wdoc

PyPI page
Home page
License: AGPLv3
Summary: A perfect AI powered RAG for document query and summary. Supports ~all LLM and ~all filetypes (url, pdf, epub, youtube (incl playlist), audio, anki, md, docx, pptx, or any combination!)
Latest version: 5.2.1
Required dependencies: beartype | beautifulsoup4 | blake3 | chonkie | ddgs | dill | duckduckgo-search | faiss-cpu | fire | ftfy | goose3 | grandalf | joblib | langchain | langchain-classic | langchain-community | langchain-litellm | langchain-openai | langfuse | lazy-import | litellm | loguru | nest-asyncio | nltk | openparse | pandas | pdf2image | pdfminer-six | pdfplumber | persistdict | pillow-heif | platformdirs | playwright | prompt-toolkit | pyfiglet | pymupdf | pypdfium2 | rich | rtoml | scikit-learn | scipy | sqlalchemy | tldextract | tqdm | trio | unstructured | uuid6
Optional dependencies: ankipandas | audioop-lts | build | bumpver | deepgram-sdk | docx2txt | fasttext-langdetect | ffmpeg-python | httpx | karakeep-python-api | langdetect | logseqmarkdownparser | pandoc | pdftotext | pre-commit | py-ankiconnect | pydub | pytest | pytest-xdist | pyzotero | ruff | torchaudio | twine | unstructured | wdoc | youtube-transcript-api | yt-dlp

Downloads last day: 6
Downloads last week: 166
Downloads last month: 269
7-day smoothing