PyPI page
Home page
Author:
LlamaIndex
Summary:
ExtractBench: a benchmark and evaluation harness for schema-guided document extraction on real-world enterprise documents
Latest version:
1.0.0
Required dependencies:
aiohttp
|
anls-star
|
apted
|
autoevals
|
beautifulsoup4
|
bleach
|
fire
|
fuzzysearch
|
huggingface-hub
|
lxml
|
markdown
|
markdown2
|
numpy
|
pandas
|
parse-bench
|
pydantic
|
python-dateutil
|
python-dotenv
|
python-levenshtein
|
rapidfuzz
|
requests
|
rich
|
scikit-learn
|
scipy
|
unidecode
Optional dependencies:
amazon-textract-textractor
|
anthropic
|
azure-ai-documentintelligence
|
boto3
|
chunkr-ai
|
datalab-python-sdk
|
docling-core
|
extend-ai
|
google-cloud-documentai
|
google-genai
|
httpx
|
infinity-parser2
|
landingai-ade
|
llama-cloud
|
mypy
|
numba
|
openai
|
pdf2image
|
pillow
|
pymupdf
|
pypdf
|
pytesseract
|
pytest
|
reductoai
|
ruff
|
unstructured-client
|
warp-ingest
Downloads last day:
6
Downloads last week:
33
Downloads last month:
137
7-day smoothing