safzanpirani/local-rag

SPEC Major Project

Local RAG

Intelligent Conversations with Documents

Upload files for retrieval augmented generation (RAG) with open-source Large Language Models (LLMs).

Features:

• Offline Embeddings & LLMs Support
• Streamed Responses
• Conversation Memory
• Chat Export

Some Documentation and Set-up:

• Setup & Deploy the App
• Using Local RAG
• RAG Pipeline
• Resources