feat: add LocalAI support #173
Workflow file for this run
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: CI | |
| on: | |
| pull_request: | |
| branches: [main] | |
| jobs: | |
| build: | |
| runs-on: ubuntu-latest | |
| strategy: | |
| matrix: | |
| python-version: | |
| - "3.10" | |
| - "3.11" | |
| - "3.12" | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: Install UV | |
| run: curl -LsSf https://astral.sh/uv/install.sh | sh | |
| - name: Source Cargo Environment | |
| run: source $HOME/.cargo/env | |
| - name: Set up Python ${{ matrix.python-version }} | |
| run: uv python install ${{ matrix.python-version }} | |
| - name: Ruff | |
| run: | | |
| uvx ruff check -v | |
| uvx ruff format --check -v | |
| - name: Run tests | |
| run: uv run pytest tests -m 'not integration' | |
| # This integration tests the OpenAI API, using Ollama to host models. | |
| # This lets us test PRs from forks which can't access secrets like API keys. | |
| ollama: | |
| runs-on: ubuntu-latest | |
| strategy: | |
| matrix: | |
| python-version: | |
| # Only test the latest python version. | |
| - "3.12" | |
| ollama-model: | |
| # For quicker CI, use a smaller, tool-capable model than the default. | |
| - "qwen2.5:0.5b" | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: Install UV | |
| run: curl -LsSf https://astral.sh/uv/install.sh | sh | |
| - name: Source Cargo Environment | |
| run: source $HOME/.cargo/env | |
| - name: Set up Python | |
| run: uv python install ${{ matrix.python-version }} | |
| - name: Install Ollama | |
| run: curl -fsSL https://ollama.com/install.sh | sh | |
| - name: Start Ollama | |
| run: | | |
| # Run the background, in a way that survives to the next step | |
| nohup ollama serve > ollama.log 2>&1 & | |
| # Block using the ready endpoint | |
| time curl --retry 5 --retry-connrefused --retry-delay 1 -sf http://localhost:11434 || cat ollama.log | |
| # Tests use OpenAI which does not have a mechanism to pull models. Run a | |
| # simple prompt to (pull and) test the model first. | |
| - name: Test Ollama model | |
| run: ollama run $OLLAMA_MODEL hello || cat ollama.log | |
| env: | |
| OLLAMA_MODEL: ${{ matrix.ollama-model }} | |
| - name: Run Ollama tests | |
| run: uv run pytest tests -m integration -k ollama || cat ollama.log | |
| env: | |
| OLLAMA_MODEL: ${{ matrix.ollama-model }} | |
| # This integration tests the OpenAI API, using LocalAI to host models. | |
| # This lets us test PRs from forks which can't access secrets like API keys. | |
| localai: | |
| runs-on: ubuntu-latest | |
| strategy: | |
| matrix: | |
| python-version: | |
| # Only test the latest python version. | |
| - "3.12" | |
| localai-model: | |
| # TODO: This is is the default model, as we haven't yet found a | |
| # small model that passes tests when run with LocalAI. For example, | |
| # "qwen2.5-0.5b-instruct" fails or hangs. | |
| - "mistral-nemo-instruct-2407" | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: Install UV | |
| run: curl -LsSf https://astral.sh/uv/install.sh | sh | |
| - name: Source Cargo Environment | |
| run: source $HOME/.cargo/env | |
| - name: Set up Python | |
| run: uv python install ${{ matrix.python-version }} | |
| - name: Download LocalAI | |
| uses: robinraju/release-downloader@v1.11 | |
| with: | |
| repository: mudler/LocalAI | |
| latest: true | |
| # Note the LocalAI linux binary is >1.2GB, so this step may take a while. | |
| fileName: 'local-ai-Linux-x86_64' | |
| - name: Install LocalAI | |
| run: | | |
| mv local-ai-Linux-x86_64 /usr/local/bin/local-ai | |
| chmod +x /usr/local/bin/local-ai | |
| - name: Start LocalAI | |
| run: | | |
| # Run the background, in a way that survives to the next step | |
| nohup local-ai run > localai.log 2>&1 & | |
| # Note: we don't `local-ai run` with the `LOCALAI_MODELS` env var | |
| # because the it would introduce a race. The below check would pass | |
| # before the model is downloaded. | |
| # Block using the ready endpoint | |
| time curl --retry 5 --retry-connrefused --retry-delay 1 -sf http://localhost:8080/readyz || cat localai.log | |
| # Tests use OpenAI which does not have a mechanism to install models. | |
| # This blocks until the model is installed to prevent failures. | |
| - name: Install LocalAI model | |
| run: local-ai models install $LOCALAI_MODEL || cat localai.log | |
| env: | |
| LOCALAI_MODEL: ${{ matrix.localai-model }} | |
| - name: Run LocalAI tests | |
| run: uv run pytest tests -m integration -k localai || cat localai.log | |
| env: | |
| LOCALAI_MODEL: ${{ matrix.localai-model }} |