llama-stack-mirror/.github/workflows/integration-vector-io-tests.yml
Ashwin Bharambe 81ecaf6221
Some checks failed
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Integration Tests (Replay) / discover-tests (push) Successful in 3s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 6s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 8s
Python Package Build Test / build (3.12) (push) Failing after 6s
Test External API and Providers / test-external (venv) (push) Failing after 6s
Update ReadTheDocs / update-readthedocs (push) Failing after 6s
Integration Tests (Replay) / Integration Tests (, , , client=, vision=) (push) Failing after 5s
Unit Tests / unit-tests (3.13) (push) Failing after 8s
Vector IO Integration Tests / test-matrix (push) Failing after 11s
Unit Tests / unit-tests (3.12) (push) Failing after 10s
Python Package Build Test / build (3.13) (push) Failing after 13s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 19s
Pre-commit / pre-commit (push) Successful in 1m19s
fix(ci): make the Vector IO CI follow the same pattern as others (#3164)
# What does this PR do?
Updates the integration-vector-io-tests workflow to run daily tests on
Python 3.13 while limiting regular PR tests to Python 3.12 only.

The PR also improves the concurrency configuration to prevent workflow
conflicts between main branch runs and PR runs.

## Test Plan


[![testinprod](https://graphite-user-uploaded-assets-prod.s3.amazonaws.com/WjlTemxb6oA4PgZFmj08/2645295d-f421-49ae-8f3f-f4672d8204e2/testinprod.jpeg)](https://app.graphite.dev/settings/meme-library?org=llamastack)
2025-08-14 21:06:08 -07:00

201 lines
7.5 KiB
YAML

name: Vector IO Integration Tests
run-name: Run the integration test suite with various VectorIO providers
on:
push:
branches: [ main ]
pull_request:
branches: [ main ]
paths:
- 'llama_stack/**'
- 'tests/integration/vector_io/**'
- 'uv.lock'
- 'pyproject.toml'
- 'requirements.txt'
- '.github/workflows/integration-vector-io-tests.yml' # This workflow
schedule:
- cron: '0 0 * * *' # (test on python 3.13) Daily at 12 AM UTC
concurrency:
group: ${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}
cancel-in-progress: true
jobs:
test-matrix:
runs-on: ubuntu-latest
strategy:
matrix:
vector-io-provider: ["inline::faiss", "inline::sqlite-vec", "inline::milvus", "remote::chromadb", "remote::pgvector", "remote::weaviate", "remote::qdrant"]
python-version: ${{ github.event.schedule == '0 0 * * *' && fromJSON('["3.12", "3.13"]') || fromJSON('["3.12"]') }}
fail-fast: false # we want to run all tests regardless of failure
steps:
- name: Checkout repository
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Install dependencies
uses: ./.github/actions/setup-runner
with:
python-version: ${{ matrix.python-version }}
- name: Setup Chroma
if: matrix.vector-io-provider == 'remote::chromadb'
run: |
docker run --rm -d --pull always \
--name chromadb \
-p 8000:8000 \
-v ~/chroma:/chroma/chroma \
-e IS_PERSISTENT=TRUE \
-e ANONYMIZED_TELEMETRY=FALSE \
chromadb/chroma:latest
- name: Setup Weaviate
if: matrix.vector-io-provider == 'remote::weaviate'
run: |
docker run --rm -d --pull always \
--name weaviate \
-p 8080:8080 -p 50051:50051 \
cr.weaviate.io/semitechnologies/weaviate:1.32.0
- name: Start PGVector DB
if: matrix.vector-io-provider == 'remote::pgvector'
run: |
docker run -d \
--name pgvector \
-e POSTGRES_USER=llamastack \
-e POSTGRES_PASSWORD=llamastack \
-e POSTGRES_DB=llamastack \
-p 5432:5432 \
pgvector/pgvector:pg17
- name: Wait for PGVector to be ready
if: matrix.vector-io-provider == 'remote::pgvector'
run: |
echo "Waiting for Postgres to be ready..."
for i in {1..30}; do
if docker exec pgvector pg_isready -U llamastack > /dev/null 2>&1; then
echo "Postgres is ready!"
break
fi
echo "Not ready yet... ($i)"
sleep 1
done
- name: Enable pgvector extension
if: matrix.vector-io-provider == 'remote::pgvector'
run: |
PGPASSWORD=llamastack psql -h localhost -U llamastack -d llamastack \
-c "CREATE EXTENSION IF NOT EXISTS vector;"
- name: Setup Qdrant
if: matrix.vector-io-provider == 'remote::qdrant'
run: |
docker run --rm -d --pull always \
--name qdrant \
-p 6333:6333 \
qdrant/qdrant
- name: Wait for Qdrant to be ready
if: matrix.vector-io-provider == 'remote::qdrant'
run: |
echo "Waiting for Qdrant to be ready..."
for i in {1..30}; do
if curl -s http://localhost:6333/collections | grep -q '"status":"ok"'; then
echo "Qdrant is ready!"
exit 0
fi
sleep 2
done
echo "Qdrant failed to start"
docker logs qdrant
exit 1
- name: Wait for ChromaDB to be ready
if: matrix.vector-io-provider == 'remote::chromadb'
run: |
echo "Waiting for ChromaDB to be ready..."
for i in {1..30}; do
if curl -s http://localhost:8000/api/v2/heartbeat | grep -q "nanosecond heartbeat"; then
echo "ChromaDB is ready!"
exit 0
fi
sleep 2
done
echo "ChromaDB failed to start"
docker logs chromadb
exit 1
- name: Wait for Weaviate to be ready
if: matrix.vector-io-provider == 'remote::weaviate'
run: |
echo "Waiting for Weaviate to be ready..."
for i in {1..30}; do
if curl -s http://localhost:8080 | grep -q "https://weaviate.io/developers/weaviate/current/"; then
echo "Weaviate is ready!"
exit 0
fi
sleep 2
done
echo "Weaviate failed to start"
docker logs weaviate
exit 1
- name: Build Llama Stack
run: |
uv run llama stack build --template ci-tests --image-type venv
- name: Check Storage and Memory Available Before Tests
if: ${{ always() }}
run: |
free -h
df -h
- name: Run Vector IO Integration Tests
env:
ENABLE_CHROMADB: ${{ matrix.vector-io-provider == 'remote::chromadb' && 'true' || '' }}
CHROMADB_URL: ${{ matrix.vector-io-provider == 'remote::chromadb' && 'http://localhost:8000' || '' }}
ENABLE_PGVECTOR: ${{ matrix.vector-io-provider == 'remote::pgvector' && 'true' || '' }}
PGVECTOR_HOST: ${{ matrix.vector-io-provider == 'remote::pgvector' && 'localhost' || '' }}
PGVECTOR_PORT: ${{ matrix.vector-io-provider == 'remote::pgvector' && '5432' || '' }}
PGVECTOR_DB: ${{ matrix.vector-io-provider == 'remote::pgvector' && 'llamastack' || '' }}
PGVECTOR_USER: ${{ matrix.vector-io-provider == 'remote::pgvector' && 'llamastack' || '' }}
PGVECTOR_PASSWORD: ${{ matrix.vector-io-provider == 'remote::pgvector' && 'llamastack' || '' }}
ENABLE_QDRANT: ${{ matrix.vector-io-provider == 'remote::qdrant' && 'true' || '' }}
QDRANT_URL: ${{ matrix.vector-io-provider == 'remote::qdrant' && 'http://localhost:6333' || '' }}
ENABLE_WEAVIATE: ${{ matrix.vector-io-provider == 'remote::weaviate' && 'true' || '' }}
WEAVIATE_CLUSTER_URL: ${{ matrix.vector-io-provider == 'remote::weaviate' && 'localhost:8080' || '' }}
run: |
uv run pytest -sv --stack-config="files=inline::localfs,inference=inline::sentence-transformers,vector_io=${{ matrix.vector-io-provider }}" \
tests/integration/vector_io \
--embedding-model inline::sentence-transformers/all-MiniLM-L6-v2
- name: Check Storage and Memory Available After Tests
if: ${{ always() }}
run: |
free -h
df -h
- name: Create sanitized provider name
if: ${{ always() }}
run: |
echo "SANITIZED_PROVIDER=$(echo "${{ matrix.vector-io-provider }}" | tr ':' '_')" >> $GITHUB_ENV
- name: Write ChromaDB logs to file
if: ${{ always() && matrix.vector-io-provider == 'remote::chromadb' }}
run: |
docker logs chromadb > chromadb.log
- name: Write Qdrant logs to file
if: ${{ always() && matrix.vector-io-provider == 'remote::qdrant' }}
run: |
docker logs qdrant > qdrant.log
- name: Upload all logs to artifacts
if: ${{ always() }}
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:
name: vector-io-logs-${{ github.run_id }}-${{ github.run_attempt }}-${{ env.SANITIZED_PROVIDER }}-${{ matrix.python-version }}
path: |
*.log
retention-days: 1