🤖 Multi-Chatbot RAG Application
Intelligent Document Interaction Platform

A sophisticated Streamlit-based conversational AI platform featuring Retrieval-Augmented Generation (RAG) for enhanced data interaction. Chat with CSV files, PDF documents, and web URLs using advanced language models from Google Gemini and Meta Llama.

🎯 Core Capabilities:

✓ Chat with CSV: Query structured data with natural language
✓ Chat with PDF: Extract and analyze document content
✓ Chat with URL: Retrieve and process web page information
✓ RAG Integration: Context-aware responses using vector embeddings
✓ Multi-Model Support: Google Gemini & Meta Llama models
✓ 95% Query Resolution: A/B tested for accuracy

💼 Business Applications:

• Enterprise knowledge management systems
• Document analysis and summarization tools
• Customer support with document context
• Research assistants for academic papers
• Data analytics chatbots for business intelligence
• Legal document review and Q&A systems

Live Demo GitHub Repository Setup Guide

Tech Stack: Python • Streamlit • LangChain • Google Gemini • Meta Llama • RAG • Vector Embeddings • FAISS

🚀 Advanced RAG Capabilities

Multiple interaction modes powered by Retrieval-Augmented Generation for enhanced accuracy and context

Technology Stack

The tools and technologies that power the Multi-Chatbot Application.

Interactive Setup Guide

Follow this step-by-step guide to get the chatbot running locally.

Check Your Tools

Before you begin, ensure you have Python installed and can get API keys for the required services.

Python 3.8 or newer
Active Google Cloud API Key
Active Together AI API Key

Install Dependencies

Open your terminal in the project directory and run the following command to install all the necessary Python packages.

pip install streamlit langchain-experimental langchain-core langchain-google-genai langchain-community langchain-text-splitters requests beautifulsoup4 python-dotenv langchain-together

Configure API Keys & Run Server

Create a folder named .streamlit in your project root, and inside it, create a file named secrets.toml.

# .streamlit/secrets.toml
google = "YOUR_GOOGLE_API_KEY_HERE"
together = "YOUR_TOGETHER_API_KEY_HERE"

Finally, run the Streamlit application. It will be accessible at `http://localhost:8501`.

streamlit run app.py

Usage Demo

See examples of questions you can ask in different modes.

Click a button below to see an example interaction.

Troubleshooting FAQ

Common questions and solutions to get you back on track.

🤖 Multi-Chatbot RAG Application Intelligent Document Interaction Platform