diff --git a/.github/workflows/test_ollama.yml b/.github/workflows/test_ollama.yml index cd1bf0aaf..7696de474 100644 --- a/.github/workflows/test_ollama.yml +++ b/.github/workflows/test_ollama.yml @@ -7,8 +7,8 @@ jobs: run_ollama_test: - - runs-on: buildjet-4vcpu-ubuntu-2204 + # needs 32 Gb RAM for phi4 in a container + runs-on: buildjet-8vcpu-ubuntu-2204 steps: - name: Checkout repository @@ -47,15 +47,15 @@ jobs: - name: Pull required Ollama models run: | - curl -X POST http://localhost:11434/api/pull -d '{"name": "phi3:mini"}' - curl -X POST http://localhost:11434/api/pull -d '{"name": "nomic-embed-text"}' + 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": "phi3:mini", + "model": "phi4", "stream": false, "messages": [ { "role": "system", "content": "You are a helpful assistant." }, @@ -65,7 +65,7 @@ jobs: curl -X POST http://127.0.0.1:11434/api/embed \ -H "Content-Type: application/json" \ -d '{ - "model": "nomic-embed-text", + "model": "avr/sfr-embedding-mistral:latest", "input": "This is a test sentence to generate an embedding." }' @@ -82,10 +82,10 @@ jobs: LLM_PROVIDER: "ollama" LLM_API_KEY: "ollama" LLM_ENDPOINT: "http://localhost:11434/v1/" - LLM_MODEL: "phi3:mini" + LLM_MODEL: "phi4" EMBEDDING_PROVIDER: "ollama" - EMBEDDING_MODEL: "nomic-embed-text" + EMBEDDING_MODEL: "avr/sfr-embedding-mistral:latest" EMBEDDING_ENDPOINT: "http://localhost:11434/api/embed" - EMBEDDING_DIMENSIONS: "768" - HUGGINGFACE_TOKENIZER: "nomic-ai/nomic-embed-text-v1" + EMBEDDING_DIMENSIONS: "4096" + HUGGINGFACE_TOKENIZER: "Salesforce/SFR-Embedding-Mistral" run: uv run python ./examples/python/simple_example.py