https://github.com/shamspias/langchain-chat

langchain-chat is an AI-driven Q&A system that leverages OpenAI's GPT-4 model and FAISS for efficient document indexing. It loads and splits documents from websites or PDFs, remembers conversations, and provides accurate, context-aware answers based on the indexed data. Easy to set up and extend.
https://github.com/shamspias/langchain-chat

chatbot chatbots embedding-model embedding-models embedding-python embedding-similarity embedding-vectors faiss faiss-backend gpt-3 gpt-35-turbo gpt-4 gpt-j langchain langchain-python pinecone vector-database

Last synced: about 2 months ago
JSON representation

langchain-chat is an AI-driven Q&A system that leverages OpenAI's GPT-4 model and FAISS for efficient document indexing. It loads and splits documents from websites or PDFs, remembers conversations, and provides accurate, context-aware answers based on the indexed data. Easy to set up and extend.

• Host: GitHub
• URL: https://github.com/shamspias/langchain-chat
• Owner: shamspias
• Created: 2023-04-09T14:12:26.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2023-10-11T06:24:16.000Z (over 1 year ago)
• Last Synced: 2023-10-11T10:08:22.279Z (over 1 year ago)
• Topics: chatbot, chatbots, embedding-model, embedding-models, embedding-python, embedding-similarity, embedding-vectors, faiss, faiss-backend, gpt-3, gpt-35-turbo, gpt-4, gpt-j, langchain, langchain-python, pinecone, vector-database
• Language: Python
• Homepage:
• Size: 1.34 MB
• Stars: 58
• Watchers: 7
• Forks: 13
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# langchain-chat

langchain-chat is a powerful AI-driven Q&A system that leverages OpenAI's GPT-4 model to provide relevant and accurate

answers to user queries. The system indexes documents from websites or PDF files using FAISS (Facebook AI Similarity

Search) and offers a convenient interface for interacting with the data.

## Features

- Load and split documents from websites or PDF files

- Index documents using FAISS for efficient similarity search

- Utilize OpenAI's GPT-4 to generate human-like responses

- Remember previous conversations and provide context-aware answers

- Easy to set up and extend

## Installation

1. Clone the repository

2. Create a virtual environment

    ```bash

    python -m venv venv

    ```

3. Activate the virtual environment

    ```bash

    source venv/Scripts/activate

    ```

4. Install the dependencies

    ```bash

    pip install -r requirements.txt

    ```

5. Copy the `.env.example` file to `.env` and fill in the required values

   ```bash

   cp .env.example .env

   ```

   ```bash

   OPEN_AI_KEY = "sk-"

   WEBSITE_URLS="https://website1, https://website2"

   ```

6. Run the application

    ```bash

    python with_faiss.py

    ```

## Example Images

![Example 1](https://github.com/shamspias/langchain-chat/blob/main/images/conversation.PNG)