https://github.com/gopikrsmscs/chat-with-document-rag

Retrieval Augment Generation, Chat with your document using lang chain and open ai.
https://github.com/gopikrsmscs/chat-with-document-rag

chatbot langchain openai-api retreival-augmented-generation streamlit

Last synced: 26 days ago
JSON representation

Retrieval Augment Generation, Chat with your document using lang chain and open ai.

• Host: GitHub
• URL: https://github.com/gopikrsmscs/chat-with-document-rag
• Owner: gopikrsmscs
• License: mit
• Created: 2024-08-27T19:00:40.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-09-04T05:11:43.000Z (5 months ago)
• Last Synced: 2024-11-18T10:28:34.967Z (3 months ago)
• Topics: chatbot, langchain, openai-api, retreival-augmented-generation, streamlit
• Language: Python
• Homepage:
• Size: 6.11 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Chat with the Document (RAG): Attention is All You Need, Transformer

This project provides an interactive interface to chat with documents using a Retrieval-Augmented Generation (RAG) approach. It uses the "Attention is All You Need" Transformer paper as a primary document, Chroma for vector storage, and OpenAI's language model for chat responses. The application is built using Streamlit to provide an easy-to-use chat interface.

# Project Structure

- retrieval_augment_generation_chat.py: The main application file that sets up the Streamlit interface and handles the chat logic.

- document_indexing.ipynb: A Jupyter Notebook responsible for loading, splitting, and creating embeddings from the document.

- Transformer.pdf: The primary document used for the chat context.

- chromadb: Directory where the Chroma vector store persists the document embeddings.

# Requirements

- Python 3.8 or higher

- Streamlit

- LangChain

- OpenAI's API key

- Chroma

- PyPDFLoader

# Installation

- Clone the repository:

```bash

git clone [email protected]:gopikrsmscs/chat-with-document-rag.git

cd chat-with-document-rag

```

- Install the required dependencies:

```bash

pip install streamlit langchain chromadb PyPDFLoader openai

```

- Set up your OpenAI API key: Export your API key to the environment variable:

```bash

export OPENAI_API_KEY='your_openai_api_key'

```

![Chat Interface Output](/chat_interface.png)

# Features

- Document Interaction: Chat with the content of the Transformer paper using a retrieval-augmented generation approach.

- Contextual Responses: The model generates responses based on specific document sections, ensuring answers are relevant.

- Streamlit Interface: Basic interface to type queries and see responses.

# License

This project is licensed under the MIT License. See the LICENSE file for more details.