RAG-basics

Welcome to the RAG-basics repository! This project showcases various applications of Retrieval-Augmented Generation (RAG) techniques using LangChain and Ollama. The focus is on enhancing information retrieval and interaction through the integration of document processing and natural language models.

Features

• PDF Processing: Upload and process PDF documents to extract meaningful content.
• Excel File Processing: Upload and process Excel files to retrieve and interact with their data.
• Vector Database Creation: Build and manage vector databases for efficient document retrieval.
• Natural Language Queries: Interact with documents using natural language questions, leveraging language models for enhanced responses.
• User-Friendly Interface: Streamlit-based applications for easy interaction and exploration.

Installation

To get started, clone the repository and install the required packages:

git clone https://github.com/agkavin/RAG-basics.git
cd RAG-basics
pip install -r requirements.txt

Usage

Run the Streamlit Application: Start the application using the following command:

streamlit run app.py

Upload a PDF: Use the provided interface to upload a PDF file for processing. Ask Questions: Once the PDF is processed, you can ask questions about its content.

Output