{"name":"Athenaeum API Server","version":"0.1.0","description":"REST API for retrieving from a custom RPG knowledge base using RAG","base_url":"https://nomikos-api.vroomfogle.com","endpoints":[{"path":"/health","method":"GET","description":"Health check endpoint to verify the server is running"},{"path":"/models","method":"GET","description":"List available models"},{"path":"/search","method":"POST","description":"Search for context chunks matching a query for RAG applications","parameters":{"query":"The search query string","limit":"Number of results to return (default: 5)"}},{"path":"/answer","method":"POST","description":"Generate a single answer using RAG (one search, direct response)","parameters":{"messages":"Array of chat messages with role and content","model":"Model name (default: gpt-4o-mini)","temperature":"Sampling temperature (default: 0.3 - lower for factual accuracy)","max_tokens":"Maximum tokens in response (default: 4096 - ~3000 words)"}},{"path":"/chat","method":"POST","description":"Interactive chat with tool calling - LLM can search multiple times as needed","parameters":{"messages":"Array of chat messages with role and content","model":"Model name (default: gpt-4o-mini)","temperature":"Sampling temperature (default: 0.3 - lower for factual accuracy)","max_tokens":"Maximum tokens in response (default: 4096 - ~3000 words)"},"note":"LLM autonomously decides when and how many times to search the knowledge base"}],"documentation":"/docs","openapi":"/openapi.json"}