Chat Format Format prompts for multi-provider LLM inference with context retrieval. When to use When preparing prompts for different LLM providers (Claude, GPT, Gemini, Ollama) or building RAG pipelines with HNSW-powered context retrieval. Steps 1. Format chat — call with messages and target provider 2. Create HNSW index — call for context retrieval 3. Add documents — call to index documents 4. Route query — call to find relevant context 5. Check status — call for provider availability Supported providers - Anthropic (Claude) — native format - OpenAI (GPT) — chat completion format - Google (G…