Chat with your pdfs using Retrieval Augmented Generation.
This Retrieval Augmented Generation (RAG) is a project aimed at optimizing the outputs of LLMS by incorporating a retrieval-based approach. Unlike traditional generative models that generate responses from scratch, RAG systems first retrieve relevant information from a large corpus and then use this retrieved information to guide the generation process. This approach enables the generation of more coherent, contextually relevant, and factually accurate responses.
To run the ChatBot project locally, follow these steps:
-
Clone the Repository: git clone {repo url}
-
Install Dependencies: Navigate to the project directory and install the required dependencies: pip install -r requirements.txt
-
Add Google API Key: Obtain a OPENAI API key and add it to the .env file in the project directory: OPENAI_API_KEY=your_openai_api_key
-
Run the Project: Launch the chatbot application using Streamlit: streamlit run rag.py
-
Interact with the ChatBot: Open your web browser and navigate to the provided URL to interact with ChatBot.
The project structure is organized as follows:
-
rag.py: Main application file containing the Streamlit user interface and chatbot functionality.
-
requirements.txt: List of Python dependencies required to run the project.
-
.env: Environment configuration file for storing sensitive information (e.g., API keys).
-
README.md: Project documentation file.