Скачать или смотреть RAG Ollama Demo

GITHUB: https://github.com/CantBeSubh/rag-ollama

RAG Ollama is an Adaptive RAG Agent web app that uses LLM to answer questions about a PDF document. The app uses a graph-based approach to answer questions. The graph is built using LangGraph.

The RAG technique used is called Adaptive RAG. Why is this called Adaptive?

Routing: Route questions to different retrieval approaches
Fallback: Fallback to web search if docs are not relevant to the query
Self-correction: Fix answers with/ hallucinations or don’t address question

Follow me on Twitter:   / cantbesubh  

Timecode
0:00 - RAG Ollama System Arch
0:05 - Starting frontend and backend server
1:02 - Webapp preview
1:31 - PROCESSING....
2:00 - OUTPUT(for answer found in docs)
2:08 - Langsmith Traces(for answer found in docs)
2:46 - PROCESSING....
3:12 - OUTPUT(for answer NOT found in docs)
3:26 - Langsmith Traces(for answer NOT found in docs)

#frontend
#nextjs14
#tailwindcss
#shadcnui
#clerk
#backend
#ollama
#lamma3
#langchain
#langraph
#langsmith
#chromadb
#pypdfloader
#fastapi
#uppy.io