langchain4j: open-ai: chat-model: # Replace with your LLM configs # Note: The default API key `demo` is provided by langchain4j community # which limits 1000 tokens per request. base-url: https://api.openai.com/v1 api-key: demo model-name: gpt-3.5-turbo temperature: 0.0 timeout: PT60S in-memory: embedding-model: model-name: bge-small-zh embedding-store: persist-path: /tmp # ollama: # chat-model: # base-url: http://localhost:11434 # api-key: demo # model-name: qwen:0.5b # temperature: 0.0 # timeout: PT60S # chroma: # embedding-store: # baseUrl: http://0.0.0.0:8000 # timeout: 120s # milvus: # embedding-store: # host: localhost # port: 2379 # uri: http://0.0.0.0:19530 # token: demo # dimension: 512 # timeout: 120s