How are you doing RAG locally?

Question

I am curious how people are doing RAG locally with minimal dependencies for internal code or complex documents?Are you using a vector database, some type of semantic search, a knowledge graph, a hypergraph?

eajr · Accepted Answer

Local LibreChat which bundles a vector db for docs.

rahimnathwani · Answer

If your data aren't too large, you can use faiss-cpu and picklehttps://pypi.org/project/faiss-cpu/

motakuk · Answer

LightRAG, Archestra as a UI with LightRAG mcp

whattheheckheck · Answer

Anythingllm is promising

ramesh31 · Answer

SQLite with FTS5

nineteen999 · Answer

A little BM25 can get you quite a way with an LLM.