Skip to main content
Glama

cognee-mcp

test_ollama.yml3.19 kB
name: test | ollama on: workflow_call: jobs: run_ollama_test: # needs 16 Gb RAM for phi4 runs-on: buildjet-4vcpu-ubuntu-2204 # services: # ollama: # image: ollama/ollama # ports: # - 11434:11434 steps: - name: Checkout repository uses: actions/checkout@v4 - name: Cognee Setup uses: ./.github/actions/cognee_setup with: python-version: '3.11.x' - name: Install torch dependency run: | uv add torch # - name: Install ollama # run: curl -fsSL https://ollama.com/install.sh | sh # - name: Run ollama # run: | # ollama serve --openai & # ollama pull llama3.2 & # ollama pull avr/sfr-embedding-mistral:latest - name: Start Ollama container run: | docker run -d --name ollama -p 11434:11434 ollama/ollama sleep 5 docker exec -d ollama bash -c "ollama serve --openai" - name: Check Ollama logs run: docker logs ollama - name: Wait for Ollama to be ready run: | for i in {1..30}; do if curl -s http://localhost:11434/v1/models > /dev/null; then echo "Ollama is ready" exit 0 fi echo "Waiting for Ollama... attempt $i" sleep 2 done echo "Ollama failed to start" exit 1 - name: Pull required Ollama models run: | curl -X POST http://localhost:11434/api/pull -d '{"name": "phi4"}' curl -X POST http://localhost:11434/api/pull -d '{"name": "avr/sfr-embedding-mistral:latest"}' - name: Call ollama API run: | curl -X POST http://localhost:11434/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{ "model": "phi4", "stream": false, "messages": [ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Whatever I say, answer with Yes." } ] }' curl -X POST http://127.0.0.1:11434/v1/embeddings \ -H "Content-Type: application/json" \ -d '{ "model": "avr/sfr-embedding-mistral:latest", "input": "This is a test sentence to generate an embedding." }' - name: Dump Docker logs run: | docker ps docker logs $(docker ps --filter "ancestor=ollama/ollama" --format "{{.ID}}") - name: Run example test env: OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }} PYTHONFAULTHANDLER: 1 LLM_PROVIDER: "ollama" LLM_API_KEY: "ollama" LLM_ENDPOINT: "http://localhost:11434/v1/" LLM_MODEL: "phi4" EMBEDDING_PROVIDER: "ollama" EMBEDDING_MODEL: "avr/sfr-embedding-mistral:latest" EMBEDDING_ENDPOINT: "http://localhost:11434/api/embeddings" EMBEDDING_DIMENSIONS: "4096" HUGGINGFACE_TOKENIZER: "Salesforce/SFR-Embedding-Mistral" run: uv run python ./examples/python/simple_example.py

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/topoteretes/cognee'

If you have feedback or need assistance with the MCP directory API, please join our Discord server