TheAiSingularity / graphrag-local-ollama

Local models support for Microsoft's graphrag using ollama (llama3, mistral, gemma2 phi3)- LLM & Embedding extraction
MIT License
770 stars 115 forks source link

Does the project only support OpenAI key but not Azure Key? #62

Open JamieVC opened 2 months ago

JamieVC commented 2 months ago

Does the GRAPHRAG_API_KEY only accept the openai_chat and openai_embedding ?
How to also support azure_openai_chat and azure_openai_embedding ?


encoding_model: cl100k_base skip_workflows: [] llm: api_key: ${GRAPHRAG_API_KEY} type: openai_chat # or azure_openai_chat model: mistral model_supports_json: true # recommended if this is available for your model.

embeddings:

async_mode: threaded # or asyncio llm: api_key: ${GRAPHRAG_API_KEY} type: openai_embedding # or azure_openai_embedding model: nomic-embed-text api_base: http://localhost:11434/api