https://github.com/murtaza-arif/rag-agnostic-guide
A comprehensive guide to building Retrieval-Augmented Generation (RAG) systems using various open-source tools.
https://github.com/murtaza-arif/rag-agnostic-guide
ai gpt4all llm lmstudio localai ml mlflow mlops ollama openlit python rag ragflow vllm
Last synced: 24 days ago
JSON representation
A comprehensive guide to building Retrieval-Augmented Generation (RAG) systems using various open-source tools.
- Host: GitHub
- URL: https://github.com/murtaza-arif/rag-agnostic-guide
- Owner: Murtaza-arif
- Created: 2024-11-29T18:16:37.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2025-02-11T16:06:14.000Z (4 months ago)
- Last Synced: 2025-03-31T05:46:02.102Z (2 months ago)
- Topics: ai, gpt4all, llm, lmstudio, localai, ml, mlflow, mlops, ollama, openlit, python, rag, ragflow, vllm
- Language: HTML
- Homepage:
- Size: 19.6 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 10
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# RAG-Agnostic-Guide
A comprehensive guide and collection of examples for building production-ready Retrieval-Augmented Generation (RAG) systems using various open-source tools. This repository demonstrates different approaches to implementing RAG pipelines, from local LLM deployment to vector stores and evaluation frameworks.
## Key Features
- Multiple local LLM deployment options
- Vector store implementations and examples
- RAG evaluation frameworks and metrics
- Production-ready examples
- Comprehensive documentation for each component
## Repository Structure
### Local LLM Solutions
- **[Ollama](ollama/)** - Easy-to-use tool for running LLMs locally
- **[LocalAI](localai/)** - OpenAI-compatible API for local model deployment
- **[LMStudio](lmstudio/)** - Desktop application with user-friendly interface
- **[vLLM](vllm_inference/)** - High-performance inference engine with PagedAttention
### Vector Stores & Search
- **[Milvus Demo](milvus_demo/)** - E-commerce semantic search implementation
- **[OpenLit](openlit/)** - Fast inference engine with CUDA optimization
### RAG Components
- **[Basic RAG](ollama/basic_rag/)** - Simple RAG implementation example
- **[Resume Screener](resume_screener/)** - Practical RAG application for resume analysis
### Evaluation & Testing
- **[RAG Evaluator](rag_evaluator/)** - Tools and metrics for RAG evaluation
- **[DeepEval Demo](deepeval_demo/)** - Comprehensive RAG evaluation using DeepEval
## Getting Started
Each component has its own setup instructions in its respective directory. Generally, you'll need:
### Prerequisites
- Python 3.8+
- Conda (recommended) or pip
- GPU (optional, but recommended for better performance)
### General Setup
1. Clone the repository:
```bash
git clone https://github.com/yourusername/RAG-Agnostic-Guide.git
cd RAG-Agnostic-Guide
```
2. Choose a component and follow its specific setup instructions in the respective README.
## Documentation
Each component includes detailed documentation covering:
- Setup instructions
- Usage examples
- API references
- Performance considerations
- Best practices
## Contributing
Contributions are welcome! Please:
1. Fork the repository
2. Create a feature branch
3. Commit your changes
4. Push to the branch
5. Create a Pull Request
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
## Acknowledgments
Special thanks to all the open-source projects and their maintainers that make this guide possible:
- Ollama team
- LocalAI community
- LMStudio developers
- vLLM contributors
- Milvus community
- And many others!
For detailed information about specific components, please refer to their respective directories.