PyPI page
Author:
ajia
License:
MIT
Summary:
Ingest sources with proper citation — PDF, URL, media, Office, DJVU
Latest version:
0.14.0
Required dependencies:
citeproc-py
|
dspy-ai
|
litellm
|
lxml
|
pymupdf
|
pypdf2
|
pypinyin
|
python-dotenv
|
pyyaml
|
readability-lxml
|
requests
|
trafilatura
Optional dependencies:
crawl4ai
|
fasttext
|
mineru
|
ocrmypdf
|
paddleocr
|
paddlepaddle
|
playwright
|
pyannote-audio
|
pymediainfo
|
pymupdf4llm
|
whisperx
|
yt-dlp
Downloads last day:
9
Downloads last week:
137
Downloads last month:
386
7-day smoothing