mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-20 23:58:52 +00:00
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
Test Llama Stack Build / generate-matrix (push) Successful in 22s
Test llama stack list-deps / show-single-provider (push) Failing after 53s
Test Llama Stack Build / build-single-provider (push) Failing after 3s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Python Package Build Test / build (3.12) (push) Failing after 18s
Python Package Build Test / build (3.13) (push) Failing after 24s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 26s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 27s
Unit Tests / unit-tests (3.12) (push) Failing after 26s
Vector IO Integration Tests / test-matrix (push) Failing after 44s
API Conformance Tests / check-schema-compatibility (push) Successful in 52s
Test llama stack list-deps / generate-matrix (push) Successful in 52s
Test Llama Stack Build / build (push) Failing after 29s
Test External API and Providers / test-external (venv) (push) Failing after 53s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1m2s
Unit Tests / unit-tests (3.13) (push) Failing after 1m30s
Test llama stack list-deps / list-deps-from-config (push) Failing after 1m59s
Test llama stack list-deps / list-deps (push) Failing after 1m10s
UI Tests / ui-tests (22) (push) Successful in 2m26s
Pre-commit / pre-commit (push) Successful in 3m8s
# What does this PR do? This PR does a few things outlined in #2878 namely: 1. adds `llama stack list-deps` a command which simply takes the build logic and instead of executing one of the `build_...` scripts, it displays all of the providers' dependencies using the `module` and `uv`. 2. deprecated `llama stack build` in favor of `llama stack list-deps` 3. updates all tests to use `list-deps` alongside `build`. PR 2/2 will migrate `llama stack run`'s default behavior to be `llama stack build --run` and use the new `list-deps` command under the hood before running the server. examples of `llama stack list-deps starter` ``` llama stack list-deps starter --format json { "name": "starter", "description": "Quick start template for running Llama Stack with several popular providers. This distribution is intended for CPU-only environments.", "apis": [ { "api": "inference", "provider": "remote::cerebras" }, { "api": "inference", "provider": "remote::ollama" }, { "api": "inference", "provider": "remote::vllm" }, { "api": "inference", "provider": "remote::tgi" }, { "api": "inference", "provider": "remote::fireworks" }, { "api": "inference", "provider": "remote::together" }, { "api": "inference", "provider": "remote::bedrock" }, { "api": "inference", "provider": "remote::nvidia" }, { "api": "inference", "provider": "remote::openai" }, { "api": "inference", "provider": "remote::anthropic" }, { "api": "inference", "provider": "remote::gemini" }, { "api": "inference", "provider": "remote::vertexai" }, { "api": "inference", "provider": "remote::groq" }, { "api": "inference", "provider": "remote::sambanova" }, { "api": "inference", "provider": "remote::azure" }, { "api": "inference", "provider": "inline::sentence-transformers" }, { "api": "vector_io", "provider": "inline::faiss" }, { "api": "vector_io", "provider": "inline::sqlite-vec" }, { "api": "vector_io", "provider": "inline::milvus" }, { "api": "vector_io", "provider": "remote::chromadb" }, { "api": "vector_io", "provider": "remote::pgvector" }, { "api": "files", "provider": "inline::localfs" }, { "api": "safety", "provider": "inline::llama-guard" }, { "api": "safety", "provider": "inline::code-scanner" }, { "api": "agents", "provider": "inline::meta-reference" }, { "api": "telemetry", "provider": "inline::meta-reference" }, { "api": "post_training", "provider": "inline::torchtune-cpu" }, { "api": "eval", "provider": "inline::meta-reference" }, { "api": "datasetio", "provider": "remote::huggingface" }, { "api": "datasetio", "provider": "inline::localfs" }, { "api": "scoring", "provider": "inline::basic" }, { "api": "scoring", "provider": "inline::llm-as-judge" }, { "api": "scoring", "provider": "inline::braintrust" }, { "api": "tool_runtime", "provider": "remote::brave-search" }, { "api": "tool_runtime", "provider": "remote::tavily-search" }, { "api": "tool_runtime", "provider": "inline::rag-runtime" }, { "api": "tool_runtime", "provider": "remote::model-context-protocol" }, { "api": "batches", "provider": "inline::reference" } ], "pip_dependencies": [ "pandas", "opentelemetry-exporter-otlp-proto-http", "matplotlib", "opentelemetry-sdk", "sentence-transformers", "datasets", "pymilvus[milvus-lite]>=2.4.10", "codeshield", "scipy", "torchvision", "tree_sitter", "h11>=0.16.0", "aiohttp", "pymongo", "tqdm", "pythainlp", "pillow", "torch", "emoji", "grpcio>=1.67.1,<1.71.0", "fireworks-ai", "langdetect", "psycopg2-binary", "asyncpg", "redis", "together", "torchao>=0.12.0", "openai", "sentencepiece", "aiosqlite", "google-cloud-aiplatform", "faiss-cpu", "numpy", "sqlite-vec", "nltk", "scikit-learn", "mcp>=1.8.1", "transformers", "boto3", "huggingface_hub", "ollama", "autoevals", "sqlalchemy[asyncio]", "torchtune>=0.5.0", "chromadb-client", "pypdf", "requests", "anthropic", "chardet", "aiosqlite", "fastapi", "fire", "httpx", "uvicorn", "opentelemetry-sdk", "opentelemetry-exporter-otlp-proto-http" ] } ``` <img width="1500" height="420" alt="Screenshot 2025-10-16 at 5 53 03 PM" src="https://github.com/user-attachments/assets/765929fb-93e2-44d7-9c3d-8918b70fc721" /> --------- Signed-off-by: Charlie Doern <cdoern@redhat.com>
204 lines
7.6 KiB
YAML
204 lines
7.6 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/**'
|
|
- '!llama_stack/ui/**'
|
|
- '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@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
|
|
|
|
- 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 --no-sync llama stack list-deps ci-tests | xargs -L1 uv pip install
|
|
|
|
- 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: ${{ matrix.vector-io-provider == 'remote::weaviate' && 'localhost:8080' || '' }}
|
|
run: |
|
|
uv run --no-sync \
|
|
pytest -sv --stack-config="files=inline::localfs,inference=inline::sentence-transformers,vector_io=${{ matrix.vector-io-provider }}" \
|
|
tests/integration/vector_io \
|
|
--embedding-model inline::sentence-transformers/nomic-ai/nomic-embed-text-v1.5 \
|
|
--embedding-dimension 768
|
|
|
|
- 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
|