Factual package intelligence from PyPI

mirage-benchmark 2.0.0 package intelligence

A Multiagent Framework for Generating Multimodal Multihop QA Datasets for RAG Evaluation

pip install mirage-benchmark

Current version
2.0.0
Python requirement
>=3.9
License
Apache-2.0
Distribution type
Pure Python wheel
Release files
2 (1 wheels, 1 source)
Download size
1.8 MiB
Release history
18 releases with files
Median release cadence
0 days

mirage-benchmark dependencies

PyPI declares 46 unique dependency rules for this release. Environment markers are shown when supplied by the project.

  1. torch >=2.0.0
  2. torchvision >=0.15.0
  3. numpy >=1.21.0
  4. scipy >=1.10.0
  5. Pillow >=10.0.0
  6. transformers >=4.44.0
  7. huggingface_hub <1.0,>=0.23.2
  8. sentence-transformers >=2.2.0
  9. safetensors >=0.4.0
  10. tokenizers >=0.20.0
  11. bitsandbytes >=0.43.0
  12. accelerate >=0.20.0
  13. peft >=0.11.0
  14. colpali-engine >=0.3.0
  15. docling >=2.0.0
  16. docling-core >=2.0.0
  17. pypdfium2 >=4.0.0
  18. easyocr >=1.7.0
  19. opencv-python-headless >=4.8.0
  20. faiss-cpu >=1.7.0
  21. bertopic >=0.16.0
  22. umap-learn >=0.5.0
  23. datamapplot >=0.4.0
  24. plotly >=5.0.0
  25. matplotlib >=3.5.0

The compact report shows 25 of 46 declarations. The interactive dependency graph loads the complete metadata.

Compatibility and release files

mirage-benchmark publishes 1 wheel and 1 source archive for version 2.0.0. Wheel platform tags: any.

Declared Python classifiers: 3.10, 3.11, 3.12, 3.9.

Release activity and sources

PyPI lists 18 releases with files. The first dated release is ; 18 releases fall within the 365 days preceding the latest dated release. The current release files were uploaded on . The preceding dated release was .