Package Insights
Package Risks
- No releases in 267 days despite active commits
((week_daily_avg - month_daily_avg) / month_daily_avg) * 100Weekly Downloads
GitHub Stars
Downloads by OS
Python Versions
Top Countries
Dependencies
- aiohttp <4.0.0,>=3.12.14
- amazon-textract-textractor <2.0.0,>=1.3.2
- aryn-sdk >=0.2.6
- async-timeout >4.0.0
- beautifulsoup4 <5.0.0,>=4.13.1
- boto3 <2.0.0,>=1.28.70
- boto3-stubs <2.0.0,>=1.35.12
- dateparser <2.0.0,>=1.2.0
- diskcache <6.0.0,>=5.6.3
- fasteners <0.20,>=0.19
- fsspec ==2024.2.0
- httpcore >=1.0.9
- jinja2 <4.0.0,>=3.1.6
- msgpack <2.0.0,>=1.1.1
- nanoid <3.0.0,>=2.0.0
- numpy <2.0.0
- openai <2.0.0,>=1.60.2
- overrides <8.0.0,>=7.7.0
- pandas <3.0.0,>=2.3.0
- pdf2image <2.0.0,>=1.16.3
- pillow <12.0.0,>=11.3.0
- protobuf <6.0.0,>=5.29.5
- pyarrow <21.0.0,>=20.0.0
- pydantic <3.0.0,>=2.8.2
- pypdf <6.0.0,>=5.1.0
- ray <3.0.0,>=2.46.0
- rich <14.0.0,>=13.7.1
- setuptools >=78.1.1
- structlog <25.0.0,>=24.2.0
- tenacity <9.0.0,>=8.4.1
- tiktoken <0.9.0,>=0.8.0
- tornado >=6.5.0
- typing-extensions <5.0.0,>=4.12.2
- urllib3 <3,>=2.5.0
28 optional dependencies
- anthropic[anthropic]
- apted[eval]
- datasets[eval]
- duckdb[duckdb]
- easyocr[local-inference]
- elasticsearch[elasticsearch]
- furo[docs]
- google-genai[google-genai]
- myst-parser[docs]
- neo4j[neo4j]
- nltk[legacy-partitioners]
- opensearch-py[opensearch]
- paddleocr[local-inference]
- pdfminer-six[local-inference]
- pinecone[pinecone]
- pinecone-text[pinecone]
- pytesseract[local-inference]
- python-pptx[legacy-partitioners]
- qdrant-client[qdrant]
- rouge[eval]
- sentence-transformers[local-inference]
- sphinx[docs]
- timm[local-inference]
- torch[local-inference]
- torchvision[local-inference]
- transformers[local-inference]
- unstructured[legacy-partitioners]
- weaviate-client[weaviate]