cleanup

[emrgnt-cmplxty]

[!IMPORTANT] Replaced Zerox parser with vision-based parsers for PDF and image processing, updated ingestion configurations, and refactored related code.

• Behavior:
  • Removed Zerox parser and related configurations from action.yml, graphrag.mdx, and full.toml.
  • Added vision-based parsers VLMPDFParser and BasicPDFParser for PDF processing in pdf_parser.py.
  • Updated ImageParser in img_parser.py to use vision models for image processing.
  • Updated AudioParser in audio_parser.py to use Whisper transcription.
• Ingestion and Parsing:
  • Updated IngestionConfig in ingestion.py to include vision model configurations.
  • Refactored R2RIngestionProvider and UnstructuredIngestionProvider to use new parsers.
  • Removed Zerox-related code and dependencies from pyproject.toml.
• Misc:
  • Added new prompts vision_img.yaml and vision_pdf.yaml for vision-based parsing.
  • Updated R2RAuthProvider in r2r_auth.py to use send_password_reset_email().
  • Minor updates to logging and configuration files.

^{This description was created by for 760606fc549b6f0db58a5576542f0b66a3659020. It will automatically update as commits are pushed.}

[vercel[bot]]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
yc_demo	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Oct 28, 2024 11:55pm
yc-demo	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Oct 28, 2024 11:55pm

1 Skipped Deployment

| Name | Status | Preview | Comments | Updated (UTC) | | :--- | :----- | :------ | :------- | :------ | | **recommendation_platform** | ⬜️ Ignored ([Inspect](https://vercel.com/my-team-88dd52c0/recommendation_platform/DdMFLrV5EMzkpWESXnqKdBe1Qz4S)) | | | Oct 28, 2024 11:55pm |