feat: support structured outputs in LlamaStackChatGenerator
#202
Workflow file for this run
This file contains hidden or 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
| # This workflow comes from https://github.com/ofek/hatch-mypyc | |
| # https://github.com/ofek/hatch-mypyc/blob/5a198c0ba8660494d02716cfc9d79ce4adfb1442/.github/workflows/test.yml | |
| name: Test / llama_stack | |
| on: | |
| schedule: | |
| - cron: "0 0 * * *" | |
| pull_request: | |
| paths: | |
| - "integrations/llama_stack/**" | |
| - "!integrations/llama_stack/*.md" | |
| - ".github/workflows/llama_stack.yml" | |
| defaults: | |
| run: | |
| working-directory: integrations/llama_stack | |
| concurrency: | |
| group: llama_stack-${{ github.head_ref }} | |
| cancel-in-progress: true | |
| env: | |
| PYTHONUNBUFFERED: "1" | |
| FORCE_COLOR: "1" | |
| jobs: | |
| run: | |
| name: Python ${{ matrix.python-version }} on ${{ startsWith(matrix.os, 'macos-') && 'macOS' || startsWith(matrix.os, 'windows-') && 'Windows' || 'Linux' }} | |
| runs-on: ${{ matrix.os }} | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| os: [ubuntu-latest] # to test on other Operating Systems, we need to install Ollama differently | |
| python-version: ["3.12", "3.13"] | |
| steps: | |
| - uses: actions/checkout@v5 | |
| - name: Install and run Ollama Server as inference provider (needed for Llama Stack Server) | |
| uses: nick-fields/retry@v3 | |
| with: | |
| timeout_minutes: 4 | |
| max_attempts: 3 | |
| command: | | |
| curl -fsSL https://ollama.com/install.sh | sh | |
| nohup ollama serve > ollama.log 2>&1 & | |
| # Check if the service is up and running with a timeout of 60 seconds | |
| timeout=60 | |
| while [ $timeout -gt 0 ] && ! curl -sSf http://localhost:11434/ > /dev/null; do | |
| echo "Waiting for Ollama service to start..." | |
| sleep 5 | |
| ((timeout-=5)) | |
| done | |
| if [ $timeout -eq 0 ]; then | |
| echo "Timed out waiting for Ollama service to start." | |
| exit 1 | |
| fi | |
| echo "Ollama service started successfully." | |
| - name: Pull models | |
| uses: nick-fields/retry@v3 | |
| with: | |
| timeout_minutes: 2 | |
| max_attempts: 5 | |
| command: | | |
| ollama pull llama3.2:3b | |
| ollama list | grep -q "llama3.2:3b" || { echo "Model llama3.2:3b not pulled."; exit 1; } | |
| echo "Models pulled successfully." | |
| - name: Set up Python ${{ matrix.python-version }} | |
| uses: actions/setup-python@v6 | |
| with: | |
| python-version: ${{ matrix.python-version }} | |
| - name: Test Llama Stack Server | |
| env: | |
| OLLAMA_INFERENCE_MODEL: llama3.2:3b | |
| OLLAMA_URL: http://localhost:11434 | |
| shell: bash | |
| run: | | |
| set -euo pipefail | |
| pip install -q uv | |
| # Install the starter distro's deps into the uv environment | |
| uv run --with llama-stack bash -lc 'llama stack list-deps starter | xargs -L1 uv pip install' | |
| # Start Llama Stack (no more --image-type flag) | |
| uv run --with llama-stack llama stack run starter > server.log 2>&1 & | |
| SERVER_PID=$! | |
| # Wait up to ~120s for health; fail fast if process dies | |
| for i in {1..60}; do | |
| if curl -fsS http://localhost:8321/v1/models >/dev/null; then | |
| echo "Llama Stack Server started successfully." | |
| break | |
| fi | |
| if ! kill -0 "$SERVER_PID" 2>/dev/null; then | |
| echo "Server exited early. Logs:"; cat server.log; exit 1 | |
| fi | |
| sleep 2 | |
| done | |
| # Final health check | |
| curl -fsS http://localhost:8321/v1/models || { echo "Health check failed. Logs:"; cat server.log; exit 1; } | |
| - name: Install Hatch | |
| run: pip install --upgrade hatch | |
| - name: Lint | |
| if: matrix.python-version == '3.12' && runner.os == 'Linux' | |
| run: hatch run fmt-check && hatch run test:types | |
| - name: Generate docs | |
| if: matrix.python-version == '3.12' && runner.os == 'Linux' | |
| run: hatch run docs | |
| - name: Run tests | |
| run: hatch run test:cov-retry | |
| - name: Run unit tests with lowest direct dependencies | |
| run: | | |
| hatch run uv pip compile pyproject.toml --resolution lowest-direct --output-file requirements_lowest_direct.txt | |
| hatch -e test env run -- uv pip install -r requirements_lowest_direct.txt | |
| hatch run test:unit | |
| # Since this integration inherits from OpenAIChatGenerator, we run ALL tests with Haystack main branch to catch regressions | |
| - name: Nightly - run tests with Haystack main branch | |
| if: github.event_name == 'schedule' | |
| run: | | |
| hatch env prune | |
| hatch -e test env run -- uv pip install git+https://github.com/deepset-ai/haystack.git@main | |
| hatch run test:all | |
| - name: Send event to Datadog for nightly failures | |
| if: failure() && github.event_name == 'schedule' | |
| uses: ./.github/actions/send_failure | |
| with: | |
| title: | | |
| Core integrations nightly tests failure: ${{ github.workflow }} | |
| api-key: ${{ secrets.CORE_DATADOG_API_KEY }} |