Overview
Every endpoint of the API at a glance.
Every endpoint lives under the base /api/v1. Send the full history with every chat call; chat_id keeps file references and working files associated with the conversation.
GET /api/v1/healthLiveness — is the process running?GET /api/v1/readyReadiness — is the LLM provider reachable?POST /api/v1/chatAnswer in one piece as JSON.POST /api/v1/chat/streamAnswer as SSE — thinking, tools, answer.GET /api/v1/modelsThe models /chat accepts.GET /api/v1/toolsEvery registered tool with its schema.POST /api/v1/visionLook at images by address (JSON).POST /api/v1/vision/uploadLook at uploaded image files (multipart).GET /api/v1/promptsList system prompts.GET /api/v1/prompts/{name}Fetch one prompt verbatim.
Base URL
Every path hangs off api_prefix — /api/v1 by default. In the examples the backend runs locally at http://localhost:8000.
Non-production only
GET /docs (Swagger UI) and GET /openapi.json are only available when the environment is not production.