Skip to content

Whether you're building an internal chatbot for your company or a public-facing assistant, this starter kit helps you get up and running with your own data + ChatGPT.

License

Notifications You must be signed in to change notification settings

sumit9000/Traditional-Rag-End-to-End

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

3 Commits
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

Welcome to my GitHub! I'm a passionate developer working on cutting-edge projects in Generative AI, Retrieval-Augmented Generation (RAG), and LLMs. πŸš€


πŸ” Traditional RAG Pipeline using LangChain + FAISS + OpenAI

This project demonstrates how to build a Retrieval-Augmented Generation (RAG) system using the following stack:

  • 🧠 LLMs from OpenAI (e.g., gpt-3.5-turbo)
  • πŸ”— LangChain for orchestration
  • πŸ“š FAISS for vector similarity search
  • πŸ“ Streamlit for interactive UI

πŸ“‚ This is a great starting point for anyone looking to build production-level AI assistants using their own data.


🧰 Tech Stack

Python LangChain FAISS OpenAI Streamlit


βš™οΈ Features

  • πŸ“„ Upload PDF documents
  • 🧠 Embed text chunks using OpenAI embeddings
  • πŸ” Semantic similarity search via FAISS
  • πŸ€– Ask questions and get intelligent answers from your knowledge base
  • πŸ–ΌοΈ Interactive UI using Streamlit

πŸ§ͺ How to Run

  1. Clone the repo
    git clone https://github.com/yourusername/traditional-rag.git
    cd traditional-rag

About

Whether you're building an internal chatbot for your company or a public-facing assistant, this starter kit helps you get up and running with your own data + ChatGPT.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published