AutoDocThinker is a production-ready Agentic RAG system that ingests PDFs, DOCX, URLs, and raw text into a Hybrid Search index (ChromaDB + BM25 + RRF + CrossEncoder), then answers natural language queries through four selectable LangGraph workflows — Naive, Advanced, CRAG, and Self-RAG.
semantic-search-engine semantic-search bm25 document-retrieval ai-agents reranker rag vector-search ai-assistant crag document-intelligence advanced-rag corrective-rag agentic-ai self-rag ai-document-search auto-document-analysis tool-usage-llm smart-document-search planner-executor-agent
-
Updated
May 16, 2026 - Python