Add Gemini OCR plugin#49
Open
Bl0ck154 wants to merge 1 commit into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
pot-gemini-ocr-patchedto the recognize plugin list.list.json,README.md, andREADME_EN.md.Why another Gemini OCR plugin?
There is already a community Gemini OCR plugin, but this patched variant is aimed at a cleaner out-of-the-box experience for non-Chinese users and current Gemini Developer API usage.
Compared with the existing community plugin, this version changes:
流式输出,模型选择,自定义模型名称,推理长度, and其他参数.ModelService.ListModels, including current Gemini 3.1/2.5/2.0 options andlatestaliases.gemini-2.5-flash-preview-04-17andgemini-2.5-pro-exp-03-25from the main preset list.Custom model nameas the recommended path so users can paste future Gemini model IDs without waiting for plugin updates.gemini-*andmodels/gemini-*custom model formats by normalizing themodels/prefix.generateContentresponse parsing is simpler and more reliable for OCR in Pot.thinkingLevel: MINIMALguidance viagenerationConfigfor faster OCR-oriented responses..potextfile in GitHub Releases.Tested
The plugin was installed and tested in Pot on Windows with Gemini Developer API. Screenshot OCR works correctly with multilingual text using this setup:
https://generativelanguage.googleapis.com/v1betagemini-3.1-flash-liteNo{thinkingConfig:{thinkingLevel:MINIMAL}}Plugin
https://github.com/Bl0ck154/pot-gemini-ocr-patched
This is meant as a cleaned-up, tested Gemini OCR option for users who need reliable multilingual screenshot OCR in Pot.