RAG Application on Unstructured Data

This project is a demonstration of a Retrieval-Augmented Generation (RAG) application that works with unstructured data. It uses a Large Language Model (LLM) to answer questions based on the content of a provided web page.

How it works

The application fetches content from a specified URL, splits it into manageable chunks, and then uses a vector store to efficiently retrieve relevant information. When a user asks a question, the application retrieves the most relevant context from the vector store and uses it to generate a concise and accurate answer.

Technologies Used

• LangChain: A framework for developing applications powered by language models.
• Google Gemini: The Large Language Model used for generating answers.
• ChromaDB: A vector store for efficient similarity search.
• Streamlit: For creating the user interface.

Setup and Usage

1. Clone the repository:

   git clone https://github.com/your-username/RAG_App_Unstructed.git

2. Install the dependencies:

   pip install -r requirements.txt

3. Set up your environment variables:

   Create a .env file in the root directory and add your Google API key:

   GOOGLE_API_KEY="your-google-api-key"
   

4. Run the application:

   python app.py

Todo

Build an android app and deploy it