Custom-Chatbot-using-Langchain

A knowledge-driven chatbot application that leverages LangChain for retrieval-augmented generation (RAG) using content from specified URLs. This project uses ChromaDB for storing embeddings and Flask for the web interface, creating a chatbot capable of generating precise answers based on a specific knowledge base.

Features

• Custom Knowledge Base: Scrapes and stores data from URLs for use in chatbot responses.
• RAG Architecture: Combines retrieval from the knowledge base with a language model to answer questions contextually.
• ChromaDB Integration: Uses ChromaDB for efficient vector storage and retrieval of document embeddings.
• Flask Web Interface: Lightweight, interactive web front end for user interaction.

Tech Stack

• LangChain: Manages the chatbot pipeline, including embedding generation and retrieval processes.
• ChromaDB: Stores and retrieves embeddings generated by the chatbot.
• Flask: Serves the web interface, handling user input and displaying responses.
• HTML and CSS: Provides a simple frontend for interacting with the chatbot.

Getting Started

Prerequisites

• Python 3.7 or above
• Git (for cloning the repository)

Installation

1. Clone the Repository

   git clone https://github.com/YourUsername/Custom-Chatbot-using-Langchain.git
   cd Custom-Chatbot-using-Langchain
   

2. Set Up the Environment

   python -m venv venv
   source venv/bin/activate  # On Windows use `venv\Scripts\activate`

3. Install Dependencies

   pip install -r requirements.txt

Configuration

• Ensure the URL sources are correctly defined in the script, under urls (I have included some random url).
• You can also include multiple url under urls

Running the ChatBot

1. Start the Flask Application

   python app.py

2. Access the Chatbot
   • Open your browser and go to http://127.0.0.1:5000 to interact with the chatbot. (as I have mentioned that port in the code, you can also change as per you wish)

License

This project is licensed under the MIT License.