Discussion

A Basic Local Retrieval-Augmented Generation (RAG) Tool with LangChain

Create a local RAG tool with LangChain to integrate real-time data into LLM responses

Mar 22, 202515 min readgregorsoutar.comUpdated Apr 26, 2025Read the article

#llm
#ollama
#rag
#langchain
#python

Written by

Gregor Soutar

@gregorsoutar · Edinburgh, Scotland

View profile

Software engineer at the UK Astronomy Technology Centre, currently developing instrument control software for MOONS, a next-generation spectrograph for the Very Large Telescope (VLT).

Responses

Markdown supported · ⌘↵ to post

No responses yet.

Search Hashnode

A Basic Local Retrieval-Augmented Generation (RAG) Tool with LangChain

Written by

Responses