A real-time, low-latency Voice AI Assistant built with Vapi.ai, FastAPI, and LangChain, featuring a dynamic RAG pipeline powered by Supabase pgvector and Llama 3.3 70B for instant, document-grounded voice conversations.
A production-grade Adaptive RAG platform featuring smart PDF table detection, Jina Web scraping, multi-tenant Supabase pgvector vector search, Groq Llama 3.3 completions, and persistent latency benchmark logging.
Add a description, image, and links to the supabase-pgvector topic page so that developers can more easily learn about it.
To associate your repository with the supabase-pgvector topic, visit your repo's landing page and select "manage topics."