Retrieval augmented generation server for policy documents, exposing search, grounded Q&A with verified citations, and source management as MCP tools. Runs with local Ollama models for free or managed AWS backends, with an evaluation harness for retrieval and grounding metrics.
Enables semantic search and retrieval of information from technical documentation PDFs using RAG-powered natural language queries with Ollama embeddings and LLMs.
An MCP server that answers questions over insurance and regulatory documents using retrieval-augmented generation, returning grounded, cited passages via local embeddings and OpenSearch.