getomni-ai / zerox

PDF to Markdown with vision models

https://getomni.ai/ocr-demo

Repository from Github https://github.comgetomni-ai/zerox

getomni-ai/zerox Issues

Supporting Vision models from Groq
Updated 14 days ago10
UnicodeEncodeError: 'gbk' codec can't encode character '\u2081' in position 7318: illegal multibyte sequence
Updated 19 days ago2
Useless re.sub in format_markdown?
Updated a month ago
Is there a parameter to control the sensitive fields like name , password in PDF file?
Closed a month ago2
Using Llama3.2-vision
Updated a month ago9
Handle ratelimit and retry
Updated a month ago2
supporting Gemini
Updated a month ago2
Add usage considerations to the docs
Updated a month ago1
Add poppler_path Argument to zerox Function
Updated a month ago1
Local LLM
Updated 2 months ago3
Deno support
Updated 2 months ago1
[Integration] Adding a better OCR vision model
Updated 2 months ago
Difficult integration with langchain
Updated 2 months ago
Update Python SDK please
Updated 2 months ago
[Question] How to set seed/TOP K/temperature parameters when calling GPT4o API?
Updated 2 months ago1
Error: Cannot find module '/.next/worker-script/node/index.js' when using server functions with zerox in Next.js
Updated 2 months ago4
does zerox work on client side
Closed 2 months ago2
Running on a m2 mac getting: Error: Could not load the "sharp" module using the darwin-arm64 runtime
Updated 2 months ago3
If there are not only texts but also pictures in the PDF file I uploaded, can these pictures be recognized and generated as separate pictures?
Updated 2 months ago3
[Error] Gemini models are not working
Closed 2 months ago1
Is there any way to access this via a hosted service?
Closed 2 months ago2
can it OCR Chinese？
Closed 2 months ago2
UnicodeEncodeError when writing data to file
Updated 2 months ago1
Upload image file
Updated 3 months ago3
Doesn't work with Amazon Bedrock, no guidelines how to use also including which model to use.
Closed 3 months ago
[Feature Request] Consider Adding Batch Processing Support to Reduce Azure AI Costs
Updated 3 months ago3
We've encountered an issue with repetitive patterns in your prompt
Closed 3 months ago2
NoneType for images in pdf.py
Updated 3 months ago4
Azure OpenAI
Closed 3 months ago1
Folder Processing Functionality
Closed 3 months ago
'gbk' codec can't encode
Closed 3 months ago
[question] How can this library be MIT and rely on libraries that are under GPL?
Updated 3 months ago
How can i make it run?
Updated 3 months ago1
Inconsistent OCR Results Between Local pyzerox Usage and Online Demo
Closed 3 months ago2
Receiving GraphicsMagick/ImageMagick - gm/convert binaries error passing file URL
Updated 3 months ago2
Multi-Linguistic?
Updated 3 months ago4
Failed to process image Error
Closed 3 months ago3
local llm
Updated 3 months ago4
Files with little text emit a description rather than just the text
Updated 3 months ago1
Support for JPG Files in Zerox
Updated 3 months ago2
No text in user content for Gemini model and None form Openai modle
Closed 3 months ago2
Can we add openrouter as an API provider?
Updated 3 months ago4
`ENAMETOOLONG` on documents with extra long file names
Closed 3 months ago
Page results occasionally start with ```
Updated 3 months ago
Python example script gives error on "None" select_pages
Updated 3 months ago4
[Question] Is it (or will it be) available for running offline?
Closed 4 months ago2
Support for Azure OpenAI in the Node.js version
Updated 4 months ago
Existing workflows to handle images in PDF.
Closed 4 months ago4
ModuleNotFoundError for py-zerox Module
Updated 4 months ago11
Missing Content in PDF to Markdown Conversion
Closed 4 months ago8