feat: slim docker distro (#314)

* feat: slim docker distro

* feat: slim docker distro

* push

Author: nicoloboschi

.github/workflows/release.yml

@@ -340,6 +340,7 @@ jobs:
         retention-days: 1
 
   release-docker-images:
+    name: Release Docker (${{ matrix.image_name }}${{ matrix.tag_suffix }})
     runs-on: ubuntu-latest
     permissions:
       contents: read
@@ -349,10 +350,28 @@ jobs:
         include:
           - target: api-only
             image_name: hindsight-api
+            tag_suffix: ""
+            build_args: ""
+          - target: api-only
+            image_name: hindsight-api
+            tag_suffix: "-slim"
+            build_args: |
+              INCLUDE_LOCAL_MODELS=false
+              PRELOAD_ML_MODELS=false
           - target: cp-only
             image_name: hindsight-control-plane
+            tag_suffix: ""
+            build_args: ""
+          - target: standalone
+            image_name: hindsight
+            tag_suffix: ""
+            build_args: ""
           - target: standalone
             image_name: hindsight
+            tag_suffix: "-slim"
+            build_args: |
+              INCLUDE_LOCAL_MODELS=false
+              PRELOAD_ML_MODELS=false
 
     steps:
     - uses: actions/checkout@v4
@@ -390,6 +409,9 @@ jobs:
       uses: docker/metadata-action@v5
       with:
         images: ghcr.io/${{ github.repository_owner }}/${{ matrix.image_name }}
+        flavor: |
+          latest=auto
+          suffix=${{ matrix.tag_suffix }}
         tags: |
           type=semver,pattern={{version}},value=${{ steps.get_version.outputs.VERSION }}
           type=semver,pattern={{major}}.{{minor}},value=${{ steps.get_version.outputs.VERSION }}
@@ -415,7 +437,7 @@ jobs:
     # - name: Smoke test - verify container starts
     #   env:
     #     GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-    #   run: ./scripts/docker-smoke-test.sh "${{ matrix.image_name }}:test" "${{ matrix.target }}"
+    #   run: ./docker/test-image.sh "${{ matrix.image_name }}:test" "${{ matrix.target }}"
 
     # Build multi-platform and push to release tags
     - name: Build and push release images
@@ -424,6 +446,7 @@ jobs:
         context: .
         file: docker/standalone/Dockerfile
         target: ${{ matrix.target }}
+        build-args: ${{ matrix.build_args }}
         push: true
         platforms: linux/amd64,linux/arm64
         tags: ${{ steps.meta.outputs.tags }}

.github/workflows/test.yml

@@ -277,16 +277,35 @@ jobs:
       run: helm lint helm/hindsight
 
   build-docker-images:
+    name: Build Docker (${{ matrix.name }})
     runs-on: ubuntu-latest
     strategy:
       matrix:
         include:
           - target: api-only
             name: api
+            variant: full
+            build_args: ""
+          - target: api-only
+            name: api-slim
+            variant: slim
+            build_args: |
+              INCLUDE_LOCAL_MODELS=false
+              PRELOAD_ML_MODELS=false
           - target: cp-only
             name: control-plane
+            variant: full
+            build_args: ""
           - target: standalone
             name: standalone
+            variant: full
+            build_args: ""
+          - target: standalone
+            name: standalone-slim
+            variant: slim
+            build_args: |
+              INCLUDE_LOCAL_MODELS=false
+              PRELOAD_ML_MODELS=false
 
     steps:
     - uses: actions/checkout@v4
@@ -305,20 +324,30 @@ jobs:
     - name: Set up Docker Buildx
       uses: docker/setup-buildx-action@v3
 
-    - name: Build ${{ matrix.name }} image
+    - name: Build ${{ matrix.name }} image (${{ matrix.variant }})
       uses: docker/build-push-action@v6
       with:
         context: .
         file: docker/standalone/Dockerfile
         target: ${{ matrix.target }}
+        build-args: ${{ matrix.build_args }}
         push: false
-        load: false
-
-    # TODO: Re-enable smoke test when disk space issue is resolved
-    # - name: Smoke test - verify container starts
-    #   env:
-    #     GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-    #   run: ./scripts/docker-smoke-test.sh "hindsight-${{ matrix.name }}:test" "${{ matrix.target }}"
+        load: ${{ matrix.variant == 'slim' }}
+        tags: hindsight-${{ matrix.name }}:test
+        cache-from: type=gha,scope=${{ matrix.name }}
+        cache-to: type=gha,mode=max,scope=${{ matrix.name }}
+
+    # Only test slim variants to save disk space (they're much smaller)
+    # Slim variants require external embedding providers
+    - name: Smoke test - verify container starts
+      if: matrix.variant == 'slim'
+      env:
+        GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+        HINDSIGHT_API_EMBEDDINGS_PROVIDER: openai
+        HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+        HINDSIGHT_API_RERANKER_PROVIDER: cohere
+        HINDSIGHT_API_COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
+      run: ./docker/test-image.sh "hindsight-${{ matrix.name }}:test" "${{ matrix.target }}"
 
   test-api:
     runs-on: ubuntu-latest

README.md

@@ -59,7 +59,7 @@ docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
 
 You can modify the LLM provider by setting `HINDSIGHT_API_LLM_PROVIDER`. Valid options are `openai`, `anthropic`, `gemini`, `groq`, `ollama`, and `lmstudio`. The documentation provides more details on [supported models](https://hindsight.vectorize.io/developer/models).
 
-API: http://localhost:8888  
+API: http://localhost:8888
 UI: http://localhost:9999
 
 Install client:

docker/README.md

@@ -0,0 +1,135 @@
+# Docker Testing
+
+Scripts for testing Hindsight Docker images locally and in CI.
+
+## Scripts
+
+### `test-image.sh`
+
+General-purpose Docker image test script. Starts a container and verifies it becomes healthy.
+
+**Usage:**
+```bash
+./docker/test-image.sh <image> [target]
+```
+
+**Arguments:**
+- `image` - Docker image to test (e.g., `hindsight:test`, `ghcr.io/vectorize-io/hindsight:latest`)
+- `target` - Optional: `cp-only` for control plane, `api-only` for API, or `standalone` (default)
+
+**Environment Variables:**
+- `GROQ_API_KEY` - Required for API/standalone images
+- `HINDSIGHT_API_LLM_PROVIDER` - LLM provider (default: `groq`)
+- `HINDSIGHT_API_LLM_MODEL` - LLM model (default: `llama-3.3-70b-versatile`)
+- `HINDSIGHT_API_EMBEDDINGS_PROVIDER` - Embeddings provider (for slim images)
+- `HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY` - OpenAI API key for embeddings
+- `HINDSIGHT_API_RERANKER_PROVIDER` - Reranker provider (for slim images)
+- `HINDSIGHT_API_COHERE_API_KEY` - Cohere API key for reranking
+- `SMOKE_TEST_TIMEOUT` - Timeout in seconds (default: 120)
+
+**Examples:**
+
+Test a full image (with local ML models):
+```bash
+export GROQ_API_KEY=gsk_xxx
+./docker/test-image.sh hindsight:test
+```
+
+Test a slim image (with external providers):
+```bash
+export GROQ_API_KEY=gsk_xxx
+export HINDSIGHT_API_EMBEDDINGS_PROVIDER=openai
+export HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY=sk-xxx
+export HINDSIGHT_API_RERANKER_PROVIDER=cohere
+export HINDSIGHT_API_COHERE_API_KEY=xxx
+./docker/test-image.sh hindsight-slim:test
+```
+
+### `test-slim-local.sh`
+
+Convenience wrapper for testing slim images locally. Automatically configures external providers.
+
+**Usage:**
+```bash
+# Set API keys
+export GROQ_API_KEY=gsk_xxx
+export OPENAI_API_KEY=sk-xxx
+export COHERE_API_KEY=xxx
+
+# Run test
+./docker/test-slim-local.sh [image]
+```
+
+**Or inline:**
+```bash
+GROQ_API_KEY=gsk_xxx \
+OPENAI_API_KEY=sk-xxx \
+COHERE_API_KEY=xxx \
+./docker/test-slim-local.sh hindsight-slim:test
+```
+
+This script:
+- ✅ Validates API keys are set
+- ✅ Configures OpenAI embeddings automatically
+- ✅ Configures Cohere reranking automatically
+- ✅ Calls `test-image.sh` with the right configuration
+
+## Building and Testing Locally
+
+### Build a slim image
+
+```bash
+docker build \
+  --build-arg INCLUDE_LOCAL_MODELS=false \
+  --build-arg PRELOAD_ML_MODELS=false \
+  --target standalone \
+  -t hindsight-slim:test \
+  -f docker/standalone/Dockerfile \
+  .
+```
+
+### Test the slim image
+
+```bash
+# With API keys
+export GROQ_API_KEY=gsk_xxx
+export OPENAI_API_KEY=sk-xxx
+export COHERE_API_KEY=xxx
+
+# Run test
+./docker/test-slim-local.sh hindsight-slim:test
+```
+
+## Expected Output
+
+**Successful test:**
+```
+Starting smoke test for: hindsight-slim:test
+  Target: standalone
+  Health endpoint: http://localhost:8888/health
+  Timeout: 120s
+
+Starting container...
+Waiting for health endpoint at http://localhost:8888/health...
+  Still waiting... (10s)
+  Still waiting... (20s)
+
+Container is healthy after 25s
+
+=== Health Response ===
+{
+    "status": "healthy",
+    "database": "connected"
+}
+
+Smoke test PASSED
+```
+
+## CI Integration
+
+These scripts are used in CI to validate Docker images on every PR:
+
+- `.github/workflows/test.yml` - Runs `test-image.sh` for slim variants with OpenAI/Cohere
+- `.github/workflows/release.yml` - Can optionally run smoke tests during release
+
+See the workflows for the exact configuration.

scripts/docker-smoke-test.sh docker/test-image.shscripts/docker-smoke-test.sh renamed to docker/test-image.sh

@@ -6,28 +6,40 @@
 # Can be run locally or in CI pipelines.
 #
 # Usage:
-#   ./scripts/docker-smoke-test.sh <image> [target]
+#   ./docker/test-image.sh <image> [target]
 #
 # Arguments:
 #   image   - Docker image to test (e.g., hindsight-api:test, ghcr.io/vectorize-io/hindsight:latest)
 #   target  - Optional: 'cp-only' for control plane, otherwise assumes API image (default: api)
 #
 # Environment variables:
-#   GROQ_API_KEY              - Required for API/standalone images (LLM verification)
-#   HINDSIGHT_API_LLM_PROVIDER - LLM provider (default: groq)
-#   HINDSIGHT_API_LLM_MODEL    - LLM model (default: llama-3.3-70b-versatile)
-#   SMOKE_TEST_TIMEOUT        - Timeout in seconds (default: 120)
-#   SMOKE_TEST_CONTAINER_NAME - Container name (default: hindsight-smoke-test)
+#   GROQ_API_KEY                                - Required for API/standalone images (LLM verification)
+#   HINDSIGHT_API_LLM_PROVIDER                  - LLM provider (default: groq)
+#   HINDSIGHT_API_LLM_MODEL                     - LLM model (default: llama-3.3-70b-versatile)
+#   HINDSIGHT_API_EMBEDDINGS_PROVIDER           - Embeddings provider (optional, for slim images: openai, cohere, tei)
+#   HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY     - OpenAI API key for embeddings (optional)
+#   HINDSIGHT_API_RERANKER_PROVIDER             - Reranker provider (optional, for slim images: cohere, tei)
+#   HINDSIGHT_API_COHERE_API_KEY                - Cohere API key for reranking (optional)
+#   SMOKE_TEST_TIMEOUT                          - Timeout in seconds (default: 120)
+#   SMOKE_TEST_CONTAINER_NAME                   - Container name (default: hindsight-smoke-test)
 #
 # Examples:
-#   # Test a locally built image
-#   ./scripts/docker-smoke-test.sh hindsight-api:test
+#   # Test a locally built full image
+#   ./docker/test-image.sh hindsight-api:test
 #
 #   # Test a released image
-#   ./scripts/docker-smoke-test.sh ghcr.io/vectorize-io/hindsight:latest
+#   ./docker/test-image.sh ghcr.io/vectorize-io/hindsight:latest
 #
 #   # Test control plane image
-#   ./scripts/docker-smoke-test.sh hindsight-control-plane:test cp-only
+#   ./docker/test-image.sh hindsight-control-plane:test cp-only
+#
+#   # Test slim image with external providers
+#   export GROQ_API_KEY=gsk_xxx
+#   export HINDSIGHT_API_EMBEDDINGS_PROVIDER=openai
+#   export HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY=sk-xxx
+#   export HINDSIGHT_API_RERANKER_PROVIDER=cohere
+#   export HINDSIGHT_API_COHERE_API_KEY=xxx
+#   ./docker/test-image.sh hindsight-slim:test
 #
 # Exit codes:
 #   0 - Success (container healthy)
@@ -108,12 +120,32 @@ if [ "$TARGET" = "cp-only" ]; then
         -p "${HEALTH_PORT}:${HEALTH_PORT}" \
         "$IMAGE"
 else
-    docker run -d --name "$CONTAINER_NAME" \
-        -e HINDSIGHT_API_LLM_PROVIDER="$LLM_PROVIDER" \
-        -e HINDSIGHT_API_LLM_API_KEY="${GROQ_API_KEY}" \
-        -e HINDSIGHT_API_LLM_MODEL="$LLM_MODEL" \
-        -p "${HEALTH_PORT}:${HEALTH_PORT}" \
-        "$IMAGE"
+    # Build docker run command with required and optional env vars
+    DOCKER_CMD="docker run -d --name $CONTAINER_NAME"
+    DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_LLM_PROVIDER=$LLM_PROVIDER"
+    DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_LLM_API_KEY=${GROQ_API_KEY}"
+    DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_LLM_MODEL=$LLM_MODEL"
+
+    # Add optional embeddings provider config
+    if [ -n "${HINDSIGHT_API_EMBEDDINGS_PROVIDER:-}" ]; then
+        DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_EMBEDDINGS_PROVIDER=${HINDSIGHT_API_EMBEDDINGS_PROVIDER}"
+    fi
+    if [ -n "${HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY:-}" ]; then
+        DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY=${HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY}"
+    fi
+
+    # Add optional reranker provider config
+    if [ -n "${HINDSIGHT_API_RERANKER_PROVIDER:-}" ]; then
+        DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_RERANKER_PROVIDER=${HINDSIGHT_API_RERANKER_PROVIDER}"
+    fi
+    if [ -n "${HINDSIGHT_API_COHERE_API_KEY:-}" ]; then
+        DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_COHERE_API_KEY=${HINDSIGHT_API_COHERE_API_KEY}"
+    fi
+
+    DOCKER_CMD="$DOCKER_CMD -p ${HEALTH_PORT}:${HEALTH_PORT}"
+    DOCKER_CMD="$DOCKER_CMD $IMAGE"
+
+    eval $DOCKER_CMD
 fi
 
 # Wait for health endpoint