https://github.com/mahikshith/langchain_rag_document_app

used gemini-pro as base LLM
https://github.com/mahikshith/langchain_rag_document_app

Last synced: 11 days ago
JSON representation

used gemini-pro as base LLM

• Host: GitHub
• URL: https://github.com/mahikshith/langchain_rag_document_app
• Owner: mahikshith
• Created: 2024-07-30T12:52:22.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-07-30T15:03:54.000Z (6 months ago)
• Last Synced: 2024-11-14T18:44:41.466Z (2 months ago)
• Language: Python
• Size: 6.58 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Langchain_RAG_app

 

Retrival augumented generation :

Retrieval-Augmented Generation (RAG) is the process of optimizing the output of a large language model, so it references an authoritative knowledge base outside of its training data sources before generating a response.  

Which means we can use the power LLMs to make it do something outside it's training knowledege.

In this exmaple we use GEMINI pro as think tank , FAISS as vector store to generate and store embeddings.

User query (based on the pdf) is taken as input and we retive the embeddings from the vector store and use it as context for the LLM to generate the answer.

This approach helps in improving the accuracy and relevance of the generated response.