https://github.com/sankethsj/phi3-rag-application
This project leverages the Phi3 model and ChromaDB to create a Retrieval-Augmented Generation (RAG) application.
https://github.com/sankethsj/phi3-rag-application
chromadb phi3 rag
Last synced: 21 days ago
JSON representation
This project leverages the Phi3 model and ChromaDB to create a Retrieval-Augmented Generation (RAG) application.
- Host: GitHub
- URL: https://github.com/sankethsj/phi3-rag-application
- Owner: sankethsj
- License: mit
- Created: 2024-06-08T04:54:58.000Z (11 months ago)
- Default Branch: master
- Last Pushed: 2024-09-14T04:37:12.000Z (8 months ago)
- Last Synced: 2025-04-28T14:05:08.001Z (21 days ago)
- Topics: chromadb, phi3, rag
- Language: Jupyter Notebook
- Homepage:
- Size: 1.1 MB
- Stars: 6
- Watchers: 1
- Forks: 4
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# RAG Application with Phi3 Model and ChromaDB
Welcome to the RAG (Retrieval-Augmented Generation) application repository! This project leverages the Phi3 model and ChromaDB to read PDF documents, embed their content, store the embeddings in a database, and perform retrieval-augmented generation.
## Table of Contents
- [Introduction](#introduction)
- [Features](#features)
- [Installation](#installation)
- [Usage](#usage)
- [Contributing](#contributing)
- [License](#license)
## Introduction
This repository contains a RAG application that reads PDF files, generates embeddings using the Alibaba-NLP/gte-large-en-v1.5 model, stores these embeddings in ChromaDB, and performs retrieval-augmented generation to provide contextual answers based on the embedded content. The system is designed to enhance the capability of answering queries by leveraging the context from the embedded documents.
## Features
- **PDF Reading**: Extracts text content from PDF documents.
- **Embedding Generation**: Utilizes the Alibaba-NLP/gte-large-en-v1.5 model to generate embeddings for the extracted text.
- **Database Storage**: Stores the generated embeddings in ChromaDB.
- **Retrieval-Augmented Generation**: Retrieves relevant embeddings from the database and generates contextually accurate responses.
## Installation
**Note:** On first installation, this script will download the necessary NLTK stopwords, the NLP embedding model, and the large language model (LLM). As a result, the initial execution may take longer than subsequent runs.
To get started with the RAG application, follow these steps:
1. **Download Ollama on to your desktop**:
This is required to run LLM model locally. [Download Ollama](https://ollama.com/download)
1. **Clone the repository**:
```bash
git clone https://github.com/sankethsj/phi3-rag-application.git
cd phi3-rag-application
```
2. **Create a virtual environment and activate it**:
```bash
python -m venv venv
source venv/bin/activate # On Windows, use `venv\Scripts\activate`
```
3. **Install the required dependencies**:
```bash
pip install -r requirements.txt
```
## Usage
### Run the script
```bash
python main.py
```
### (Optional) Run the notebook
This is more interactive, you can see what's going in each step.
1. Open [RAG-Workbook.ipynb](/RAG-Workbook.ipynb) and run all cells.
## Contributing
We welcome contributions to enhance the capabilities of this RAG application. To contribute, please follow these steps:
1. Fork the repository.
2. Create a new branch for your feature or bugfix:
```bash
git checkout -b feature-name
```
3. Make your changes and commit them with descriptive messages.
4. Push your changes to your fork:
```bash
git push origin feature-name
```
5. Create a pull request to the main repository.
## License
This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for more details.
---
Thank you for using the RAG application with the Phi3 model and ChromaDB. If you encounter any issues or have any questions, please feel free to open an issue on this repository.