RAG (Retrieval-Augmented Generation) and basic chatbot application built using the LangChain, LangGraph, and LangSmith frameworks/tools.

• Retrieval-Augmented Generation (RAG): Combines retrieval techniques with generative AI to provide accurate and context-aware responses.
• Chatbot Functionality: Interactive chatbot powered by LangChain and LangGraph for seamless communication.
• Modular Frameworks: Utilizes LangSmith for advanced debugging and monitoring of AI workflows.
• Streamed Responses: Supports streaming responses for real-time interaction.

• LangChain: Framework for building applications with LLMs (Large Language Models).
• LangGraph: Tool for managing and executing complex workflows with AI agents.
• LangSmith: Framework for debugging and monitoring AI workflows.
• Python: Core programming language for the application.

1. Clone the repository:

git clone https://github.com/your-username/RAG-app.git
cd RAG-app

2. Create a virtual environment:

python3 -m venv venv
source venv/bin/activate

3. Install dependencies:

pip install -r requirements.txt

4. Ensure the Ollama server is running and the required models (e.g., deepseek-coder) are available.

1. Start the chatbot application:

python chatbot.py

2. Interact with the chatbot by typing your queries in the terminal.

3. To exit the chatbot, type quit.

1. create .env file and insert these important key-values in that:

   OPENAI_API_KEY=sk-your-openai-key-here

   GOOGLE_API_KEY=your-gemini-api-key

LANGSMITH_API_KEY=your-langsmith-key

LANGCHAIN_ENDPOINT="https://api.smith.langchain.com"

export LANGSMITH_TRACING=true

export LANGSMITH_API_KEY=your-langsmith-key

export OLLAMA_API_KEY="your_ollama_api_key"