mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-20 23:58:52 +00:00
b11bcfde11
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>
92 lines
3 KiB
YAML
92 lines
3 KiB
YAML
name: Test External API and Providers
|
|
|
|
run-name: Test the External API and Provider mechanisms
|
|
|
|
on:
|
|
push:
|
|
branches: [ main ]
|
|
pull_request:
|
|
branches: [ main ]
|
|
paths:
|
|
- 'llama_stack/**'
|
|
- '!llama_stack/ui/**'
|
|
- 'tests/integration/**'
|
|
- 'uv.lock'
|
|
- 'pyproject.toml'
|
|
- 'requirements.txt'
|
|
- 'tests/external/*'
|
|
- '.github/workflows/test-external.yml' # This workflow
|
|
|
|
jobs:
|
|
test-external:
|
|
runs-on: ubuntu-latest
|
|
strategy:
|
|
matrix:
|
|
image-type: [venv]
|
|
# We don't do container yet, it's tricky to install a package from the host into the
|
|
# container and point 'uv pip install' to the correct path...
|
|
steps:
|
|
- name: Checkout repository
|
|
uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
|
|
|
|
- name: Install dependencies
|
|
uses: ./.github/actions/setup-runner
|
|
|
|
- name: Create API configuration
|
|
run: |
|
|
mkdir -p /home/runner/.llama/apis.d
|
|
cp tests/external/weather.yaml /home/runner/.llama/apis.d/weather.yaml
|
|
|
|
- name: Create provider configuration
|
|
run: |
|
|
mkdir -p /home/runner/.llama/providers.d/remote/weather
|
|
cp tests/external/kaze.yaml /home/runner/.llama/providers.d/remote/weather/kaze.yaml
|
|
|
|
- name: Print distro dependencies
|
|
run: |
|
|
USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run --no-sync llama stack list-deps tests/external/build.yaml
|
|
|
|
- name: Build distro from config file
|
|
run: |
|
|
uv venv ci-test
|
|
source ci-test/bin/activate
|
|
uv pip install -e .
|
|
LLAMA_STACK_LOGGING=all=CRITICAL llama stack list-deps tests/external/build.yaml | xargs -L1 uv pip install
|
|
|
|
- name: Start Llama Stack server in background
|
|
if: ${{ matrix.image-type }} == 'venv'
|
|
env:
|
|
INFERENCE_MODEL: "meta-llama/Llama-3.2-3B-Instruct"
|
|
LLAMA_STACK_LOG_FILE: "server.log"
|
|
run: |
|
|
# Use the virtual environment created by the build step (name comes from build config)
|
|
source ci-test/bin/activate
|
|
uv pip list
|
|
nohup llama stack run tests/external/run-byoa.yaml > server.log 2>&1 &
|
|
|
|
- name: Wait for Llama Stack server to be ready
|
|
run: |
|
|
echo "Waiting for Llama Stack server..."
|
|
for i in {1..30}; do
|
|
if curl -sSf http://localhost:8321/v1/health | grep -q "OK"; then
|
|
echo "Llama Stack server is up!"
|
|
exit 0
|
|
fi
|
|
sleep 1
|
|
done
|
|
echo "Llama Stack server failed to start"
|
|
cat server.log
|
|
exit 1
|
|
|
|
- name: Test external API
|
|
run: |
|
|
curl -sSf http://localhost:8321/v1/weather/locations
|
|
|
|
- name: Upload all logs to artifacts
|
|
if: ${{ always() }}
|
|
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
|
|
with:
|
|
name: logs-${{ github.run_id }}-${{ github.run_attempt }}-external-test
|
|
path: |
|
|
*.log
|
|
retention-days: 1
|