https://github.com/abeed04/chat-with-pdf-using-gemini-1.5-flash

Chat with the content of PDFs using an informative LLM powered by RAG.
https://github.com/abeed04/chat-with-pdf-using-gemini-1.5-flash

embeddings-similarity faiss-vector-database gemini-api langchain rag

Last synced: 6 days ago
JSON representation

Chat with the content of PDFs using an informative LLM powered by RAG.

• Host: GitHub
• URL: https://github.com/abeed04/chat-with-pdf-using-gemini-1.5-flash
• Owner: abeed04
• License: mit
• Created: 2024-06-21T13:43:11.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2024-06-24T06:58:23.000Z (5 months ago)
• Last Synced: 2024-06-24T08:07:32.793Z (5 months ago)
• Topics: embeddings-similarity, faiss-vector-database, gemini-api, langchain, rag
• Language: Python
• Homepage:
• Size: 36.1 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
This project enables users to engage in an informative and interactive conversation with the content of PDF documents using Gemini-1.5 Flash, a large language model (LLM) empowered by Retrieval-Augmented Generation (RAG). RAG enhances Gemini's ability to process and respond to your questions by leveraging external knowledge sources like PDF files.




Key Technologies:




-->Gemini-1.5 Flash: A powerful LLM from Google AI, trained on a massive dataset of text and code.




-->Retrieval-Augmented Generation (RAG): A technique that integrates external information retrieval into the LLM, allowing it to ground its responses in factual content from PDFs.




-->FIASS (Flexible Information Access System): (Potentially) A framework for information retrieval, likely used to manage and search within PDF documents. (If FIASS is not directly involved, remove this line.)




-->RecursiveCharacterTextSplitter: A tool that breaks down text into smaller units for processing by the LLM.




-->Google Generative AI Embeddings: Pre-trained vector representations of text that can aid in information retrieval and similarity comparisons