AutoRAG
Automatically Evaluate RAG pipelines with your own data. Find optimal structure for new RAG product.
Installation
In a virtualenv (see these instructions if you need to create one):
pip3 install autorag
Dependencies
- fastapi
- ipywidgets-bokeh
- llama-index-readers-file
- llama-index-embeddings-openai-like
- rich
- grpcio-status
- llama-index
- tokenlog
- chromadb
- pymilvus
- pyarrow
- llama-index-embeddings-ollama
- llama-index-llms-openai-like
- banks
- langchain-core
- langchain-unstructured
- tqdm
- openai
- gradio
- sacrebleu
- langchain-community
- grpcio-tools
- fastparquet
- pinecone
- quart
- grpcio
- panel
- rouge-score
- streamlit
- pyngrok
- llama-index-embeddings-openai
- ipykernel
- llama-index-core
- scikit-learn
- voyageai
- numpy
- cohere
- ipywidgets
- qdrant-client
- aiohttp
- datasets
- langsmith
- grpcio-health-checking
- llama-index-llms-openai
- emoji
- couchbase
- mixedbread-ai
- pydantic
- pyyaml
- seaborn
- llama-index-llms-bedrock
- tiktoken
- pandas
- evaluate
- click
- langchain-upstage
- llama-index-retrievers-bm25
- weaviate-client
- rank-bm25
Releases
Issues with this package?
- Search issues for this package
- Package or version missing? Open a new issue
- Something else? Open a new issue