rag-platform
Open-source RAG platform for pluggable document ingestion, multimodal indexing, hybrid search, tenant-isolated APIs, RBAC, citations, and MCP-based AI agent integration.
- 12
- Python
- MIT
- 3 mo ago
Open-source RAG platform for pluggable document ingestion, multimodal indexing, hybrid search, tenant-isolated APIs, RBAC, citations, and MCP-based AI agent integration.
Data ingestion service for the Agent Landing Zone. Processes PDFs, images, spreadsheets, transcripts and SharePoint content into grounding knowledge for agents, with smart chunking and multimodal embeddings.
Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server
Production-grade RAG chatbot with a FastAPI + LangGraph backend (Pinecone vector search + Groq LLM + Tavily web fallback) and a Streamlit chat UI, secured via API key and observable in LangSmith.
AI agent for market and audience research: web research with citations, document ingestion for RAG, audience/persona profiling — backed by real web-search and document APIs