DEV Community

Ollama-OCR for High-Precision OCR with Ollama

Bytefer on November 25, 2024

Llama 3.2-Vision is a multimodal large language model available in 11B and 90B sizes, capable of processing both text and image inputs to generate ...

Read full post

ogodo olutayo • Nov 27

Can you please what the speed is like for a image-based pdf with over 60 pages?

Bytefer • Nov 27

Recognition speed depends on the performance of your current device.

Nov Piseth • Nov 28

how to add other language like asia language in UTF8. thanks

Bytefer • Nov 28

You can learn about MiniCPM-V

Nov Piseth • Nov 28

thanks you so much let me try.

Bytefer • Nov 29

You're welcome, for higher precision OCR scenarios, macOS platform, interested to try macos-vision-ocr.

Danny • Nov 28

Possible to use 90B model?

Bytefer • Nov 28

ollama run llama3.2-vision:90b
ollama.com/library/llama3.2-vision...

Akshay Ballal • Nov 27

Does it hallucinate with large tables with lot of numbers ?

Bytefer • Nov 27

You can test the recognition of the Llama-3.2-90B-Vision at the llamaocr website.

Ramya Menon • Nov 27

Damn needed this.

Bytefer • Nov 27

Other application scenarios for Llama 3.2 Vision, if you are interested.

Tan KC • Nov 27

Can local ollama minicpm-v be used

Bytefer • Nov 27

The minicpm-v visual model is also supported with the following code:

  const text = await ollamaOCR({
    model: "minicpm-v",
    filePath: "./trader-joes-receipt.jpg",
    systemPrompt: DEFAULT_OCR_SYSTEM_PROMPT,
  });