader_task, builder_task);
// Check uploader result first to early return on task abortion.
// safety: JoinHandle can return an error if the task was aborted, cancelled, or panicked.
uploader_result.unwrap()?;
builder_result.unwrap()?;
uploader_result.unwrap()?;
for task in &mut tasks {
task.status = Status::Succeeded;
@@ -297,340 +558,3 @@ impl IndexScheduler {
Ok(tasks)
}
}
/// Streams a tarball of the database content into a pipe.
#[cfg(unix)]
fn stream_tarball_into_pipe(
progress: Progress,
level: u32,
writer: std::io::PipeWriter,
index_scheduler: IndexScheduler,
) -> std::result::Result<(), Error> {
use std::io::Write as _;
use std::path::Path;
let writer = flate2::write::GzEncoder::new(writer, flate2::Compression::new(level));
let mut tarball = tar::Builder::new(writer);
// 1. Snapshot the version file
tarball
.append_path_with_name(&index_scheduler.scheduler.version_file_path, VERSION_FILE_NAME)?;
// 2. Snapshot the index scheduler LMDB env
progress.update_progress(SnapshotCreationProgress::SnapshotTheIndexScheduler);
let tasks_env_file = index_scheduler.env.try_clone_inner_file()?;
let path = Path::new("tasks").join("data.mdb");
append_file_to_tarball(&mut tarball, path, tasks_env_file)?;
// 2.3 Create a read transaction on the index-scheduler
let rtxn = index_scheduler.env.read_txn()?;
// 2.4 Create the update files directory
// And only copy the update files of the enqueued tasks
progress.update_progress(SnapshotCreationProgress::SnapshotTheUpdateFiles);
let enqueued = index_scheduler.queue.tasks.get_status(&rtxn, Status::Enqueued)?;
let (atomic, update_file_progress) = AtomicUpdateFileStep::new(enqueued.len() as u32);
progress.update_progress(update_file_progress);
// We create the update_files directory so that it
// always exists even if there are no update files
let update_files_dir = Path::new(UPDATE_FILES_DIR_NAME);
let src_update_files_dir = {
let mut path = index_scheduler.env.path().to_path_buf();
path.pop();
path.join(UPDATE_FILES_DIR_NAME)
};
tarball.append_dir(update_files_dir, src_update_files_dir)?;
for task_id in enqueued {
let task = index_scheduler
.queue
.tasks
.get_task(&rtxn, task_id)?
.ok_or(Error::CorruptedTaskQueue)?;
if let Some(content_uuid) = task.content_uuid() {
use std::fs::File;
let src = index_scheduler.queue.file_store.update_path(content_uuid);
let mut update_file = File::open(src)?;
let path = update_files_dir.join(content_uuid.to_string());
tarball.append_file(path, &mut update_file)?;
}
atomic.fetch_add(1, Ordering::Relaxed);
}
// 3. Snapshot every indexes
progress.update_progress(SnapshotCreationProgress::SnapshotTheIndexes);
let index_mapping = index_scheduler.index_mapper.index_mapping;
let nb_indexes = index_mapping.len(&rtxn)? as u32;
let indexes_dir = Path::new("indexes");
let indexes_references: Vec<_> = index_scheduler
.index_mapper
.index_mapping
.iter(&rtxn)?
.map(|res| res.map_err(Error::from).map(|(name, uuid)| (name.to_string(), uuid)))
.collect::<Result<_, Error>>()?;
// It's prettier to use a for loop instead of the IndexMapper::try_for_each_index
// method, especially when we need to access the UUID, local path and index number.
for (i, (name, uuid)) in indexes_references.into_iter().enumerate() {
progress.update_progress(VariableNameStep::<SnapshotCreationProgress>::new(
&name, i as u32, nb_indexes,
));
let path = indexes_dir.join(uuid.to_string()).join("data.mdb");
let index = index_scheduler.index_mapper.index(&rtxn, &name)?;
let index_file = index.try_clone_inner_file()?;
tracing::trace!("Appending index file for {name} in {}", path.display());
append_file_to_tarball(&mut tarball, path, index_file)?;
}
drop(rtxn);
// 4. Snapshot the auth LMDB env
progress.update_progress(SnapshotCreationProgress::SnapshotTheApiKeys);
let auth_env_file = index_scheduler.scheduler.auth_env.try_clone_inner_file()?;
let path = Path::new("auth").join("data.mdb");
append_file_to_tarball(&mut tarball, path, auth_env_file)?;
let mut gzencoder = tarball.into_inner()?;
gzencoder.flush()?;
gzencoder.try_finish()?;
let mut writer = gzencoder.finish()?;
writer.flush()?;
Result::<_, Error>::Ok(())
}
#[cfg(unix)]
fn append_file_to_tarball<W, P>(
tarball: &mut tar::Builder<W>,
path: P,
mut auth_env_file: fs::File,
) -> Result<(), Error>
where
W: std::io::Write,
P: AsRef<std::path::Path>,
{
use std::io::{Seek as _, SeekFrom};
// Note: A previous snapshot operation may have left the cursor
// at the end of the file so we need to seek to the start.
auth_env_file.seek(SeekFrom::Start(0))?;
tarball.append_file(path, &mut auth_env_file)?;
Ok(())
}
/// Streams the content read from the given reader to S3.
#[cfg(unix)]
#[allow(clippy::too_many_arguments)]
async fn multipart_stream_to_s3(
s3_bucket_url: String,
s3_bucket_region: String,
s3_bucket_name: String,
s3_snapshot_prefix: String,
s3_access_key: String,
s3_secret_key: String,
s3_max_in_flight_parts: std::num::NonZero<usize>,
s3_signature_duration: std::time::Duration,
s3_multipart_part_size: u64,
must_stop_processing: super::MustStopProcessing,
retry_backoff: backoff::exponential::ExponentialBackoff<backoff::SystemClock>,
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 bytes::{Bytes, BytesMut};
use reqwest::{Client, Response};
use rusty_s3::actions::CreateMultipartUpload;
use rusty_s3::{Bucket, BucketError, Credentials, S3Action as _, UrlStyle};
use tokio::task::JoinHandle;
let reader = OwnedFd::from(reader);
let reader = tokio::net::unix::pipe::Receiver::from_owned_fd(reader)?;
let s3_snapshot_prefix = PathBuf::from(s3_snapshot_prefix);
let url =
s3_bucket_url.parse().map_err(BucketError::ParseError).map_err(Error::S3BucketError)?;
let bucket = Bucket::new(url, UrlStyle::Path, s3_bucket_name, s3_bucket_region)
.map_err(Error::S3BucketError)?;
let credential = Credentials::new(s3_access_key, s3_secret_key);
// Note for the future (rust 1.91+): use with_added_extension, it's prettier
let object_path = s3_snapshot_prefix.join(format!("{db_name}.snapshot"));
// Note: It doesn't work on Windows and if a port to this platform is needed,
// use the slash-path crate or similar to get the correct path separator.
let object = object_path.display().to_string();
let action = bucket.create_multipart_upload(Some(&credential), &object);
let url = action.sign(s3_signature_duration);
let client = Client::new();
let resp = client.post(url).send().await.map_err(Error::S3HttpError)?;
let status = resp.status();
let body = match resp.error_for_status_ref() {
Ok(_) => resp.text().await.map_err(Error::S3HttpError)?,
Err(_) => {
return Err(Error::S3Error { status, body: resp.text().await.unwrap_or_default() })
}
};
let multipart =
CreateMultipartUpload::parse_response(&body).map_err(|e| Error::S3XmlError(Box::new(e)))?;
tracing::debug!("Starting the upload of the snapshot to {object}");
// We use this bumpalo for etags strings.
let bump = bumpalo::Bump::new();
let mut etags = Vec::<&str>::new();
let mut in_flight = VecDeque::<(JoinHandle<reqwest::Result<Response>>, Bytes)>::with_capacity(
s3_max_in_flight_parts.get(),
);
// Part numbers start at 1 and cannot be larger than 10k
for part_number in 1u16.. {
if must_stop_processing.get() {
return Err(Error::AbortedTask);
}
let part_upload =
bucket.upload_part(Some(&credential), &object, part_number, multipart.upload_id());
let url = part_upload.sign(s3_signature_duration);
// Wait for a buffer to be ready if there are in-flight parts that landed
let mut buffer = if in_flight.len() >= s3_max_in_flight_parts.get() {
let (handle, buffer) = in_flight.pop_front().expect("At least one in flight request");
let resp = join_and_map_error(handle).await?;
extract_and_append_etag(&bump, &mut etags, resp.headers())?;
let mut buffer = match buffer.try_into_mut() {
Ok(buffer) => buffer,
Err(_) => unreachable!("All bytes references were consumed in the task"),
};
buffer.clear();
buffer
} else {
BytesMut::with_capacity(s3_multipart_part_size as usize)
};
// If we successfully read enough bytes,
// we can continue and send the buffer/part
while buffer.len() < (s3_multipart_part_size as usize / 2) {
// Wait for the pipe to be readable
reader.readable().await?;
match reader.try_read_buf(&mut buffer) {
Ok(0) => break,
// We read some bytes but maybe not enough
Ok(_) => continue,
// The readiness event is a false positive.
Err(ref e) if e.kind() == io::ErrorKind::WouldBlock => continue,
Err(e) => return Err(e.into()),
}
}
if buffer.is_empty() {
// Break the loop if the buffer is
// empty after we tried to read bytes
break;
}
let body = buffer.freeze();
tracing::trace!("Sending part {part_number}");
let task = tokio::spawn({
let client = client.clone();
let body = body.clone();
backoff::future::retry(retry_backoff.clone(), move || {
let client = client.clone();
let url = url.clone();
let body = body.clone();
async move {
match client.put(url).body(body).send().await {
Ok(resp) if resp.status().is_client_error() => {
resp.error_for_status().map_err(backoff::Error::Permanent)
}
Ok(resp) => Ok(resp),
Err(e) => Err(backoff::Error::transient(e)),
}
}
})
});
in_flight.push_back((task, body));
}
for (handle, _buffer) in in_flight {
let resp = join_and_map_error(handle).await?;
extract_and_append_etag(&bump, &mut etags, resp.headers())?;
}
tracing::debug!("Finalizing the multipart upload");
let action = bucket.complete_multipart_upload(
Some(&credential),
&object,
multipart.upload_id(),
etags.iter().map(AsRef::as_ref),
);
let url = action.sign(s3_signature_duration);
let body = action.body();
let resp = backoff::future::retry(retry_backoff, move || {
let client = client.clone();
let url = url.clone();
let body = body.clone();
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(),
}))
}
Ok(resp) => Ok(resp),
Err(e) => Err(backoff::Error::transient(Error::S3HttpError(e))),
}
}
})
.await?;
let status = resp.status();
let body = resp.text().await.map_err(|e| Error::S3Error { status, body: e.to_string() })?;
if status.is_success() {
Ok(())
} else {
Err(Error::S3Error { status, body })
}
}
#[cfg(unix)]
async fn join_and_map_error(
join_handle: tokio::task::JoinHandle<Result<reqwest::Response, reqwest::Error>>,
) -> Result<reqwest::Response> {
// safety: Panic happens if the task (JoinHandle) was aborted, cancelled, or panicked
let request = join_handle.await.unwrap();
let resp = request.map_err(Error::S3HttpError)?;
match resp.error_for_status_ref() {
Ok(_) => Ok(resp),
Err(_) => Err(Error::S3Error {
status: resp.status(),
body: resp.text().await.unwrap_or_default(),
}),
}
}
#[cfg(unix)]
fn extract_and_append_etag<'b>(
bump: &'b bumpalo::Bump,
etags: &mut Vec<&'b str>,
headers: &reqwest::header::HeaderMap,
) -> Result<()> {
use reqwest::header::ETAG;
let etag = headers.get(ETAG).ok_or_else(|| Error::S3XmlError("Missing ETag header".into()))?;
let etag = etag.to_str().map_err(|e| Error::S3XmlError(Box::new(e)))?;
etags.push(bump.alloc_str(etag));
Ok(())
}

View File

@@ -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, 24, 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":"v1.24.0"}, 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.", }

View File

@@ -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, 24, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
----------------------------------------------------------------------
### Status:
enqueued [0,]

View File

@@ -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, 24, 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:

View File

@@ -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, 24, 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":"v1.24.0"}, 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,]

View File

@@ -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, 24, 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":"v1.24.0"}, 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,]

View File

@@ -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, 24, 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":"v1.24.0"}, 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,]

View File

@@ -126,7 +126,7 @@ impl IndexScheduler {
std::fs::create_dir_all(&options.auth_path).unwrap();
let auth_env = open_auth_store_env(&options.auth_path).unwrap();
let index_scheduler =
Self::new_test(options, auth_env, version, None, sender, planned_failures).unwrap();
Self::new(options, auth_env, version, None, sender, planned_failures).unwrap();
// To be 100% consistent between all test we're going to start the scheduler right now
// and ensure it's in the expected starting state.

View File

@@ -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 +9,79 @@ 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,
(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(
@@ -97,14 +94,31 @@ 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,
},
)?;
wtxn.commit()?;
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)
}
}

View File

@@ -379,7 +379,6 @@ impl crate::IndexScheduler {
status,
kind,
network: _,
custom_metadata: _,
} = task;
assert_eq!(uid, task.uid);
if task.status != Status::Enqueued {

View File

@@ -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

View File

@@ -15,7 +15,7 @@ license.workspace = true
serde_json = "1.0"
[dev-dependencies]
criterion = "0.7.0"
criterion = "0.6.0"
[[bench]]
name = "depth"

View File

@@ -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"] }

View File

@@ -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"] }

View File

@@ -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

View File

@@ -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
}
}
}

View File

@@ -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>,
}

View File

@@ -254,12 +254,10 @@ InvalidSearchHybridQuery , InvalidRequest , BAD_REQU
InvalidIndexLimit , InvalidRequest , BAD_REQUEST ;
InvalidIndexOffset , InvalidRequest , BAD_REQUEST ;
InvalidIndexPrimaryKey , InvalidRequest , BAD_REQUEST ;
InvalidIndexCustomMetadata , InvalidRequest , BAD_REQUEST ;
InvalidIndexUid , InvalidRequest , BAD_REQUEST ;
InvalidMultiSearchFacets , InvalidRequest , BAD_REQUEST ;
InvalidMultiSearchFacetsByIndex , InvalidRequest , BAD_REQUEST ;
InvalidMultiSearchFacetOrder , InvalidRequest , BAD_REQUEST ;
InvalidMultiSearchQueryPersonalization , InvalidRequest , BAD_REQUEST ;
InvalidMultiSearchFederated , InvalidRequest , BAD_REQUEST ;
InvalidMultiSearchFederationOptions , InvalidRequest , BAD_REQUEST ;
InvalidMultiSearchMaxValuesPerFacet , InvalidRequest , BAD_REQUEST ;
@@ -317,8 +315,6 @@ InvalidSearchShowRankingScoreDetails , InvalidRequest , BAD_REQU
InvalidSimilarShowRankingScoreDetails , InvalidRequest , BAD_REQUEST ;
InvalidSearchSort , InvalidRequest , BAD_REQUEST ;
InvalidSearchDistinct , InvalidRequest , BAD_REQUEST ;
InvalidSearchPersonalize , InvalidRequest , BAD_REQUEST ;
InvalidSearchPersonalizeUserContext , InvalidRequest , BAD_REQUEST ;
InvalidSearchMediaAndVector , InvalidRequest , BAD_REQUEST ;
InvalidSettingsDisplayedAttributes , InvalidRequest , BAD_REQUEST ;
InvalidSettingsDistinctAttribute , InvalidRequest , BAD_REQUEST ;
@@ -394,9 +390,6 @@ TooManyVectors , InvalidRequest , BAD_REQU
UnretrievableDocument , Internal , BAD_REQUEST ;
UnretrievableErrorCode , InvalidRequest , BAD_REQUEST ;
UnsupportedMediaType , InvalidRequest , UNSUPPORTED_MEDIA_TYPE ;
InvalidS3SnapshotRequest , Internal , BAD_REQUEST ;
InvalidS3SnapshotParameters , Internal , BAD_REQUEST ;
S3SnapshotServerError , Internal , BAD_GATEWAY ;
// Experimental features
VectorEmbeddingError , InvalidRequest , BAD_REQUEST ;
@@ -433,7 +426,6 @@ 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 ;
@@ -687,18 +679,6 @@ impl fmt::Display for deserr_codes::InvalidNetworkSearchApiKey {
}
}
impl fmt::Display for deserr_codes::InvalidSearchPersonalize {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!(f, "the value of `personalize` is invalid, expected a JSON object with `userContext` string.")
}
}
impl fmt::Display for deserr_codes::InvalidSearchPersonalizeUserContext {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!(f, "the value of `userContext` is invalid, expected a string.")
}
}
#[macro_export]
macro_rules! internal_error {
($target:ty : $($other:path), *) => {

View File

@@ -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;

View File

@@ -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>,
}

View File

@@ -346,26 +346,24 @@ impl<T> Settings<T> {
continue;
};
hide_secret(api_key, 0);
Self::hide_secret(api_key);
}
}
}
/// Redact a secret string, starting from the `secret_offset`th byte.
pub fn hide_secret(secret: &mut String, secret_offset: usize) {
match secret.len().checked_sub(secret_offset) {
None => (),
Some(x) if x < 10 => {
secret.replace_range(secret_offset.., "XXX...");
}
Some(x) if x < 20 => {
secret.replace_range((secret_offset + 2).., "XXXX...");
}
Some(x) if x < 30 => {
secret.replace_range((secret_offset + 3).., "XXXXX...");
}
Some(_x) => {
secret.replace_range((secret_offset + 5).., "XXXXXX...");
fn hide_secret(secret: &mut String) {
match secret.len() {
x if x < 10 => {
secret.replace_range(.., "XXX...");
}
x if x < 20 => {
secret.replace_range(2.., "XXXX...");
}
x if x < 30 => {
secret.replace_range(3.., "XXXXX...");
}
_x => {
secret.replace_range(5.., "XXXXXX...");
}
}
}
}

View File

@@ -55,9 +55,6 @@ pub struct TaskView {
#[serde(default, skip_serializing_if = "Option::is_none")]
pub network: Option<TaskNetwork>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub custom_metadata: Option<String>,
}
impl TaskView {
@@ -76,7 +73,6 @@ impl TaskView {
started_at: task.started_at,
finished_at: task.finished_at,
network: task.network.clone(),
custom_metadata: task.custom_metadata.clone(),
}
}
}

View File

@@ -45,9 +45,6 @@ pub struct Task {
#[serde(default, skip_serializing_if = "Option::is_none")]
pub network: Option<TaskNetwork>,
#[serde(default, skip_serializing_if = "Option::is_none")]
pub custom_metadata: Option<String>,
}
impl Task {

View File

@@ -11,24 +11,6 @@ pub struct Webhook {
pub headers: BTreeMap<String, String>,
}
impl Webhook {
pub fn redact_authorization_header(&mut self) {
// headers are case insensitive, so to make the redaction robust we iterate over qualifying headers
// rather than getting one canonical `Authorization` header.
for value in self
.headers
.iter_mut()
.filter_map(|(name, value)| name.eq_ignore_ascii_case("authorization").then_some(value))
{
if value.starts_with("Bearer ") {
crate::settings::hide_secret(value, "Bearer ".len());
} else {
crate::settings::hide_secret(value, 0);
}
}
}
}
#[derive(Debug, Serialize, Default, Clone, PartialEq)]
#[serde(rename_all = "camelCase")]
pub struct WebhooksView {

View File

@@ -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"]

View File

@@ -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,
@@ -208,7 +208,6 @@ struct Infos {
experimental_no_edition_2024_for_prefix_post_processing: bool,
experimental_no_edition_2024_for_facet_post_processing: bool,
experimental_vector_store_setting: bool,
experimental_personalization: bool,
gpu_enabled: bool,
db_path: bool,
import_dump: bool,
@@ -218,7 +217,6 @@ struct Infos {
import_snapshot: bool,
schedule_snapshot: Option<u64>,
snapshot_dir: bool,
uses_s3_snapshots: bool,
ignore_missing_snapshot: bool,
ignore_snapshot_if_db_exists: bool,
http_addr: bool,
@@ -287,8 +285,6 @@ impl Infos {
indexer_options,
config_file_path,
no_analytics: _,
experimental_personalization_api_key,
s3_snapshot_options,
} = options;
let schedule_snapshot = match schedule_snapshot {
@@ -352,14 +348,13 @@ impl Infos {
import_snapshot: import_snapshot.is_some(),
schedule_snapshot,
snapshot_dir: snapshot_dir != PathBuf::from("snapshots/"),
uses_s3_snapshots: s3_snapshot_options.is_some(),
ignore_missing_snapshot,
ignore_snapshot_if_db_exists,
http_addr: http_addr != default_http_addr(),
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(),
@@ -376,7 +371,6 @@ impl Infos {
experimental_no_edition_2024_for_settings,
experimental_no_edition_2024_for_prefix_post_processing,
experimental_no_edition_2024_for_facet_post_processing,
experimental_personalization: experimental_personalization_api_key.is_some(),
}
}
}

View File

@@ -38,8 +38,6 @@ pub enum MeilisearchHttpError {
PaginationInFederatedQuery(usize, &'static str),
#[error("Inside `.queries[{0}]`: Using facet options is not allowed in federated queries.\n - Hint: remove `facets` from query #{0} or remove `federation` from the request\n - Hint: pass `federation.facetsByIndex.{1}: {2:?}` for facets in federated search")]
FacetsInFederatedQuery(usize, String, Vec<String>),
#[error("Inside `.queries[{0}]`: Using `.personalize` is not allowed in federated queries.\n - Hint: remove `personalize` from query #{0} or remove `federation` from the request")]
PersonalizationInFederatedQuery(usize),
#[error("Inconsistent order for values in facet `{facet}`: index `{previous_uid}` orders {previous_facet_order}, but index `{current_uid}` orders {index_facet_order}.\n - Hint: Remove `federation.mergeFacets` or change `faceting.sortFacetValuesBy` to be consistent in settings.")]
InconsistentFacetOrder {
facet: String,
@@ -139,9 +137,6 @@ impl ErrorCode for MeilisearchHttpError {
MeilisearchHttpError::InconsistentFacetOrder { .. } => {
Code::InvalidMultiSearchFacetOrder
}
MeilisearchHttpError::PersonalizationInFederatedQuery(_) => {
Code::InvalidMultiSearchQueryPersonalization
}
MeilisearchHttpError::InconsistentOriginHeaders { .. } => {
Code::InconsistentDocumentChangeHeaders
}

View File

@@ -11,7 +11,6 @@ pub mod middleware;
pub mod option;
#[cfg(test)]
mod option_test;
pub mod personalization;
pub mod routes;
pub mod search;
pub mod search_queue;
@@ -59,7 +58,6 @@ use tracing::{error, info_span};
use tracing_subscriber::filter::Targets;
use crate::error::MeilisearchHttpError;
use crate::personalization::PersonalizationService;
/// Default number of simultaneously opened indexes.
///
@@ -130,8 +128,12 @@ pub type LogStderrType = tracing_subscriber::filter::Filtered<
>;
pub fn create_app(
services: ServicesData,
index_scheduler: Data<IndexScheduler>,
auth_controller: Data<AuthController>,
search_queue: Data<SearchQueue>,
opt: Opt,
logs: (LogRouteHandle, LogStderrHandle),
analytics: Data<Analytics>,
enable_dashboard: bool,
) -> actix_web::App<
impl ServiceFactory<
@@ -143,7 +145,17 @@ pub fn create_app(
>,
> {
let app = actix_web::App::new()
.configure(|s| configure_data(s, services, &opt))
.configure(|s| {
configure_data(
s,
index_scheduler.clone(),
auth_controller.clone(),
search_queue.clone(),
&opt,
logs,
analytics.clone(),
)
})
.configure(routes::configure)
.configure(|s| dashboard(s, enable_dashboard));
@@ -221,26 +233,12 @@ pub fn setup_meilisearch(
task_db_size: opt.max_task_db_size.as_u64() as usize,
index_base_map_size: opt.max_index_size.as_u64() as usize,
enable_mdb_writemap: opt.experimental_reduce_indexing_memory_usage,
indexer_config: Arc::new({
let s3_snapshot_options =
opt.s3_snapshot_options.clone().map(|opt| opt.try_into()).transpose()?;
IndexerConfig { s3_snapshot_options, ..(&opt.indexer_options).try_into()? }
}),
indexer_config: Arc::new((&opt.indexer_options).try_into()?),
autobatching_enabled: true,
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(),
@@ -536,11 +534,7 @@ fn import_dump(
let indexer_config = if base_config.max_threads.is_none() {
let (thread_pool, _) = default_thread_pool_and_threads();
let _config = IndexerConfig {
thread_pool,
s3_snapshot_options: base_config.s3_snapshot_options.clone(),
..*base_config
};
let _config = IndexerConfig { thread_pool, ..*base_config };
backup_config = _config;
&backup_config
} else {
@@ -688,26 +682,23 @@ fn import_dump(
Ok(index_scheduler_dump.finish()?)
}
pub fn configure_data(config: &mut web::ServiceConfig, services: ServicesData, opt: &Opt) {
let ServicesData {
index_scheduler,
auth,
search_queue,
personalization_service,
logs_route_handle,
logs_stderr_handle,
analytics,
} = services;
pub fn configure_data(
config: &mut web::ServiceConfig,
index_scheduler: Data<IndexScheduler>,
auth: Data<AuthController>,
search_queue: Data<SearchQueue>,
opt: &Opt,
(logs_route, logs_stderr): (LogRouteHandle, LogStderrHandle),
analytics: Data<Analytics>,
) {
let http_payload_size_limit = opt.http_payload_size_limit.as_u64() as usize;
config
.app_data(index_scheduler)
.app_data(auth)
.app_data(search_queue)
.app_data(analytics)
.app_data(personalization_service)
.app_data(logs_route_handle)
.app_data(logs_stderr_handle)
.app_data(web::Data::new(logs_route))
.app_data(web::Data::new(logs_stderr))
.app_data(web::Data::new(opt.clone()))
.app_data(
web::JsonConfig::default()
@@ -768,14 +759,3 @@ pub fn dashboard(config: &mut web::ServiceConfig, enable_frontend: bool) {
pub fn dashboard(config: &mut web::ServiceConfig, _enable_frontend: bool) {
config.service(web::resource("/").route(web::get().to(routes::running)));
}
#[derive(Clone)]
pub struct ServicesData {
pub index_scheduler: Data<IndexScheduler>,
pub auth: Data<AuthController>,
pub search_queue: Data<SearchQueue>,
pub personalization_service: Data<PersonalizationService>,
pub logs_route_handle: Data<LogRouteHandle>,
pub logs_stderr_handle: Data<LogStderrHandle>,
pub analytics: Data<Analytics>,
}

View File

@@ -14,11 +14,10 @@ use index_scheduler::IndexScheduler;
use is_terminal::IsTerminal;
use meilisearch::analytics::Analytics;
use meilisearch::option::LogMode;
use meilisearch::personalization::PersonalizationService;
use meilisearch::search_queue::SearchQueue;
use meilisearch::{
analytics, create_app, setup_meilisearch, LogRouteHandle, LogRouteType, LogStderrHandle,
LogStderrType, Opt, ServicesData, SubscriberForSecondLayer,
LogStderrType, Opt, SubscriberForSecondLayer,
};
use meilisearch_auth::{generate_master_key, AuthController, MASTER_KEY_MIN_SIZE};
use termcolor::{Color, ColorChoice, ColorSpec, StandardStream, WriteColor};
@@ -153,15 +152,8 @@ async fn run_http(
let enable_dashboard = &opt.env == "development";
let opt_clone = opt.clone();
let index_scheduler = Data::from(index_scheduler);
let auth = Data::from(auth_controller);
let auth_controller = Data::from(auth_controller);
let analytics = Data::from(analytics);
// Create personalization service with API key from options
let personalization_service = Data::new(
opt.experimental_personalization_api_key
.clone()
.map(PersonalizationService::cohere)
.unwrap_or_else(PersonalizationService::disabled),
);
let search_queue = SearchQueue::new(
opt.experimental_search_queue_size,
available_parallelism()
@@ -173,25 +165,21 @@ async fn run_http(
usize::from(opt.experimental_drop_search_after) as u64
));
let search_queue = Data::new(search_queue);
let (logs_route_handle, logs_stderr_handle) = logs;
let logs_route_handle = Data::new(logs_route_handle);
let logs_stderr_handle = Data::new(logs_stderr_handle);
let services = ServicesData {
index_scheduler,
auth,
search_queue,
personalization_service,
logs_route_handle,
logs_stderr_handle,
analytics,
};
let http_server =
HttpServer::new(move || create_app(services.clone(), opt.clone(), enable_dashboard))
// Disable signals allows the server to terminate immediately when a user enter CTRL-C
.disable_signals()
.keep_alive(KeepAlive::Os);
let http_server = HttpServer::new(move || {
create_app(
index_scheduler.clone(),
auth_controller.clone(),
search_queue.clone(),
opt.clone(),
logs.clone(),
analytics.clone(),
enable_dashboard,
)
})
// Disable signals allows the server to terminate immediately when a user enter CTRL-C
.disable_signals()
.keep_alive(KeepAlive::Os);
if let Some(config) = opt_clone.get_ssl_config()? {
http_server.bind_rustls_0_23(opt_clone.http_addr, config)?.run().await?;

View File

@@ -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");
@@ -129,9 +114,4 @@ lazy_static! {
"Meilisearch Task Queue Size Until Stop Registering",
))
.expect("Can't create a metric");
pub static ref MEILISEARCH_PERSONALIZED_SEARCH_REQUESTS: IntGauge = register_int_gauge!(opts!(
"meilisearch_personalized_search_requests",
"Meilisearch number of search requests with personalization"
))
.expect("Can't create a metric");
}

View File

@@ -7,13 +7,12 @@ use std::ops::Deref;
use std::path::PathBuf;
use std::str::FromStr;
use std::sync::Arc;
use std::time::Duration;
use std::{env, fmt, fs};
use byte_unit::{Byte, ParseError, UnitType};
use clap::Parser;
use meilisearch_types::features::InstanceTogglableFeatures;
use meilisearch_types::milli::update::{IndexerConfig, S3SnapshotOptions};
use meilisearch_types::milli::update::IndexerConfig;
use meilisearch_types::milli::ThreadPoolNoAbortBuilder;
use rustls::server::{ServerSessionMemoryCache, WebPkiClientVerifier};
use rustls::RootCertStore;
@@ -75,22 +74,6 @@ const MEILI_EXPERIMENTAL_EMBEDDING_CACHE_ENTRIES: &str =
const MEILI_EXPERIMENTAL_NO_SNAPSHOT_COMPACTION: &str = "MEILI_EXPERIMENTAL_NO_SNAPSHOT_COMPACTION";
const MEILI_EXPERIMENTAL_NO_EDITION_2024_FOR_DUMPS: &str =
"MEILI_EXPERIMENTAL_NO_EDITION_2024_FOR_DUMPS";
const MEILI_EXPERIMENTAL_PERSONALIZATION_API_KEY: &str =
"MEILI_EXPERIMENTAL_PERSONALIZATION_API_KEY";
// Related to S3 snapshots
const MEILI_S3_BUCKET_URL: &str = "MEILI_S3_BUCKET_URL";
const MEILI_S3_BUCKET_REGION: &str = "MEILI_S3_BUCKET_REGION";
const MEILI_S3_BUCKET_NAME: &str = "MEILI_S3_BUCKET_NAME";
const MEILI_S3_SNAPSHOT_PREFIX: &str = "MEILI_S3_SNAPSHOT_PREFIX";
const MEILI_S3_ACCESS_KEY: &str = "MEILI_S3_ACCESS_KEY";
const MEILI_S3_SECRET_KEY: &str = "MEILI_S3_SECRET_KEY";
const MEILI_EXPERIMENTAL_S3_MAX_IN_FLIGHT_PARTS: &str = "MEILI_EXPERIMENTAL_S3_MAX_IN_FLIGHT_PARTS";
const MEILI_EXPERIMENTAL_S3_COMPRESSION_LEVEL: &str = "MEILI_EXPERIMENTAL_S3_COMPRESSION_LEVEL";
const MEILI_EXPERIMENTAL_S3_SIGNATURE_DURATION_SECONDS: &str =
"MEILI_EXPERIMENTAL_S3_SIGNATURE_DURATION_SECONDS";
const MEILI_EXPERIMENTAL_S3_MULTIPART_PART_SIZE: &str = "MEILI_EXPERIMENTAL_S3_MULTIPART_PART_SIZE";
const DEFAULT_CONFIG_FILE_PATH: &str = "./config.toml";
const DEFAULT_DB_PATH: &str = "./data.ms";
const DEFAULT_HTTP_ADDR: &str = "localhost:7700";
@@ -100,10 +83,6 @@ const DEFAULT_SNAPSHOT_DIR: &str = "snapshots/";
const DEFAULT_SNAPSHOT_INTERVAL_SEC: u64 = 86400;
const DEFAULT_SNAPSHOT_INTERVAL_SEC_STR: &str = "86400";
const DEFAULT_DUMP_DIR: &str = "dumps/";
const DEFAULT_S3_SNAPSHOT_MAX_IN_FLIGHT_PARTS: NonZeroUsize = NonZeroUsize::new(10).unwrap();
const DEFAULT_S3_SNAPSHOT_COMPRESSION_LEVEL: u32 = 0;
const DEFAULT_S3_SNAPSHOT_SIGNATURE_DURATION_SECONDS: u64 = 8 * 3600; // 8 hours
const DEFAULT_S3_SNAPSHOT_MULTIPART_PART_SIZE: Byte = Byte::from_u64(375 * 1024 * 1024); // 375 MiB
const MEILI_MAX_INDEXING_MEMORY: &str = "MEILI_MAX_INDEXING_MEMORY";
const MEILI_MAX_INDEXING_THREADS: &str = "MEILI_MAX_INDEXING_THREADS";
@@ -473,14 +452,11 @@ 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.
@@ -499,20 +475,10 @@ pub struct Opt {
#[serde(default)]
pub experimental_no_snapshot_compaction: bool,
/// Experimental personalization API key feature.
///
/// Sets the API key for personalization features.
#[clap(long, env = MEILI_EXPERIMENTAL_PERSONALIZATION_API_KEY)]
pub experimental_personalization_api_key: Option<String>,
#[serde(flatten)]
#[clap(flatten)]
pub indexer_options: IndexerOpts,
#[serde(flatten)]
#[clap(flatten)]
pub s3_snapshot_options: Option<S3SnapshotOpts>,
/// Set the path to a configuration file that should be used to setup the engine.
/// Format must be TOML.
#[clap(long)]
@@ -614,8 +580,6 @@ impl Opt {
experimental_limit_batched_tasks_total_size,
experimental_embedding_cache_entries,
experimental_no_snapshot_compaction,
experimental_personalization_api_key,
s3_snapshot_options,
} = self;
export_to_env_if_not_present(MEILI_DB_PATH, db_path);
export_to_env_if_not_present(MEILI_HTTP_ADDR, http_addr);
@@ -704,12 +668,10 @@ 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(),
@@ -718,22 +680,7 @@ impl Opt {
MEILI_EXPERIMENTAL_NO_SNAPSHOT_COMPACTION,
experimental_no_snapshot_compaction.to_string(),
);
if let Some(experimental_personalization_api_key) = experimental_personalization_api_key {
export_to_env_if_not_present(
MEILI_EXPERIMENTAL_PERSONALIZATION_API_KEY,
experimental_personalization_api_key,
);
}
indexer_options.export_to_env();
if let Some(s3_snapshot_options) = s3_snapshot_options {
#[cfg(not(unix))]
{
let _ = s3_snapshot_options;
panic!("S3 snapshot options are not supported on Windows");
}
#[cfg(unix)]
s3_snapshot_options.export_to_env();
}
}
pub fn get_ssl_config(&self) -> anyhow::Result<Option<rustls::ServerConfig>> {
@@ -902,16 +849,6 @@ impl TryFrom<&IndexerOpts> for IndexerConfig {
type Error = anyhow::Error;
fn try_from(other: &IndexerOpts) -> Result<Self, Self::Error> {
let IndexerOpts {
max_indexing_memory,
max_indexing_threads,
skip_index_budget,
experimental_no_edition_2024_for_settings,
experimental_no_edition_2024_for_dumps,
experimental_no_edition_2024_for_prefix_post_processing,
experimental_no_edition_2024_for_facet_post_processing,
} = other;
let thread_pool = ThreadPoolNoAbortBuilder::new_for_indexing()
.num_threads(other.max_indexing_threads.unwrap_or_else(|| num_cpus::get() / 2))
.build()?;
@@ -919,163 +856,21 @@ impl TryFrom<&IndexerOpts> for IndexerConfig {
Ok(Self {
thread_pool,
log_every_n: Some(DEFAULT_LOG_EVERY_N),
max_memory: max_indexing_memory.map(|b| b.as_u64() as usize),
max_threads: max_indexing_threads.0,
max_memory: other.max_indexing_memory.map(|b| b.as_u64() as usize),
max_threads: *other.max_indexing_threads,
max_positions_per_attributes: None,
skip_index_budget: *skip_index_budget,
experimental_no_edition_2024_for_settings: *experimental_no_edition_2024_for_settings,
experimental_no_edition_2024_for_dumps: *experimental_no_edition_2024_for_dumps,
skip_index_budget: other.skip_index_budget,
experimental_no_edition_2024_for_settings: other
.experimental_no_edition_2024_for_settings,
experimental_no_edition_2024_for_dumps: other.experimental_no_edition_2024_for_dumps,
chunk_compression_type: Default::default(),
chunk_compression_level: Default::default(),
documents_chunk_size: Default::default(),
max_nb_chunks: Default::default(),
experimental_no_edition_2024_for_prefix_post_processing:
*experimental_no_edition_2024_for_prefix_post_processing,
experimental_no_edition_2024_for_facet_post_processing:
*experimental_no_edition_2024_for_facet_post_processing,
s3_snapshot_options: None,
})
}
}
#[derive(Debug, Clone, Parser, Deserialize)]
// This group is a bit tricky but makes it possible to require all listed fields if one of them
// is specified. It lets us keep an Option for the S3SnapshotOpts configuration.
// <https://github.com/clap-rs/clap/issues/5092#issuecomment-2616986075>
#[group(requires_all = ["s3_bucket_url", "s3_bucket_region", "s3_bucket_name", "s3_snapshot_prefix", "s3_access_key", "s3_secret_key"])]
pub struct S3SnapshotOpts {
/// The S3 bucket URL in the format https://s3.<region>.amazonaws.com.
#[clap(long, env = MEILI_S3_BUCKET_URL, required = false)]
#[serde(default)]
pub s3_bucket_url: String,
/// The region in the format us-east-1.
#[clap(long, env = MEILI_S3_BUCKET_REGION, required = false)]
#[serde(default)]
pub s3_bucket_region: String,
/// The bucket name.
#[clap(long, env = MEILI_S3_BUCKET_NAME, required = false)]
#[serde(default)]
pub s3_bucket_name: String,
/// The prefix path where to put the snapshot, uses normal slashes (/).
#[clap(long, env = MEILI_S3_SNAPSHOT_PREFIX, required = false)]
#[serde(default)]
pub s3_snapshot_prefix: String,
/// The S3 access key.
#[clap(long, env = MEILI_S3_ACCESS_KEY, required = false)]
#[serde(default)]
pub s3_access_key: String,
/// The S3 secret key.
#[clap(long, env = MEILI_S3_SECRET_KEY, required = false)]
#[serde(default)]
pub s3_secret_key: String,
/// The maximum number of parts that can be uploaded in parallel.
///
/// For more information, see <https://github.com/orgs/meilisearch/discussions/869>.
#[clap(long, env = MEILI_EXPERIMENTAL_S3_MAX_IN_FLIGHT_PARTS, default_value_t = default_experimental_s3_snapshot_max_in_flight_parts())]
#[serde(default = "default_experimental_s3_snapshot_max_in_flight_parts")]
pub experimental_s3_max_in_flight_parts: NonZeroUsize,
/// The compression level. Defaults to no compression (0).
///
/// For more information, see <https://github.com/orgs/meilisearch/discussions/869>.
#[clap(long, env = MEILI_EXPERIMENTAL_S3_COMPRESSION_LEVEL, default_value_t = default_experimental_s3_snapshot_compression_level())]
#[serde(default = "default_experimental_s3_snapshot_compression_level")]
pub experimental_s3_compression_level: u32,
/// The signature duration for the multipart upload.
///
/// For more information, see <https://github.com/orgs/meilisearch/discussions/869>.
#[clap(long, env = MEILI_EXPERIMENTAL_S3_SIGNATURE_DURATION_SECONDS, default_value_t = default_experimental_s3_snapshot_signature_duration_seconds())]
#[serde(default = "default_experimental_s3_snapshot_signature_duration_seconds")]
pub experimental_s3_signature_duration_seconds: u64,
/// The size of the the multipart parts.
///
/// Must not be less than 10MiB and larger than 8GiB. Yes,
/// twice the boundaries of the AWS S3 multipart upload
/// because we use it a bit differently internally.
///
/// For more information, see <https://github.com/orgs/meilisearch/discussions/869>.
#[clap(long, env = MEILI_EXPERIMENTAL_S3_MULTIPART_PART_SIZE, default_value_t = default_experimental_s3_snapshot_multipart_part_size())]
#[serde(default = "default_experimental_s3_snapshot_multipart_part_size")]
pub experimental_s3_multipart_part_size: Byte,
}
impl S3SnapshotOpts {
/// Exports the values to their corresponding env vars if they are not set.
pub fn export_to_env(self) {
let S3SnapshotOpts {
s3_bucket_url,
s3_bucket_region,
s3_bucket_name,
s3_snapshot_prefix,
s3_access_key,
s3_secret_key,
experimental_s3_max_in_flight_parts,
experimental_s3_compression_level,
experimental_s3_signature_duration_seconds,
experimental_s3_multipart_part_size,
} = self;
export_to_env_if_not_present(MEILI_S3_BUCKET_URL, s3_bucket_url);
export_to_env_if_not_present(MEILI_S3_BUCKET_REGION, s3_bucket_region);
export_to_env_if_not_present(MEILI_S3_BUCKET_NAME, s3_bucket_name);
export_to_env_if_not_present(MEILI_S3_SNAPSHOT_PREFIX, s3_snapshot_prefix);
export_to_env_if_not_present(MEILI_S3_ACCESS_KEY, s3_access_key);
export_to_env_if_not_present(MEILI_S3_SECRET_KEY, s3_secret_key);
export_to_env_if_not_present(
MEILI_EXPERIMENTAL_S3_MAX_IN_FLIGHT_PARTS,
experimental_s3_max_in_flight_parts.to_string(),
);
export_to_env_if_not_present(
MEILI_EXPERIMENTAL_S3_COMPRESSION_LEVEL,
experimental_s3_compression_level.to_string(),
);
export_to_env_if_not_present(
MEILI_EXPERIMENTAL_S3_SIGNATURE_DURATION_SECONDS,
experimental_s3_signature_duration_seconds.to_string(),
);
export_to_env_if_not_present(
MEILI_EXPERIMENTAL_S3_MULTIPART_PART_SIZE,
experimental_s3_multipart_part_size.to_string(),
);
}
}
impl TryFrom<S3SnapshotOpts> for S3SnapshotOptions {
type Error = anyhow::Error;
fn try_from(other: S3SnapshotOpts) -> Result<Self, Self::Error> {
let S3SnapshotOpts {
s3_bucket_url,
s3_bucket_region,
s3_bucket_name,
s3_snapshot_prefix,
s3_access_key,
s3_secret_key,
experimental_s3_max_in_flight_parts,
experimental_s3_compression_level,
experimental_s3_signature_duration_seconds,
experimental_s3_multipart_part_size,
} = other;
Ok(S3SnapshotOptions {
s3_bucket_url,
s3_bucket_region,
s3_bucket_name,
s3_snapshot_prefix,
s3_access_key,
s3_secret_key,
s3_max_in_flight_parts: experimental_s3_max_in_flight_parts,
s3_compression_level: experimental_s3_compression_level,
s3_signature_duration: Duration::from_secs(experimental_s3_signature_duration_seconds),
s3_multipart_part_size: experimental_s3_multipart_part_size.as_u64(),
experimental_no_edition_2024_for_prefix_post_processing: other
.experimental_no_edition_2024_for_prefix_post_processing,
experimental_no_edition_2024_for_facet_post_processing: other
.experimental_no_edition_2024_for_facet_post_processing,
})
}
}
@@ -1278,6 +1073,10 @@ 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
}
@@ -1290,22 +1089,6 @@ fn default_snapshot_interval_sec() -> &'static str {
DEFAULT_SNAPSHOT_INTERVAL_SEC_STR
}
fn default_experimental_s3_snapshot_max_in_flight_parts() -> NonZeroUsize {
DEFAULT_S3_SNAPSHOT_MAX_IN_FLIGHT_PARTS
}
fn default_experimental_s3_snapshot_compression_level() -> u32 {
DEFAULT_S3_SNAPSHOT_COMPRESSION_LEVEL
}
fn default_experimental_s3_snapshot_signature_duration_seconds() -> u64 {
DEFAULT_S3_SNAPSHOT_SIGNATURE_DURATION_SECONDS
}
fn default_experimental_s3_snapshot_multipart_part_size() -> Byte {
DEFAULT_S3_SNAPSHOT_MULTIPART_PART_SIZE
}
fn default_dump_dir() -> PathBuf {
PathBuf::from(DEFAULT_DUMP_DIR)
}

View File

@@ -1,366 +0,0 @@
use std::time::Duration;
use meilisearch_types::error::{Code, ErrorCode, ResponseError};
use meilisearch_types::milli::TimeBudget;
use rand::Rng;
use reqwest::Client;
use serde::{Deserialize, Serialize};
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;
#[derive(Debug, thiserror::Error)]
enum PersonalizationError {
#[error("Personalization service: HTTP request failed: {0}")]
Request(#[from] reqwest::Error),
#[error("Personalization service: Failed to parse response: {0}")]
Parse(String),
#[error("Personalization service: Cohere API error: {0}")]
Api(String),
#[error("Personalization service: Unauthorized: invalid API key")]
Unauthorized,
#[error("Personalization service: Rate limited: too many requests")]
RateLimited,
#[error("Personalization service: Bad request: {0}")]
BadRequest(String),
#[error("Personalization service: Internal server error: {0}")]
InternalServerError(String),
#[error("Personalization service: Network error: {0}")]
Network(String),
#[error("Personalization service: Deadline exceeded")]
DeadlineExceeded,
#[error(transparent)]
FeatureNotEnabled(#[from] index_scheduler::error::FeatureNotEnabledError),
}
impl ErrorCode for PersonalizationError {
fn error_code(&self) -> Code {
match self {
PersonalizationError::FeatureNotEnabled { .. } => Code::FeatureNotEnabled,
PersonalizationError::Unauthorized => Code::RemoteInvalidApiKey,
PersonalizationError::RateLimited => Code::TooManySearchRequests,
PersonalizationError::BadRequest(_) => Code::RemoteBadRequest,
PersonalizationError::InternalServerError(_) => Code::RemoteRemoteError,
PersonalizationError::Network(_) | PersonalizationError::Request(_) => {
Code::RemoteCouldNotSendRequest
}
PersonalizationError::Parse(_) | PersonalizationError::Api(_) => {
Code::RemoteBadResponse
}
PersonalizationError::DeadlineExceeded => Code::Internal, // should not be returned to the client
}
}
}
pub struct CohereService {
client: Client,
api_key: String,
}
impl CohereService {
pub fn new(api_key: String) -> Self {
info!("Personalization service initialized with Cohere API");
let client = Client::builder()
.timeout(Duration::from_secs(30))
.build()
.expect("Failed to create HTTP client");
Self { client, api_key }
}
pub async fn rerank_search_results(
&self,
search_result: SearchResult,
personalize: &Personalize,
query: Option<&str>,
time_budget: TimeBudget,
) -> Result<SearchResult, ResponseError> {
if time_budget.exceeded() {
warn!("Could not rerank due to deadline");
// If the deadline is exceeded, return the original search result instead of an error
return Ok(search_result);
}
// Extract user context from personalization
let user_context = personalize.user_context.as_str();
// Build the prompt by merging query and user context
let prompt = match query {
Some(q) => format!("User Context: {user_context}\nQuery: {q}"),
None => format!("User Context: {user_context}"),
};
// Extract documents for reranking
let documents: Vec<String> = search_result
.hits
.iter()
.map(|hit| {
// Convert the document to a string representation for reranking
serde_json::to_string(&hit.document).unwrap_or_else(|_| "{}".to_string())
})
.collect();
if documents.is_empty() {
return Ok(search_result);
}
// Call Cohere's rerank API with retry logic
let reranked_indices =
match self.call_rerank_with_retry(&prompt, &documents, time_budget).await {
Ok(indices) => indices,
Err(PersonalizationError::DeadlineExceeded) => {
// If the deadline is exceeded, return the original search result instead of an error
return Ok(search_result);
}
Err(e) => return Err(e.into()),
};
debug!("Cohere rerank successful, reordering {} results", search_result.hits.len());
// Reorder the hits based on Cohere's reranking
let mut reranked_hits = Vec::new();
for index in reranked_indices.iter() {
if let Some(hit) = search_result.hits.get(*index) {
reranked_hits.push(hit.clone());
}
}
Ok(SearchResult { hits: reranked_hits, ..search_result })
}
async fn call_rerank_with_retry(
&self,
query: &str,
documents: &[String],
time_budget: TimeBudget,
) -> Result<Vec<usize>, PersonalizationError> {
let request_body = CohereRerankRequest {
query: query.to_string(),
documents: documents.to_vec(),
model: "rerank-english-v3.0".to_string(),
};
// Retry loop similar to vector extraction
for attempt in 0..MAX_RETRIES {
let response_result = self.send_rerank_request(&request_body).await;
let retry_duration = match self.handle_response(response_result).await {
Ok(indices) => return Ok(indices),
Err(retry) => {
warn!("Cohere rerank attempt #{} failed: {}", attempt, retry.error);
if time_budget.exceeded() {
warn!("Could not rerank due to deadline");
return Err(PersonalizationError::DeadlineExceeded);
} else {
match retry.into_duration(attempt) {
Ok(d) => d,
Err(error) => return Err(error),
}
}
}
};
// randomly up to double the retry duration
let retry_duration = retry_duration
+ rand::thread_rng().gen_range(std::time::Duration::ZERO..retry_duration);
warn!("Retrying after {}ms", retry_duration.as_millis());
tokio::time::sleep(retry_duration).await;
}
// Final attempt without retry
let response_result = self.send_rerank_request(&request_body).await;
match self.handle_response(response_result).await {
Ok(indices) => Ok(indices),
Err(retry) => Err(retry.into_error()),
}
}
async fn send_rerank_request(
&self,
request_body: &CohereRerankRequest,
) -> Result<reqwest::Response, reqwest::Error> {
self.client
.post(COHERE_API_URL)
.header("Authorization", format!("Bearer {}", self.api_key))
.header("Content-Type", "application/json")
.json(request_body)
.send()
.await
}
async fn handle_response(
&self,
response_result: Result<reqwest::Response, reqwest::Error>,
) -> Result<Vec<usize>, Retry> {
let response = match response_result {
Ok(r) => r,
Err(e) if e.is_timeout() => {
return Err(Retry::retry_later(PersonalizationError::Network(format!(
"Request timeout: {}",
e
))));
}
Err(e) => {
return Err(Retry::retry_later(PersonalizationError::Network(format!(
"Network error: {}",
e
))));
}
};
let status = response.status();
let status_code = status.as_u16();
if status.is_success() {
let rerank_response: CohereRerankResponse = match response.json().await {
Ok(r) => r,
Err(e) => {
return Err(Retry::retry_later(PersonalizationError::Parse(format!(
"Failed to parse response: {}",
e
))));
}
};
// Extract indices from rerank results
let indices: Vec<usize> =
rerank_response.results.iter().map(|result| result.index as usize).collect();
return Ok(indices);
}
// Handle error status codes
let error_body = response.text().await.unwrap_or_else(|_| "Unknown error".to_string());
let retry = match status_code {
401 => Retry::give_up(PersonalizationError::Unauthorized),
429 => Retry::rate_limited(PersonalizationError::RateLimited),
400 => Retry::give_up(PersonalizationError::BadRequest(error_body)),
500..=599 => Retry::retry_later(PersonalizationError::InternalServerError(format!(
"Status {}: {}",
status_code, error_body
))),
402..=499 => Retry::give_up(PersonalizationError::Api(format!(
"Status {}: {}",
status_code, error_body
))),
_ => Retry::retry_later(PersonalizationError::Api(format!(
"Unexpected status {}: {}",
status_code, error_body
))),
};
Err(retry)
}
}
#[derive(Serialize)]
struct CohereRerankRequest {
query: String,
documents: Vec<String>,
model: String,
}
#[derive(Deserialize)]
struct CohereRerankResponse {
results: Vec<CohereRerankResult>,
}
#[derive(Deserialize)]
struct CohereRerankResult {
index: u32,
}
// Retry strategy similar to vector extraction
struct Retry {
error: PersonalizationError,
strategy: RetryStrategy,
}
enum RetryStrategy {
GiveUp,
Retry,
RetryAfterRateLimit,
}
impl Retry {
fn give_up(error: PersonalizationError) -> Self {
Self { error, strategy: RetryStrategy::GiveUp }
}
fn retry_later(error: PersonalizationError) -> Self {
Self { error, strategy: RetryStrategy::Retry }
}
fn rate_limited(error: PersonalizationError) -> Self {
Self { error, strategy: RetryStrategy::RetryAfterRateLimit }
}
fn into_duration(self, attempt: u32) -> Result<Duration, PersonalizationError> {
match self.strategy {
RetryStrategy::GiveUp => Err(self.error),
RetryStrategy::Retry => {
// Exponential backoff: 10^attempt milliseconds
Ok(Duration::from_millis((10u64).pow(attempt)))
}
RetryStrategy::RetryAfterRateLimit => {
// Longer backoff for rate limits: 100ms + exponential
Ok(Duration::from_millis(100 + (10u64).pow(attempt)))
}
}
}
fn into_error(self) -> PersonalizationError {
self.error
}
}
pub enum PersonalizationService {
Cohere(CohereService),
Disabled,
}
impl PersonalizationService {
pub fn cohere(api_key: String) -> Self {
// If the API key is empty, consider the personalization service as disabled
if api_key.trim().is_empty() {
Self::disabled()
} else {
Self::Cohere(CohereService::new(api_key))
}
}
pub fn disabled() -> Self {
debug!("Personalization service disabled");
Self::Disabled
}
pub async fn rerank_search_results(
&self,
search_result: SearchResult,
personalize: &Personalize,
query: Option<&str>,
time_budget: TimeBudget,
) -> Result<SearchResult, ResponseError> {
match self {
Self::Cohere(cohere_service) => {
cohere_service
.rerank_search_results(search_result, personalize, query, time_budget)
.await
}
Self::Disabled => Err(PersonalizationError::FeatureNotEnabled(
index_scheduler::error::FeatureNotEnabledError {
disabled_action: "reranking search results",
feature: "personalization",
issue_link: "https://github.com/orgs/meilisearch/discussions/866",
},
)
.into()),
}
}
}

View File

@@ -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(())
}
}

View File

@@ -34,7 +34,7 @@ pub fn configure(cfg: &mut web::ServiceConfig) {
/// Compact an index
#[utoipa::path(
post,
path = "/{indexUid}/compact",
path = "{indexUid}/compact",
tag = "Compact an index",
security(("Bearer" = ["search", "*"])),
params(("indexUid" = String, Path, example = "movies", description = "Index Unique Identifier", nullable = false)),

View File

@@ -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,
@@ -333,12 +333,10 @@ impl Aggregate for DocumentsDeletionAggregator {
pub async fn delete_document(
index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_DELETE }>, Data<IndexScheduler>>,
path: web::Path<DocumentParam>,
params: AwebQueryParameter<CustomMetadataQuery, DeserrQueryParamError>,
req: HttpRequest,
opt: web::Data<Opt>,
analytics: web::Data<Analytics>,
) -> Result<HttpResponse, ResponseError> {
let CustomMetadataQuery { custom_metadata } = params.into_inner();
let DocumentParam { index_uid, document_id } = path.into_inner();
let index_uid = IndexUid::try_from(index_uid)?;
let network = index_scheduler.network();
@@ -361,13 +359,10 @@ pub async fn delete_document(
let dry_run = is_dry_run(&req, &opt)?;
let task = {
let index_scheduler = index_scheduler.clone();
tokio::task::spawn_blocking(move || {
index_scheduler.register_with_custom_metadata(task, uid, custom_metadata, dry_run)
})
.await??
tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run)).await??
};
if network.sharding() && !dry_run {
if network.sharding && !dry_run {
proxy(&index_scheduler, &index_uid, &req, network, Body::none(), &task).await?;
}
@@ -683,19 +678,6 @@ pub struct UpdateDocumentsQuery {
#[param(value_type = char, default = ",", example = ";")]
#[deserr(default, try_from(char) = from_char_csv_delimiter -> DeserrQueryParamError<InvalidDocumentCsvDelimiter>, error = DeserrQueryParamError<InvalidDocumentCsvDelimiter>)]
pub csv_delimiter: Option<u8>,
#[param(example = "custom")]
#[deserr(default, error = DeserrQueryParamError<InvalidIndexCustomMetadata>)]
pub custom_metadata: Option<String>,
}
#[derive(Deserialize, Debug, Deserr, IntoParams)]
#[deserr(error = DeserrQueryParamError, rename_all = camelCase, deny_unknown_fields)]
#[into_params(parameter_in = Query, rename_all = "camelCase")]
pub struct CustomMetadataQuery {
#[param(example = "custom")]
#[deserr(default, error = DeserrQueryParamError<InvalidIndexCustomMetadata>)]
pub custom_metadata: Option<String>,
}
fn from_char_csv_delimiter(
@@ -837,7 +819,6 @@ pub async fn replace_documents(
body,
IndexDocumentsMethod::ReplaceDocuments,
uid,
params.custom_metadata,
dry_run,
allow_index_creation,
&req,
@@ -940,7 +921,6 @@ pub async fn update_documents(
body,
IndexDocumentsMethod::UpdateDocuments,
uid,
params.custom_metadata,
dry_run,
allow_index_creation,
&req,
@@ -960,7 +940,6 @@ async fn document_addition(
body: Payload,
method: IndexDocumentsMethod,
task_id: Option<TaskId>,
custom_metadata: Option<String>,
dry_run: bool,
allow_index_creation: bool,
req: &HttpRequest,
@@ -1086,10 +1065,8 @@ async fn document_addition(
};
let scheduler = index_scheduler.clone();
let task = match tokio::task::spawn_blocking(move || {
scheduler.register_with_custom_metadata(task, task_id, custom_metadata, dry_run)
})
.await?
let task = match tokio::task::spawn_blocking(move || scheduler.register(task, task_id, dry_run))
.await?
{
Ok(task) => task,
Err(e) => {
@@ -1098,7 +1075,7 @@ async fn document_addition(
}
};
if network.sharding() {
if network.sharding {
if let Some(file) = file {
proxy(
&index_scheduler,
@@ -1153,7 +1130,7 @@ async fn copy_body_to_file(
/// Delete a set of documents based on an array of document ids.
#[utoipa::path(
post,
path = "{indexUid}/documents/delete-batch",
path = "{indexUid}/delete-batch",
tag = "Documents",
security(("Bearer" = ["documents.delete", "documents.*", "*"])),
params(
@@ -1184,14 +1161,11 @@ pub async fn delete_documents_batch(
index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_DELETE }>, Data<IndexScheduler>>,
index_uid: web::Path<String>,
body: web::Json<Vec<Value>>,
params: AwebQueryParameter<CustomMetadataQuery, DeserrQueryParamError>,
req: HttpRequest,
opt: web::Data<Opt>,
analytics: web::Data<Analytics>,
) -> Result<HttpResponse, ResponseError> {
debug!(parameters = ?body, "Delete documents by batch");
let CustomMetadataQuery { custom_metadata } = params.into_inner();
let index_uid = IndexUid::try_from(index_uid.into_inner())?;
let network = index_scheduler.network();
@@ -1216,13 +1190,10 @@ pub async fn delete_documents_batch(
let dry_run = is_dry_run(&req, &opt)?;
let task = {
let index_scheduler = index_scheduler.clone();
tokio::task::spawn_blocking(move || {
index_scheduler.register_with_custom_metadata(task, uid, custom_metadata, dry_run)
})
.await??
tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run)).await??
};
if network.sharding() && !dry_run {
if network.sharding && !dry_run {
proxy(&index_scheduler, &index_uid, &req, network, Body::Inline(body), &task).await?;
}
@@ -1273,15 +1244,12 @@ pub struct DocumentDeletionByFilter {
pub async fn delete_documents_by_filter(
index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_DELETE }>, Data<IndexScheduler>>,
index_uid: web::Path<String>,
params: AwebQueryParameter<CustomMetadataQuery, DeserrQueryParamError>,
body: AwebJson<DocumentDeletionByFilter, DeserrJsonError>,
req: HttpRequest,
opt: web::Data<Opt>,
analytics: web::Data<Analytics>,
) -> Result<HttpResponse, ResponseError> {
debug!(parameters = ?body, "Delete documents by filter");
let CustomMetadataQuery { custom_metadata } = params.into_inner();
let index_uid = IndexUid::try_from(index_uid.into_inner())?;
let index_uid = index_uid.into_inner();
let filter = body.into_inner();
@@ -1314,13 +1282,10 @@ pub async fn delete_documents_by_filter(
let dry_run = is_dry_run(&req, &opt)?;
let task = {
let index_scheduler = index_scheduler.clone();
tokio::task::spawn_blocking(move || {
index_scheduler.register_with_custom_metadata(task, uid, custom_metadata, dry_run)
})
.await??
tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run)).await??
};
if network.sharding() && !dry_run {
if network.sharding && !dry_run {
proxy(&index_scheduler, &index_uid, &req, network, Body::Inline(filter), &task).await?;
}
@@ -1407,14 +1372,12 @@ impl Aggregate for EditDocumentsByFunctionAggregator {
pub async fn edit_documents_by_function(
index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_ALL }>, Data<IndexScheduler>>,
index_uid: web::Path<String>,
params: AwebQueryParameter<CustomMetadataQuery, DeserrQueryParamError>,
body: AwebJson<DocumentEditionByFunction, DeserrJsonError>,
params: AwebJson<DocumentEditionByFunction, DeserrJsonError>,
req: HttpRequest,
opt: web::Data<Opt>,
analytics: web::Data<Analytics>,
) -> Result<HttpResponse, ResponseError> {
debug!(parameters = ?body, "Edit documents by function");
let CustomMetadataQuery { custom_metadata } = params.into_inner();
debug!(parameters = ?params, "Edit documents by function");
index_scheduler
.features()
@@ -1424,23 +1387,23 @@ pub async fn edit_documents_by_function(
let index_uid = IndexUid::try_from(index_uid.into_inner())?;
let index_uid = index_uid.into_inner();
let body = body.into_inner();
let params = params.into_inner();
analytics.publish(
EditDocumentsByFunctionAggregator {
filtered: body.filter.is_some(),
with_context: body.context.is_some(),
filtered: params.filter.is_some(),
with_context: params.context.is_some(),
index_creation: index_scheduler.index(&index_uid).is_err(),
},
&req,
);
let engine = milli::rhai::Engine::new();
if let Err(e) = engine.compile(&body.function) {
if let Err(e) = engine.compile(&params.function) {
return Err(ResponseError::from_msg(e.to_string(), Code::BadRequest));
}
if let Some(ref filter) = body.filter {
if let Some(ref filter) = params.filter {
// we ensure the filter is well formed before enqueuing it
crate::search::parse_filter(
filter,
@@ -1451,8 +1414,8 @@ pub async fn edit_documents_by_function(
}
let task = KindWithContent::DocumentEdition {
index_uid: index_uid.clone(),
filter_expr: body.filter.clone(),
context: match body.context.clone() {
filter_expr: params.filter.clone(),
context: match params.context.clone() {
Some(Value::Object(m)) => Some(m),
None => None,
_ => {
@@ -1462,21 +1425,18 @@ pub async fn edit_documents_by_function(
))
}
},
function: body.function.clone(),
function: params.function.clone(),
};
let uid = get_task_id(&req, &opt)?;
let dry_run = is_dry_run(&req, &opt)?;
let task = {
let index_scheduler = index_scheduler.clone();
tokio::task::spawn_blocking(move || {
index_scheduler.register_with_custom_metadata(task, uid, custom_metadata, dry_run)
})
.await??
tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run)).await??
};
if network.sharding() && !dry_run {
proxy(&index_scheduler, &index_uid, &req, network, Body::Inline(body), &task).await?;
if network.sharding && !dry_run {
proxy(&index_scheduler, &index_uid, &req, network, Body::Inline(params), &task).await?;
}
let task: SummarizedTaskView = task.into();
@@ -1517,14 +1477,12 @@ pub async fn edit_documents_by_function(
pub async fn clear_all_documents(
index_scheduler: GuardedData<ActionPolicy<{ actions::DOCUMENTS_DELETE }>, Data<IndexScheduler>>,
index_uid: web::Path<String>,
params: AwebQueryParameter<CustomMetadataQuery, DeserrQueryParamError>,
req: HttpRequest,
opt: web::Data<Opt>,
analytics: web::Data<Analytics>,
) -> Result<HttpResponse, ResponseError> {
let index_uid = IndexUid::try_from(index_uid.into_inner())?;
let network = index_scheduler.network();
let CustomMetadataQuery { custom_metadata } = params.into_inner();
analytics.publish(
DocumentsDeletionAggregator {
@@ -1543,13 +1501,10 @@ pub async fn clear_all_documents(
let task = {
let index_scheduler = index_scheduler.clone();
tokio::task::spawn_blocking(move || {
index_scheduler.register_with_custom_metadata(task, uid, custom_metadata, dry_run)
})
.await??
tokio::task::spawn_blocking(move || index_scheduler.register(task, uid, dry_run)).await??
};
if network.sharding() && !dry_run {
if network.sharding && !dry_run {
proxy(&index_scheduler, &index_uid, &req, network, Body::none(), &task).await?;
}

View File

@@ -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> {

View File

@@ -343,7 +343,6 @@ impl From<FacetSearchQuery> for SearchQuery {
hybrid,
ranking_score_threshold,
locales,
personalize: None,
}
}
}

View File

@@ -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(

View File

@@ -24,9 +24,9 @@ use crate::metrics::MEILISEARCH_DEGRADED_SEARCH_REQUESTS;
use crate::routes::indexes::search_analytics::{SearchAggregator, SearchGET, SearchPOST};
use crate::routes::parse_include_metadata_header;
use crate::search::{
add_search_rules, perform_search, HybridQuery, MatchingStrategy, Personalize,
RankingScoreThreshold, RetrieveVectors, SearchKind, SearchParams, SearchQuery, SearchResult,
SemanticRatio, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
add_search_rules, perform_search, HybridQuery, MatchingStrategy, RankingScoreThreshold,
RetrieveVectors, SearchKind, SearchParams, SearchQuery, SearchResult, SemanticRatio,
DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT, DEFAULT_SEARCH_OFFSET, DEFAULT_SEMANTIC_RATIO,
};
use crate::search_queue::SearchQueue;
@@ -134,8 +134,6 @@ pub struct SearchQueryGet {
#[deserr(default, error = DeserrQueryParamError<InvalidSearchLocales>)]
#[param(value_type = Vec<Locale>, explode = false)]
pub locales: Option<CS<Locale>>,
#[deserr(default, error = DeserrQueryParamError<InvalidSearchPersonalizeUserContext>)]
pub personalize_user_context: Option<String>,
}
#[derive(Debug, Clone, Copy, PartialEq, deserr::Deserr)]
@@ -207,9 +205,6 @@ impl TryFrom<SearchQueryGet> for SearchQuery {
));
}
let personalize =
other.personalize_user_context.map(|user_context| Personalize { user_context });
Ok(Self {
q: other.q,
// `media` not supported for `GET`
@@ -239,7 +234,6 @@ impl TryFrom<SearchQueryGet> for SearchQuery {
hybrid,
ranking_score_threshold: other.ranking_score_threshold.map(|o| o.0),
locales: other.locales.map(|o| o.into_iter().collect()),
personalize,
})
}
}
@@ -328,7 +322,6 @@ pub fn fix_sort_query_parameters(sort_query: &str) -> Vec<String> {
pub async fn search_with_url_query(
index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
search_queue: web::Data<SearchQueue>,
personalization_service: web::Data<crate::personalization::PersonalizationService>,
index_uid: web::Path<String>,
params: AwebQueryParameter<SearchQueryGet, DeserrQueryParamError>,
req: HttpRequest,
@@ -349,16 +342,9 @@ pub async fn search_with_url_query(
let index = index_scheduler.index(&index_uid)?;
// Extract personalization and query string before moving query
let personalize = query.personalize.take();
let search_kind =
search_kind(&query, index_scheduler.get_ref(), index_uid.to_string(), &index)?;
let retrieve_vector = RetrieveVectors::new(query.retrieve_vectors);
// Save the query string for personalization if requested
let personalize_query = personalize.is_some().then(|| query.q.clone()).flatten();
let permit = search_queue.try_get_search_permit().await?;
let include_metadata = parse_include_metadata_header(&req);
@@ -379,24 +365,12 @@ pub async fn search_with_url_query(
.await;
permit.drop().await;
let search_result = search_result?;
if let Ok((search_result, _)) = search_result.as_ref() {
if let Ok(ref search_result) = search_result {
aggregate.succeed(search_result);
}
analytics.publish(aggregate, &req);
let (mut search_result, time_budget) = search_result?;
// Apply personalization if requested
if let Some(personalize) = personalize.as_ref() {
search_result = personalization_service
.rerank_search_results(
search_result,
personalize,
personalize_query.as_deref(),
time_budget,
)
.await?;
}
let search_result = search_result?;
debug!(request_uid = ?request_uid, returns = ?search_result, "Search get");
Ok(HttpResponse::Ok().json(search_result))
@@ -461,7 +435,6 @@ pub async fn search_with_url_query(
pub async fn search_with_post(
index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
search_queue: web::Data<SearchQueue>,
personalization_service: web::Data<crate::personalization::PersonalizationService>,
index_uid: web::Path<String>,
params: AwebJson<SearchQuery, DeserrJsonError>,
req: HttpRequest,
@@ -482,18 +455,12 @@ pub async fn search_with_post(
let index = index_scheduler.index(&index_uid)?;
// Extract personalization and query string before moving query
let personalize = query.personalize.take();
let search_kind =
search_kind(&query, index_scheduler.get_ref(), index_uid.to_string(), &index)?;
let retrieve_vectors = RetrieveVectors::new(query.retrieve_vectors);
let include_metadata = parse_include_metadata_header(&req);
// Save the query string for personalization if requested
let personalize_query = personalize.is_some().then(|| query.q.clone()).flatten();
let permit = search_queue.try_get_search_permit().await?;
let search_result = tokio::task::spawn_blocking(move || {
perform_search(
@@ -512,7 +479,7 @@ pub async fn search_with_post(
.await;
permit.drop().await;
let search_result = search_result?;
if let Ok((ref search_result, _)) = search_result {
if let Ok(ref search_result) = search_result {
aggregate.succeed(search_result);
if search_result.degraded {
MEILISEARCH_DEGRADED_SEARCH_REQUESTS.inc();
@@ -520,19 +487,7 @@ pub async fn search_with_post(
}
analytics.publish(aggregate, &req);
let (mut search_result, time_budget) = search_result?;
// Apply personalization if requested
if let Some(personalize) = personalize.as_ref() {
search_result = personalization_service
.rerank_search_results(
search_result,
personalize,
personalize_query.as_deref(),
time_budget,
)
.await?;
}
let search_result = search_result?;
debug!(request_uid = ?request_uid, returns = ?search_result, "Search post");
Ok(HttpResponse::Ok().json(search_result))

View File

@@ -7,7 +7,6 @@ use serde_json::{json, Value};
use crate::aggregate_methods;
use crate::analytics::{Aggregate, AggregateMethod};
use crate::metrics::MEILISEARCH_PERSONALIZED_SEARCH_REQUESTS;
use crate::search::{
SearchQuery, SearchResult, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
@@ -96,9 +95,6 @@ pub struct SearchAggregator<Method: AggregateMethod> {
show_ranking_score_details: bool,
ranking_score_threshold: bool,
// personalization
total_personalized: usize,
marker: std::marker::PhantomData<Method>,
}
@@ -133,7 +129,6 @@ impl<Method: AggregateMethod> SearchAggregator<Method> {
hybrid,
ranking_score_threshold,
locales,
personalize,
} = query;
let mut ret = Self::default();
@@ -209,12 +204,6 @@ impl<Method: AggregateMethod> SearchAggregator<Method> {
ret.locales = locales.iter().copied().collect();
}
// personalization
if personalize.is_some() {
ret.total_personalized = 1;
MEILISEARCH_PERSONALIZED_SEARCH_REQUESTS.inc();
}
ret.highlight_pre_tag = *highlight_pre_tag != DEFAULT_HIGHLIGHT_PRE_TAG();
ret.highlight_post_tag = *highlight_post_tag != DEFAULT_HIGHLIGHT_POST_TAG();
ret.crop_marker = *crop_marker != DEFAULT_CROP_MARKER();
@@ -307,7 +296,6 @@ impl<Method: AggregateMethod> Aggregate for SearchAggregator<Method> {
total_used_negative_operator,
ranking_score_threshold,
mut locales,
total_personalized,
marker: _,
} = *new;
@@ -393,9 +381,6 @@ impl<Method: AggregateMethod> Aggregate for SearchAggregator<Method> {
// locales
self.locales.append(&mut locales);
// personalization
self.total_personalized = self.total_personalized.saturating_add(total_personalized);
self
}
@@ -441,7 +426,6 @@ impl<Method: AggregateMethod> Aggregate for SearchAggregator<Method> {
total_used_negative_operator,
ranking_score_threshold,
locales,
total_personalized,
marker: _,
} = *self;
@@ -515,9 +499,6 @@ impl<Method: AggregateMethod> Aggregate for SearchAggregator<Method> {
"show_ranking_score_details": show_ranking_score_details,
"ranking_score_threshold": ranking_score_threshold,
},
"personalization": {
"total_personalized": total_personalized,
},
})
}
}

View File

@@ -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());
}

View File

@@ -41,9 +41,7 @@ use crate::routes::indexes::IndexView;
use crate::routes::multi_search::SearchResults;
use crate::routes::network::{Network, Remote};
use crate::routes::swap_indexes::SwapIndexesPayload;
use crate::routes::webhooks::{
WebhookResults, WebhookSettings, WebhookWithMetadataRedactedAuthorization,
};
use crate::routes::webhooks::{WebhookResults, WebhookSettings, WebhookWithMetadata};
use crate::search::{
FederatedSearch, FederatedSearchResult, Federation, FederationOptions, MergeFacets,
SearchQueryWithIndex, SearchResultWithIndex, SimilarQuery, SimilarResult,
@@ -105,7 +103,7 @@ mod webhooks;
url = "/",
description = "Local server",
)),
components(schemas(PaginationView<KeyView>, PaginationView<IndexView>, IndexView, DocumentDeletionByFilter, AllBatches, BatchStats, ProgressStepView, ProgressView, BatchView, RuntimeTogglableFeatures, SwapIndexesPayload, DocumentEditionByFunction, MergeFacets, FederationOptions, SearchQueryWithIndex, Federation, FederatedSearch, FederatedSearchResult, SearchResults, SearchResultWithIndex, SimilarQuery, SimilarResult, PaginationView<serde_json::Value>, BrowseQuery, UpdateIndexRequest, IndexUid, IndexCreateRequest, KeyView, Action, CreateApiKey, UpdateStderrLogs, LogMode, GetLogs, IndexStats, Stats, HealthStatus, HealthResponse, VersionResponse, Code, ErrorType, AllTasks, TaskView, Status, DetailsView, ResponseError, Settings<Unchecked>, Settings<Checked>, TypoSettings, MinWordSizeTyposSetting, FacetingSettings, PaginationSettings, SummarizedTaskView, Kind, Network, Remote, FilterableAttributesRule, FilterableAttributesPatterns, AttributePatterns, FilterableAttributesFeatures, FilterFeatures, Export, WebhookSettings, WebhookResults, WebhookWithMetadataRedactedAuthorization, meilisearch_types::milli::vector::VectorStoreBackend))
components(schemas(PaginationView<KeyView>, PaginationView<IndexView>, IndexView, DocumentDeletionByFilter, AllBatches, BatchStats, ProgressStepView, ProgressView, BatchView, RuntimeTogglableFeatures, SwapIndexesPayload, DocumentEditionByFunction, MergeFacets, FederationOptions, SearchQueryWithIndex, Federation, FederatedSearch, FederatedSearchResult, SearchResults, SearchResultWithIndex, SimilarQuery, SimilarResult, PaginationView<serde_json::Value>, BrowseQuery, UpdateIndexRequest, IndexUid, IndexCreateRequest, KeyView, Action, CreateApiKey, UpdateStderrLogs, LogMode, GetLogs, IndexStats, Stats, HealthStatus, HealthResponse, VersionResponse, Code, ErrorType, AllTasks, TaskView, Status, DetailsView, ResponseError, Settings<Unchecked>, Settings<Checked>, TypoSettings, MinWordSizeTyposSetting, FacetingSettings, PaginationSettings, SummarizedTaskView, Kind, Network, Remote, FilterableAttributesRule, FilterableAttributesPatterns, AttributePatterns, FilterableAttributesFeatures, FilterFeatures, Export, WebhookSettings, WebhookResults, WebhookWithMetadata, meilisearch_types::milli::vector::VectorStoreBackend))
)]
pub struct MeilisearchApi;
@@ -218,8 +216,6 @@ pub struct SummarizedTaskView {
deserialize_with = "time::serde::rfc3339::deserialize"
)]
enqueued_at: OffsetDateTime,
#[serde(default, skip_serializing_if = "Option::is_none")]
custom_metadata: Option<String>,
}
impl From<Task> for SummarizedTaskView {
@@ -230,7 +226,6 @@ impl From<Task> for SummarizedTaskView {
status: task.status,
kind: task.kind.as_kind(),
enqueued_at: task.enqueued_at,
custom_metadata: task.custom_metadata,
}
}
}

View File

@@ -146,7 +146,6 @@ pub struct SearchResults {
pub async fn multi_search_with_post(
index_scheduler: GuardedData<ActionPolicy<{ actions::SEARCH }>, Data<IndexScheduler>>,
search_queue: Data<SearchQueue>,
personalization_service: web::Data<crate::personalization::PersonalizationService>,
params: AwebJson<FederatedSearch, DeserrJsonError>,
req: HttpRequest,
analytics: web::Data<Analytics>,
@@ -237,7 +236,7 @@ pub async fn multi_search_with_post(
// changes.
let search_results: Result<_, (ResponseError, usize)> = async {
let mut search_results = Vec::with_capacity(queries.len());
for (query_index, (index_uid, mut query, federation_options)) in queries
for (query_index, (index_uid, query, federation_options)) in queries
.into_iter()
.map(SearchQueryWithIndex::into_index_query_federation)
.enumerate()
@@ -270,13 +269,6 @@ pub async fn multi_search_with_post(
})
.with_index(query_index)?;
// Extract personalization and query string before moving query
let personalize = query.personalize.take();
// Save the query string for personalization if requested
let personalize_query =
personalize.is_some().then(|| query.q.clone()).flatten();
let index_uid_str = index_uid.to_string();
let search_kind = search_kind(
@@ -288,7 +280,7 @@ pub async fn multi_search_with_post(
.with_index(query_index)?;
let retrieve_vector = RetrieveVectors::new(query.retrieve_vectors);
let (mut search_result, time_budget) = tokio::task::spawn_blocking(move || {
let search_result = tokio::task::spawn_blocking(move || {
perform_search(
SearchParams {
index_uid: index_uid_str.clone(),
@@ -303,25 +295,11 @@ pub async fn multi_search_with_post(
)
})
.await
.with_index(query_index)?
.with_index(query_index)?;
// Apply personalization if requested
if let Some(personalize) = personalize.as_ref() {
search_result = personalization_service
.rerank_search_results(
search_result,
personalize,
personalize_query.as_deref(),
time_budget,
)
.await
.with_index(query_index)?;
}
search_results.push(SearchResultWithIndex {
index_uid: index_uid.into_inner(),
result: search_result,
result: search_result.with_index(query_index)?,
});
}
Ok(search_results)

View File

@@ -67,7 +67,6 @@ impl MultiSearchAggregator {
hybrid: _,
ranking_score_threshold: _,
locales: _,
personalize: _,
} in &federated_search.queries
{
if let Some(federation_options) = federation_options {

View File

@@ -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))

View File

@@ -90,7 +90,7 @@ fn deny_immutable_fields_webhook(
#[derive(Debug, Serialize, ToSchema)]
#[serde(rename_all = "camelCase")]
#[schema(rename_all = "camelCase")]
pub(super) struct WebhookWithMetadataRedactedAuthorization {
pub(super) struct WebhookWithMetadata {
uuid: Uuid,
is_editable: bool,
#[schema(value_type = WebhookSettings)]
@@ -98,9 +98,8 @@ pub(super) struct WebhookWithMetadataRedactedAuthorization {
webhook: Webhook,
}
impl WebhookWithMetadataRedactedAuthorization {
pub fn from(uuid: Uuid, mut webhook: Webhook) -> Self {
webhook.redact_authorization_header();
impl WebhookWithMetadata {
pub fn from(uuid: Uuid, webhook: Webhook) -> Self {
Self { uuid, is_editable: uuid != Uuid::nil(), webhook }
}
}
@@ -108,7 +107,7 @@ impl WebhookWithMetadataRedactedAuthorization {
#[derive(Debug, Serialize, ToSchema)]
#[serde(rename_all = "camelCase")]
pub(super) struct WebhookResults {
results: Vec<WebhookWithMetadataRedactedAuthorization>,
results: Vec<WebhookWithMetadata>,
}
#[utoipa::path(
@@ -151,7 +150,7 @@ async fn get_webhooks(
let results = webhooks
.webhooks
.into_iter()
.map(|(uuid, webhook)| WebhookWithMetadataRedactedAuthorization::from(uuid, webhook))
.map(|(uuid, webhook)| WebhookWithMetadata::from(uuid, webhook))
.collect::<Vec<_>>();
let results = WebhookResults { results };
@@ -302,7 +301,7 @@ fn check_changed(uuid: Uuid, webhook: &Webhook) -> Result<(), WebhooksError> {
tag = "Webhooks",
security(("Bearer" = ["webhooks.get", "webhooks.*", "*.get", "*"])),
responses(
(status = 200, description = "Webhook found", body = WebhookWithMetadataRedactedAuthorization, content_type = "application/json", example = json!({
(status = 200, description = "Webhook found", body = WebhookWithMetadata, content_type = "application/json", example = json!({
"uuid": "550e8400-e29b-41d4-a716-446655440000",
"url": "https://your.site/on-tasks-completed",
"headers": {
@@ -325,7 +324,7 @@ async fn get_webhook(
let mut webhooks = index_scheduler.webhooks_view();
let webhook = webhooks.webhooks.remove(&uuid).ok_or(WebhookNotFound(uuid))?;
let webhook = WebhookWithMetadataRedactedAuthorization::from(uuid, webhook);
let webhook = WebhookWithMetadata::from(uuid, webhook);
debug!(returns = ?webhook, "Get webhook");
Ok(HttpResponse::Ok().json(webhook))
@@ -338,7 +337,7 @@ async fn get_webhook(
request_body = WebhookSettings,
security(("Bearer" = ["webhooks.create", "webhooks.*", "*"])),
responses(
(status = 201, description = "Webhook created successfully", body = WebhookWithMetadataRedactedAuthorization, content_type = "application/json", example = json!({
(status = 201, description = "Webhook created successfully", body = WebhookWithMetadata, content_type = "application/json", example = json!({
"uuid": "550e8400-e29b-41d4-a716-446655440000",
"url": "https://your.site/on-tasks-completed",
"headers": {
@@ -384,7 +383,7 @@ async fn post_webhook(
analytics.publish(PostWebhooksAnalytics, &req);
let response = WebhookWithMetadataRedactedAuthorization::from(uuid, webhook);
let response = WebhookWithMetadata::from(uuid, webhook);
debug!(returns = ?response, "Post webhook");
Ok(HttpResponse::Created().json(response))
}
@@ -396,7 +395,7 @@ async fn post_webhook(
request_body = WebhookSettings,
security(("Bearer" = ["webhooks.update", "webhooks.*", "*"])),
responses(
(status = 200, description = "Webhook updated successfully", body = WebhookWithMetadataRedactedAuthorization, content_type = "application/json", example = json!({
(status = 200, description = "Webhook updated successfully", body = WebhookWithMetadata, content_type = "application/json", example = json!({
"uuid": "550e8400-e29b-41d4-a716-446655440000",
"url": "https://your.site/on-tasks-completed",
"headers": {
@@ -436,7 +435,7 @@ async fn patch_webhook(
analytics.publish(PatchWebhooksAnalytics, &req);
let response = WebhookWithMetadataRedactedAuthorization::from(uuid, webhook);
let response = WebhookWithMetadata::from(uuid, webhook);
debug!(returns = ?response, "Patch webhook");
Ok(HttpResponse::Ok().json(response))
}

View File

@@ -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;
@@ -601,10 +601,6 @@ impl PartitionedQueries {
.into());
}
if federated_query.has_personalize() {
return Err(MeilisearchHttpError::PersonalizationInFederatedQuery(query_index).into());
}
let (index_uid, query, federation_options) = federated_query.into_index_query_federation();
let federation_options = federation_options.unwrap_or_default();

View File

@@ -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;

View File

@@ -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;

View File

@@ -59,13 +59,6 @@ pub const DEFAULT_HIGHLIGHT_POST_TAG: fn() -> String = || "</em>".to_string();
pub const DEFAULT_SEMANTIC_RATIO: fn() -> SemanticRatio = || SemanticRatio(0.5);
pub const INCLUDE_METADATA_HEADER: &str = "Meili-Include-Metadata";
#[derive(Clone, Default, PartialEq, Deserr, ToSchema, Debug)]
#[deserr(error = DeserrJsonError<InvalidSearchPersonalize>, rename_all = camelCase, deny_unknown_fields)]
pub struct Personalize {
#[deserr(error = DeserrJsonError<InvalidSearchPersonalizeUserContext>)]
pub user_context: String,
}
#[derive(Clone, Default, PartialEq, Deserr, ToSchema)]
#[deserr(error = DeserrJsonError, rename_all = camelCase, deny_unknown_fields)]
pub struct SearchQuery {
@@ -129,8 +122,6 @@ pub struct SearchQuery {
pub ranking_score_threshold: Option<RankingScoreThreshold>,
#[deserr(default, error = DeserrJsonError<InvalidSearchLocales>)]
pub locales: Option<Vec<Locale>>,
#[deserr(default, error = DeserrJsonError<InvalidSearchPersonalize>, default)]
pub personalize: Option<Personalize>,
}
impl From<SearchParameters> for SearchQuery {
@@ -178,7 +169,6 @@ impl From<SearchParameters> for SearchQuery {
highlight_post_tag: DEFAULT_HIGHLIGHT_POST_TAG(),
crop_marker: DEFAULT_CROP_MARKER(),
locales: None,
personalize: None,
}
}
}
@@ -260,7 +250,6 @@ impl fmt::Debug for SearchQuery {
attributes_to_search_on,
ranking_score_threshold,
locales,
personalize,
} = self;
let mut debug = f.debug_struct("SearchQuery");
@@ -349,10 +338,6 @@ impl fmt::Debug for SearchQuery {
debug.field("locales", &locales);
}
if let Some(personalize) = personalize {
debug.field("personalize", &personalize);
}
debug.finish()
}
}
@@ -558,9 +543,6 @@ pub struct SearchQueryWithIndex {
pub ranking_score_threshold: Option<RankingScoreThreshold>,
#[deserr(default, error = DeserrJsonError<InvalidSearchLocales>, default)]
pub locales: Option<Vec<Locale>>,
#[deserr(default, error = DeserrJsonError<InvalidSearchPersonalize>, default)]
#[serde(skip)]
pub personalize: Option<Personalize>,
#[deserr(default)]
pub federation_options: Option<FederationOptions>,
@@ -585,10 +567,6 @@ impl SearchQueryWithIndex {
self.facets.as_deref().filter(|v| !v.is_empty())
}
pub fn has_personalize(&self) -> bool {
self.personalize.is_some()
}
pub fn from_index_query_federation(
index_uid: IndexUid,
query: SearchQuery,
@@ -622,7 +600,6 @@ impl SearchQueryWithIndex {
attributes_to_search_on,
ranking_score_threshold,
locales,
personalize,
} = query;
SearchQueryWithIndex {
@@ -654,7 +631,6 @@ impl SearchQueryWithIndex {
attributes_to_search_on,
ranking_score_threshold,
locales,
personalize,
federation_options,
}
}
@@ -690,7 +666,6 @@ impl SearchQueryWithIndex {
hybrid,
ranking_score_threshold,
locales,
personalize,
} = self;
(
index_uid,
@@ -722,7 +697,6 @@ impl SearchQueryWithIndex {
hybrid,
ranking_score_threshold,
locales,
personalize,
// do not use ..Default::default() here,
// rather add any missing field from `SearchQuery` to `SearchQueryWithIndex`
},
@@ -1175,10 +1149,7 @@ pub struct SearchParams {
pub include_metadata: bool,
}
pub fn perform_search(
params: SearchParams,
index: &Index,
) -> Result<(SearchResult, TimeBudget), ResponseError> {
pub fn perform_search(params: SearchParams, index: &Index) -> Result<SearchResult, ResponseError> {
let SearchParams {
index_uid,
query,
@@ -1197,7 +1168,7 @@ pub fn perform_search(
};
let (search, is_finite_pagination, max_total_hits, offset) =
prepare_search(index, &rtxn, &query, &search_kind, time_budget.clone(), features)?;
prepare_search(index, &rtxn, &query, &search_kind, time_budget, features)?;
let (
milli::SearchResult {
@@ -1255,7 +1226,6 @@ pub fn perform_search(
attributes_to_search_on: _,
filter: _,
distinct: _,
personalize: _,
} = query;
let format = AttributesFormat {
@@ -1321,7 +1291,7 @@ pub fn perform_search(
request_uid: Some(request_uid),
metadata,
};
Ok((result, time_budget))
Ok(result)
}
#[derive(Debug, Clone, Default, Serialize, Deserialize, ToSchema)]

View File

@@ -91,16 +91,7 @@ impl<'a> Index<'a, Owned> {
documents: Value,
primary_key: Option<&str>,
) -> (Value, StatusCode) {
self._add_documents(documents, primary_key, None).await
}
pub async fn add_documents_with_custom_metadata(
&self,
documents: Value,
primary_key: Option<&str>,
custom_metadata: Option<&str>,
) -> (Value, StatusCode) {
self._add_documents(documents, primary_key, custom_metadata).await
self._add_documents(documents, primary_key).await
}
pub async fn raw_add_documents(
@@ -361,25 +352,12 @@ impl<State> Index<'_, State> {
&self,
documents: Value,
primary_key: Option<&str>,
custom_metadata: Option<&str>,
) -> (Value, StatusCode) {
let url = match (primary_key, custom_metadata) {
(Some(key), Some(meta)) => {
format!(
"/indexes/{}/documents?primaryKey={key}&customMetadata={meta}",
urlencode(self.uid.as_ref()),
)
let url = match primary_key {
Some(key) => {
format!("/indexes/{}/documents?primaryKey={}", urlencode(self.uid.as_ref()), key)
}
(None, Some(meta)) => {
format!(
"/indexes/{}/documents?&customMetadata={meta}",
urlencode(self.uid.as_ref()),
)
}
(Some(key), None) => {
format!("/indexes/{}/documents?&primaryKey={key}", urlencode(self.uid.as_ref()),)
}
(None, None) => format!("/indexes/{}/documents", urlencode(self.uid.as_ref())),
None => format!("/indexes/{}/documents", urlencode(self.uid.as_ref())),
};
self.service.post_encoded(url, documents, self.encoder).await
}

View File

@@ -241,7 +241,7 @@ pub async fn shared_index_with_documents() -> &'static Index<'static, Shared> {
let server = Server::new_shared();
let index = server._index("SHARED_DOCUMENTS").to_shared();
let documents = DOCUMENTS.clone();
let (response, _code) = index._add_documents(documents, None, None).await;
let (response, _code) = index._add_documents(documents, None).await;
server.wait_task(response.uid()).await.succeeded();
let (response, _code) = index
._update_settings(
@@ -284,7 +284,7 @@ pub async fn shared_index_with_score_documents() -> &'static Index<'static, Shar
let server = Server::new_shared();
let index = server._index("SHARED_SCORE_DOCUMENTS").to_shared();
let documents = SCORE_DOCUMENTS.clone();
let (response, _code) = index._add_documents(documents, None, None).await;
let (response, _code) = index._add_documents(documents, None).await;
server.wait_task(response.uid()).await.succeeded();
let (response, _code) = index
._update_settings(
@@ -361,7 +361,7 @@ pub async fn shared_index_with_nested_documents() -> &'static Index<'static, Sha
let server = Server::new_shared();
let index = server._index("SHARED_NESTED_DOCUMENTS").to_shared();
let documents = NESTED_DOCUMENTS.clone();
let (response, _code) = index._add_documents(documents, None, None).await;
let (response, _code) = index._add_documents(documents, None).await;
server.wait_task(response.uid()).await.succeeded();
let (response, _code) = index
._update_settings(
@@ -508,7 +508,7 @@ pub async fn shared_index_with_geo_documents() -> &'static Index<'static, Shared
.get_or_init(|| async {
let server = Server::new_shared();
let index = server._index("SHARED_GEO_DOCUMENTS").to_shared();
let (response, _code) = index._add_documents(GEO_DOCUMENTS.clone(), None, None).await;
let (response, _code) = index._add_documents(GEO_DOCUMENTS.clone(), None).await;
server.wait_task(response.uid()).await.succeeded();
let (response, _code) = index
@@ -531,7 +531,7 @@ pub async fn shared_index_geojson_documents() -> &'static Index<'static, Shared>
let index = server._index("SHARED_GEOJSON_DOCUMENTS").to_shared();
let countries = include_str!("../documents/geojson/assets/countries.json");
let lille = serde_json::from_str::<serde_json::Value>(countries).unwrap();
let (response, _code) = index._add_documents(Value(lille), Some("name"), None).await;
let (response, _code) = index._add_documents(Value(lille), Some("name")).await;
server.wait_task(response.uid()).await.succeeded();
let (response, _code) =

View File

@@ -10,9 +10,8 @@ use actix_web::test::TestRequest;
use actix_web::web::Data;
use index_scheduler::IndexScheduler;
use meilisearch::analytics::Analytics;
use meilisearch::personalization::PersonalizationService;
use meilisearch::search_queue::SearchQueue;
use meilisearch::{create_app, Opt, ServicesData, SubscriberForSecondLayer};
use meilisearch::{create_app, Opt, SubscriberForSecondLayer};
use meilisearch_auth::AuthController;
use tracing::level_filters::LevelFilter;
use tracing_subscriber::Layer;
@@ -136,24 +135,14 @@ impl Service {
self.options.experimental_search_queue_size,
NonZeroUsize::new(1).unwrap(),
);
let personalization_service = self
.options
.experimental_personalization_api_key
.clone()
.map(PersonalizationService::cohere)
.unwrap_or_else(PersonalizationService::disabled);
actix_web::test::init_service(create_app(
ServicesData {
index_scheduler: self.index_scheduler.clone().into(),
auth: self.auth.clone().into(),
search_queue: Data::new(search_queue),
personalization_service: Data::new(personalization_service),
logs_route_handle: Data::new(route_layer_handle),
logs_stderr_handle: Data::new(stderr_layer_handle),
analytics: Data::new(Analytics::no_analytics()),
},
self.index_scheduler.clone().into(),
self.auth.clone().into(),
Data::new(search_queue),
self.options.clone(),
(route_layer_handle, stderr_layer_handle),
Data::new(Analytics::no_analytics()),
true,
))
.await

View File

@@ -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
}
"###);
}

View File

@@ -207,118 +207,3 @@ async fn errors() {
}
"###);
}
#[actix_rt::test]
async fn search_with_personalization_without_enabling_the_feature() {
let server = Server::new().await;
let index = server.unique_index();
// Create the index and add some documents
let (task, _code) = index.create(None).await;
server.wait_task(task.uid()).await.succeeded();
let (task, _code) = index
.add_documents(
json!([
{"id": 1, "title": "The Dark Knight", "genre": "Action"},
{"id": 2, "title": "Inception", "genre": "Sci-Fi"},
{"id": 3, "title": "The Matrix", "genre": "Sci-Fi"}
]),
None,
)
.await;
server.wait_task(task.uid()).await.succeeded();
// Try to search with personalization - should return feature_not_enabled error
let (response, code) = index
.search_post(json!({
"q": "movie",
"personalize": {
"userContext": "I love science fiction movies"
}
}))
.await;
meili_snap::snapshot!(code, @"400 Bad Request");
meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
{
"message": "reranking search results requires enabling the `personalization` experimental feature. See https://github.com/orgs/meilisearch/discussions/866",
"code": "feature_not_enabled",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#feature_not_enabled"
}
"###);
}
#[actix_rt::test]
async fn multi_search_with_personalization_without_enabling_the_feature() {
let server = Server::new().await;
let index = server.unique_index();
// Create the index and add some documents
let (task, _code) = index.create(None).await;
server.wait_task(task.uid()).await.succeeded();
let (task, _code) = index
.add_documents(
json!([
{"id": 1, "title": "The Dark Knight", "genre": "Action"},
{"id": 2, "title": "Inception", "genre": "Sci-Fi"},
{"id": 3, "title": "The Matrix", "genre": "Sci-Fi"}
]),
None,
)
.await;
server.wait_task(task.uid()).await.succeeded();
// Try to multi-search with personalization - should return feature_not_enabled error
let (response, code) = server
.multi_search(json!({
"queries": [
{
"indexUid": index.uid,
"q": "movie",
"personalize": {
"userContext": "I love science fiction movies"
}
}
]
}))
.await;
meili_snap::snapshot!(code, @"400 Bad Request");
meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
{
"message": "Inside `.queries[0]`: reranking search results requires enabling the `personalization` experimental feature. See https://github.com/orgs/meilisearch/discussions/866",
"code": "feature_not_enabled",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#feature_not_enabled"
}
"###);
// Try to federated search with personalization - should return feature_not_enabled error
let (response, code) = server
.multi_search(json!({
"federation": {},
"queries": [
{
"indexUid": index.uid,
"q": "movie",
"personalize": {
"userContext": "I love science fiction movies"
}
}
]
}))
.await;
meili_snap::snapshot!(code, @"400 Bad Request");
meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
{
"message": "Inside `.queries[0]`: Using `.personalize` is not allowed in federated queries.\n - Hint: remove `personalize` from query #0 or remove `federation` from the request",
"code": "invalid_multi_search_query_personalization",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_multi_search_query_personalization"
}
"###);
}

View File

@@ -8,9 +8,8 @@ use actix_web::http::header::ContentType;
use actix_web::web::Data;
use meili_snap::snapshot;
use meilisearch::analytics::Analytics;
use meilisearch::personalization::PersonalizationService;
use meilisearch::search_queue::SearchQueue;
use meilisearch::{create_app, Opt, ServicesData, SubscriberForSecondLayer};
use meilisearch::{create_app, Opt, SubscriberForSecondLayer};
use tracing::level_filters::LevelFilter;
use tracing_subscriber::layer::SubscriberExt;
use tracing_subscriber::Layer;
@@ -51,16 +50,12 @@ async fn basic_test_log_stream_route() {
);
let app = actix_web::test::init_service(create_app(
ServicesData {
index_scheduler: server.service.index_scheduler.clone().into(),
auth: server.service.auth.clone().into(),
search_queue: Data::new(search_queue),
personalization_service: Data::new(PersonalizationService::disabled()),
logs_route_handle: Data::new(route_layer_handle),
logs_stderr_handle: Data::new(stderr_layer_handle),
analytics: Data::new(Analytics::no_analytics()),
},
server.service.index_scheduler.clone().into(),
server.service.auth.clone().into(),
Data::new(search_queue),
server.service.options.clone(),
(route_layer_handle, stderr_layer_handle),
Data::new(Analytics::no_analytics()),
true,
))
.await;

View File

@@ -1,11 +1,7 @@
use meili_snap::*;
use meilisearch::Opt;
use tempfile::TempDir;
use super::test_settings_documents_indexing_swapping_and_search;
use crate::common::{
default_settings, shared_does_not_exists_index, Server, DOCUMENTS, NESTED_DOCUMENTS,
};
use crate::common::{shared_does_not_exists_index, Server, DOCUMENTS, NESTED_DOCUMENTS};
use crate::json;
#[actix_rt::test]
@@ -1324,98 +1320,3 @@ async fn search_with_contains_without_enabling_the_feature() {
}
"#);
}
#[actix_rt::test]
#[ignore]
async fn search_with_personalization_invalid_api_key() {
// Create a server with a fake personalization API key
let dir = TempDir::new().unwrap();
let options = Opt {
experimental_personalization_api_key: Some("fake-api-key-12345".to_string()),
..default_settings(dir.path())
};
let server = Server::new_with_options(options).await.unwrap();
let index = server.unique_index();
// Create the index and add some documents
let (task, _code) = index.create(None).await;
server.wait_task(task.uid()).await.succeeded();
let (task, _code) = index
.add_documents(
json!([
{"id": 1, "title": "The Dark Knight", "genre": "Action"},
{"id": 2, "title": "Inception", "genre": "Sci-Fi"},
{"id": 3, "title": "The Matrix", "genre": "Sci-Fi"}
]),
None,
)
.await;
server.wait_task(task.uid()).await.succeeded();
// Try to search with personalization - should return remote_invalid_api_key error
let (response, code) = index
.search_post(json!({
"q": "the",
"personalize": {
"userContext": "I love science fiction movies"
}
}))
.await;
snapshot!(code, @"403 Forbidden");
snapshot!(json_string!(response), @r#"
{
"message": "Personalization service: Unauthorized: invalid API key",
"code": "remote_invalid_api_key",
"type": "auth",
"link": "https://docs.meilisearch.com/errors#remote_invalid_api_key"
}
"#);
}
#[actix_rt::test]
async fn search_with_personalization_no_user_context() {
// Create a server with a fake personalization API key
let dir = TempDir::new().unwrap();
let options = Opt {
experimental_personalization_api_key: Some("fake-api-key-12345".to_string()),
..default_settings(dir.path())
};
let server = Server::new_with_options(options).await.unwrap();
let index = server.unique_index();
// Create the index and add some documents
let (task, _code) = index.create(None).await;
server.wait_task(task.uid()).await.succeeded();
let (task, _code) = index
.add_documents(
json!([
{"id": 1, "title": "The Dark Knight", "genre": "Action"},
{"id": 2, "title": "Inception", "genre": "Sci-Fi"},
{"id": 3, "title": "The Matrix", "genre": "Sci-Fi"}
]),
None,
)
.await;
server.wait_task(task.uid()).await.succeeded();
// Try to search with personalization - should return remote_invalid_api_key error
let (response, code) = index
.search_post(json!({
"q": "the",
"personalize": {}
}))
.await;
snapshot!(code, @"400 Bad Request");
snapshot!(json_string!(response), @r###"
{
"message": "Missing field `userContext` inside `.personalize`",
"code": "invalid_search_personalize",
"type": "invalid_request",
"link": "https://docs.meilisearch.com/errors#invalid_search_personalize"
}
"###);
}

View File

@@ -137,60 +137,6 @@ static SIMPLE_SEARCH_DOCUMENTS: Lazy<Value> = Lazy::new(|| {
}])
});
static MANY_DOCS: Lazy<Value> = Lazy::new(|| {
json!([
{
"title": "Shazam!",
"desc": "a Captain Marvel ersatz",
"id": "1",
},
{
"title": "Captain Planet",
"desc": "He's not part of the Marvel Cinematic Universe",
"id": "2",
},
{
"title": "Captain Marvel",
"desc": "a Shazam ersatz",
"id": "3",
},
{
"title": "Captain Marvel",
"desc": "a Shazam ersatz",
"id": "4",
},
{
"title": "Captain Marvel",
"desc": "a Shazam ersatz",
"id": "5",
},
{
"title": "Captain Marvel",
"desc": "a Shazam ersatz",
"id": "6",
},
{
"title": "Captain Marvel",
"desc": "a Shazam ersatz",
"id": "7",
},
{
"title": "Captain Marvel",
"desc": "a Shazam ersatz",
"id": "8",
},
{
"title": "Captain Marvel",
"desc": "a Shazam ersatz",
"id": "9",
},
{
"title": "Captain Marvel",
"desc": "a Shazam ersatz",
"id": "10",
}])
});
#[actix_rt::test]
async fn simple_search() {
let server = Server::new_shared();
@@ -503,38 +449,6 @@ async fn simple_search_hf() {
snapshot!(response["semanticHitCount"], @"3");
}
#[actix_rt::test]
async fn issue_5976_missing_docs_hf() {
let server = Server::new_shared();
let index = index_with_documents_hf(server, &MANY_DOCS).await;
let (response, code) = index
.search_post(
json!({"q": "Wonder replacement", "hybrid": {"embedder": "default", "semanticRatio": 1.0}, "retrieveVectors": true}),
)
.await;
snapshot!(code, @"200 OK");
let are_empty: Vec<_> = response["hits"]
.as_array()
.unwrap()
.iter()
.map(|hit| hit["_vectors"]["default"]["embeddings"].as_array().unwrap().is_empty())
.collect();
snapshot!(json!(are_empty), @r###"
[
false,
false,
false,
false,
false,
false,
false,
false,
false,
false
]
"###);
}
#[actix_rt::test]
async fn distribution_shift() {
let server = Server::new_shared();

Some files were not shown because too many files have changed in this diff Show More