Metadata-Version: 2.1
Name: distyll-info
Version: 0.1.0
Summary: Information parsing assistant
License: MIT
Author: JP Hwang
Author-email: 61258750+databyjp@users.noreply.github.com
Requires-Python: >=3.10,<4.0
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
Requires-Dist: moviepy (>=1.0.3,<2.0.0)
Requires-Dist: openai (>=1.13.3,<2.0.0)
Requires-Dist: pydub (>=0.25.1,<0.26.0)
Requires-Dist: pypdf (>=4.1.0,<5.0.0)
Requires-Dist: weaviate-client (>=4.5.0,<5.0.0)
Requires-Dist: yt-dlp (>=2023.12.30,<2024.0.0)
Description-Content-Type: text/markdown

## Installation

Install `ffmpeg` (`brew install ffmpeg` on macOS)
Install packages from `requirements.txt` (`pip install -r requirements.txt`)

## Configuration

Set parameters as appropriate in `config.json`

## Usage

See `demo.ipynb` for an example.

- download_and_parse_pdf(pdf_url) -> pdf_text
- get_arxiv_paper(arxiv_url) -> {"title": title, "url": arxiv_url, "text": pdf_text}
- get_youtube_transcript(youtube_url) -> {"title": title, "date": date, "yt_url": youtube_url, "uploader": uploader, "channel": channel, "transcripts": transcripts}

## What happened to the old version?

Sorry! I'm working on making this more streamlined and better. For the old version, please see the `distyll_old` branch.

