Skip to content

Conversation

@pull
Copy link

@pull pull bot commented Apr 1, 2024

See Commits and Changes for more details.


Created by pull[bot] (v2.0.0-alpha.4)

Can you help keep this open source service alive? 💖 Please sponsor : )

@pull pull bot added ⤵️ pull merge-conflict Resolve conflicts manually labels Apr 1, 2024
VikParuchuri and others added 28 commits June 5, 2025 07:46
Also add option to skip via config
Add an argument for the openai service image format

Using LM studio to serve a Qwen Vision LM appeared to crash with base64-encoded png, but not webp. To add compatability with this (and potentially other models) this adds a `openai_image_format` string that gets passed to the mimetype and PIL.save() arguments.

Defaults to ‘webp’ that it was originally hardcoded as.
Adding image format arg to OpenAI interface
tarun-menta and others added 30 commits September 23, 2025 17:32
Fix condition that incorrectly checked 'superscript or superscript' instead of 'superscript or subscript' in PDF text processing. This typo would prevent subscript text from having whitespace trimmed, causing inconsistent formatting between superscript and subscript spans. Detected using Claude Code.
Fix typo in superscript/subscript condition check
Enable passing arbitrary config
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

⤵️ pull merge-conflict Resolve conflicts manually

Projects

None yet

Development

Successfully merging this pull request may close these issues.