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?
Ask HN: How are you doing RAG locally?
1–10 of 166 posts
Re: Ask HN: How are you doing RAG locally?
#2Local LibreChat which bundles a vector db for docs.
Re: Ask HN: How are you doing RAG locally?
#3Anythingllm is promising
Re: Ask HN: How are you doing RAG locally?
#4If your data aren't too large, you can use faiss-cpu and pickle
Re: Ask HN: How are you doing RAG locally?
#5LightRAG, Archestra as a UI with LightRAG mcp
Re: Ask HN: How are you doing RAG locally?
#6SQLite with FTS5
Re: Ask HN: How are you doing RAG locally?
#7A little BM25 can get you quite a way with an LLM.
Re: Ask HN: How are you doing RAG locally?
#8try out chroma or better yet as opus to!
Re: Ask HN: How are you doing RAG locally?
#9If your data aren't too large, you can use faiss-cpu and pickle https://pypi.org/project/faiss-cpu/
For the uneducated, how large is too large? Curious.
Re: Ask HN: How are you doing RAG locally?
#10simple lil setup with qdrant