Merge manifests into multi-architecture Docker image

Fix embedding skip

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

@@ -13,11 +13,93 @@ on:
     - cron: '0 23 * * *' # Every day at 11:00pm
   workflow_dispatch:
 
+env:
+  REGISTRY_IMAGE: getmeili/meilisearch
+
 jobs:
-  docker:
-    runs-on: docker
+  build:
+    runs-on: ${{ matrix.runner }}
+
+    strategy:
+      matrix:
+        platform: [amd64, arm64]
+        include:
+          - platform: amd64
+            runner: ubuntu-24.04
+          - platform: arm64
+            runner: ubuntu-24.04-arm
+
+    permissions: {}
+    steps:
+      - uses: actions/checkout@v5
+
+      - name: Prepare
+        run: |
+          platform=linux/${{ 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: ${{ env.REGISTRY_IMAGE }}
+          # Prevent `latest` to be updated for each new tag pushed.
+          # We need latest and `vX.Y` tags to only be pushed for the stable Meilisearch releases.
+          flavor: latest=false
+          tags: |
+            type=ref,event=tag
+            type=raw,value=nightly,enable=${{ 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: ${{ env.REGISTRY_IMAGE }}
+          outputs: type=image,push-by-digest=true,name-canonical=true,push=true
+          build-args: |
+            COMMIT_SHA=${{ github.sha }}
+            COMMIT_DATE=${{ steps.build-metadata.outputs.date }}
+            GIT_TAG=${{ github.ref_name }}
+
+      - 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-${{ env.PLATFORM_PAIR }}
+          path: ${{ runner.temp }}/digests/*
+          if-no-files-found: error
+          retention-days: 1
+
+  merge:
+    runs-on: ubuntu-latest
+    needs:
+      - build
+
     permissions:
       id-token: write # This is needed to use Cosign in keyless mode
+
     steps:
       - uses: actions/checkout@v5
 
@@ -58,26 +140,30 @@ 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-*
+          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: getmeili/meilisearch
+          images: ${{ env.REGISTRY_IMAGE }}
           # Prevent `latest` to be updated for each new tag pushed.
           # We need latest and `vX.Y` tags to only be pushed for the stable Meilisearch releases.
           flavor: latest=false
@@ -88,26 +174,24 @@ jobs:
             type=semver,pattern=v{{major}},enable=${{ 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: 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: 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") \
+            $(printf '${{ env.REGISTRY_IMAGE }}@sha256:%s ' *)
+
+      - name: Inspect image
+        run: |
+          digest=$(docker buildx imagetools inspect --raw ${{ env.REGISTRY_IMAGE }}:${{ steps.meta.outputs.version }} | jq -r '.manifests[0].digest')
+          echo "DIGEST=${digest}" >> $GITHUB_ENV
 
       - name: Sign the images with GitHub OIDC Token
         env:
-          DIGEST: ${{ steps.build-and-push.outputs.digest }}
           TAGS: ${{ steps.meta.outputs.tags }}
         run: |
           images=""
           for tag in ${TAGS}; do
-            images+="${tag}@${DIGEST} "
+            images+="${tag}@${{ env.DIGEST }} "
           done
           cosign sign --yes ${images}
 

crates/meilisearch/tests/search/hybrid.rs

@@ -137,6 +137,60 @@ 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();
@@ -449,6 +503,38 @@ 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();

crates/milli/src/vector/session.rs

@@ -112,13 +112,12 @@ impl<'doc, C: OnEmbed<'doc>, I: Input> EmbedSession<'doc, C, I> {
         rendered: I,
         unused_vectors_distribution: &C::ErrorMetadata,
     ) -> Result<()> {
-        if self.inputs.len() < self.inputs.capacity() {
-            self.inputs.push(rendered);
-            self.metadata.push(metadata);
-            return Ok(());
+        if self.inputs.len() >= self.inputs.capacity() {
+            self.embed_chunks(unused_vectors_distribution)?;
         }
-
-        self.embed_chunks(unused_vectors_distribution)
+        self.inputs.push(rendered);
+        self.metadata.push(metadata);
+        Ok(())
     }
 
     pub fn drain(mut self, unused_vectors_distribution: &C::ErrorMetadata) -> Result<C> {