AutoRAG
ActiveDescription
AutoRAG is an open-source RAG evaluation and optimization framework using AutoML-style automation to help developers automatically find the best RAG pipeline configurations and benchmark them.
Key Features
- AutoML-style automation to automatically find the optimal RAG pipeline for your data
- End-to-end data creation: parsing, chunking, and QA dataset generation
- Supports multiple parsing modules (pdfminer, etc.) and chunking strategies
- Dashboard for visualizing and comparing RAG pipeline evaluation results
- HuggingFace Spaces integration with pre-built chatbot and optimization demos
- Custom LLM and embedding model support for evaluation
Use Cases
💡 Automatically optimizing RAG pipeline configuration for specific datasets
💡 Evaluating and benchmarking different retrieval and generation modules
💡 Creating QA training datasets from raw documents for RAG evaluation
💡 Comparing RAG module combinations to find the best performing setup
💡 Building production-ready RAG systems with data-driven configuration
Categories
Quick Start
```bash
pip install AutoRAG
# Create QA dataset
python -c "
from autorag.parser import Parser
parser = Parser(data_path_glob='data/*')
parser.start_parsing('parse_config.yaml')
"
# Run optimization
autorag run --yaml rag_config.yaml --qa_path qa.parquet --corpus_path corpus.parquet
# Launch dashboard
autorag dashboard --project_path ./projects/[project_name]
```