Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/neeldevenshah/rag_application_with_llm_and_mongodb
https://github.com/neeldevenshah/rag_application_with_llm_and_mongodb
Last synced: 4 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/neeldevenshah/rag_application_with_llm_and_mongodb
- Owner: NeelDevenShah
- Created: 2024-03-24T20:09:06.000Z (9 months ago)
- Default Branch: main
- Last Pushed: 2024-04-03T09:32:18.000Z (9 months ago)
- Last Synced: 2024-04-03T10:35:02.355Z (9 months ago)
- Language: Jupyter Notebook
- Size: 13.2 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Smart AI Based Text RAG
Smart AI Based Text RAG is an intelligent search system that utilizes cutting-edge technologies to provide users with efficient and intuitive text search capabilities. The system combines the power of Retrieval Augmented Generation (RAG) techniques and natural language processing to enable users to discover and explore information seamlessly.
## Overview
This project aims to develop an intelligent search system with the following key features:
- Text-based search: Users can input text queries to search for information based on various criteria such as topic, keywords, and context.
- Cloud-native architecture: The backend API is designed as a cloud-native application, allowing for easy integration into cloud-based ecosystems such as Microsoft Azure.
- Cost-effective solution: The system utilizes open-source technologies, including pre-trained language models from the Hugging Face library, to optimize cost and achieve high performance and accuracy without relying on commercial APIs.
## Features
- **Text-based search**: Analyzes user input, extracts relevant entities and keywords, and retrieves the most relevant information from the database using advanced retrieval algorithms.
- **Data sources**: Utilizes custom-made text datasets providing comprehensive information across different domains.
- **Vectorization**: Uses MongoDB for data storage and vectorization, enabling the application of Ranked Answer Grouping (RAG) for search functionality.
- **Custom API**: Implements a custom API using Flask, enabling users to interact with the RAG search system through a user-friendly interface.
- **Cloud deployment**: Deployed on Microsoft Azure, ensuring smooth operation, efficient inference processing, and proactive system management.
- **Open-source models**: Integrates pre-trained language models from the Hugging Face library for text embeddings, ensuring cost-effectiveness and customization.
## Installation and Setup
1. Clone the repository:
```bash
git clone https://github.com/NeelDevenShah/RAG_Application_with_LLM_and_MongoDB.git
```
2. Install dependencies:
```bash
pip install -r requirements.txt
```
3. Set up MongoDB Atlas for data storage and retrieval.
4. Deploy the Flask API on Microsoft Azure or any preferred cloud platform.
## Usage
1. Access the API endpoint through the provided URL.
2. Use text queries or upload images to search for restaurants, dishes, and menu items.
3. Explore search results and discover a wide range of food options available.
## Contributors
- Neel Shah - [email protected]
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.