PyPI page
Home page
Author:
None
Summary:
General-purpose, AI-enabled Intelligent Document Processing framework for Python. OCR + multimodal extraction with Pydantic schemas, confidence assessment, HITL review, and a built-in eval harness. Supports OpenAI, Anthropic, Ollama, and 8 China LLMs.
Latest version:
0.3.1.post1
Required dependencies:
httpx
|
pdfplumber
|
pydantic
|
python-dotenv
|
rich
|
streamlit
|
tenacity
|
tiktoken
|
typer
Optional dependencies:
accelerate
|
anthropic
|
datasets
|
docling
|
fastapi
|
httpx
|
huggingface-hub
|
hypothesis
|
mkdocs
|
mkdocs-material
|
mkdocstrings
|
mypy
|
ollama
|
openai
|
pandas
|
pdf2image
|
pillow
|
pymdown-extensions
|
pytesseract
|
pytest
|
pytest-asyncio
|
pytest-benchmark
|
reportlab
|
ruff
|
safetensors
|
torch
|
transformers
|
types-pyyaml
|
uvicorn
Downloads last day:
0
Downloads last week:
232
Downloads last month:
232