https://github.com/omjavia/doc_query_genie
Rag (Retreival Augmented Generation) Python solution with LLama3, LangChain, Ollama and ChromaDB in a Flask API based solution
https://github.com/omjavia/doc_query_genie
chromadb langchain-python llama3-meta-ai ollama rag
Last synced: 6 months ago
JSON representation
Rag (Retreival Augmented Generation) Python solution with LLama3, LangChain, Ollama and ChromaDB in a Flask API based solution
- Host: GitHub
- URL: https://github.com/omjavia/doc_query_genie
- Owner: OmJavia
- Created: 2024-06-20T11:37:43.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-02-08T09:17:29.000Z (8 months ago)
- Last Synced: 2025-02-08T10:24:58.115Z (8 months ago)
- Topics: chromadb, langchain-python, llama3-meta-ai, ollama, rag
- Language: Python
- Homepage:
- Size: 1.11 MB
- Stars: 14
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 📜 Doc_Query_Genie
🚀 **A Powerful Retrieval-Augmented Generation (RAG) API using LLama3, LangChain, Ollama, and ChromaDB**
## 🔍 About The Project
**Doc_Query_Genie** is a cutting-edge RAG-based Python solution that enhances information retrieval and generation using **Flask API**. With the power of **LLama3, LangChain, Ollama, and ChromaDB**, this tool provides a seamless experience for querying both general knowledge and custom document uploads.
### ✨ Key Features
✅ **AI-Powered Chat** – Use it like OpenAI's ChatGPT to ask any question.
✅ **PDF Intelligence** – Upload a PDF and ask context-specific questions.
✅ **Source Referencing** – Get precise answers with citations from the document (paragraph/line references).
✅ **Fast & Efficient** – Optimized for quick and reliable response generation.
✅ **Easy Integration** – Simple API setup to integrate with other applications.
This project brings the best of **AI-driven retrieval** and **context-aware generation**, making it a versatile tool for researchers, students, and professionals.
## 🚀 Getting Started
1. **Clone the repository**
```sh
git clone https://github.com/yourusername/Doc_Query_Genie.git
cd Doc_Query_Genie
```
2. **Install dependencies**
```sh
pip install -r requirements.txt
```
3. **Run the application**
```sh
python app.py
```
4. **Use the API**
- Access it at `http://127.0.0.1:5000/`
- Upload PDFs and start querying
## 🤝 Contributing
We welcome contributions! Feel free to submit issues or pull requests.
---
🌟 **If you find this project helpful, please consider giving it a star!**