github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-09 01:59:50 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #7238] Ollama document intelligence engine #51108

New Issue
Closed
opened 2026-04-28 18:24:16 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-28 18:24:16 -05:00
Owner
Copy Link

Originally created by @dcasota on GitHub (Oct 17, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7238

Has anyone Ollama examples for document intelligence?

In comparison, Azure AI comes with an engine which extracts elements from documents and makes them eligible passing the data into customizeable workflows. However, there are culprits even in the payed tier.

Azure AI Document Intelligence requirements

  • Microsoft Office files, or
  • JPEG, PNG, BMP, TIFF, or PDF format
  • PDF documents must have dimensions less than 17 x 17 inches or A3 paper size.
  • PDF documents must not be protected with a password.
  • Images must have dimensions between 50 x 50 pixels and 10,000 x 10,000 pixels.
  • file size less than 500 MB (payed standard tier)
  • only the first 2000 pages are analyzed (payed standard tier)

Some information about supported languages

Which Ollama examples fit to this extraction+passing-to-external-workflow demand?

Originally created by @dcasota on GitHub (Oct 17, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7238 Has anyone Ollama examples for document intelligence? In comparison, Azure AI comes with an engine which extracts elements from documents and makes them eligible passing the data into customizeable workflows. However, there are culprits even in the payed tier. Azure AI Document Intelligence requirements - Microsoft Office files, or - JPEG, PNG, BMP, TIFF, or PDF format - PDF documents must have dimensions less than 17 x 17 inches or A3 paper size. - PDF documents must not be protected with a password. - Images must have dimensions between 50 x 50 pixels and 10,000 x 10,000 pixels. - file size less than 500 MB (payed standard tier) - only the first 2000 pages are analyzed (payed standard tier) Some information about [supported languages](https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/language-support/ocr?view=doc-intel-4.0.0&preserve-view=true&tabs=read-print%2Clayout-print%2Cgeneral) Which Ollama examples fit to this extraction+passing-to-external-workflow demand?
GiteaMirror added the feature request label 2026-04-28 18:24:16 -05:00
GiteaMirror commented 2026-04-28 18:24:20 -05:00
Author
Owner
Copy Link

@mitja commented on GitHub (Oct 18, 2024):

I think this is not in scope of Ollama. Ollama's focus is on local model serving and not integrated solutions. Maybe look at end user tools like OpenWebUI or frameworks like LlamaIndex, which can both use Ollama for model serving.

<!-- gh-comment-id:2421565740 --> @mitja commented on GitHub (Oct 18, 2024): I think this is not in scope of Ollama. Ollama's focus is on local model serving and not integrated solutions. Maybe look at end user tools like OpenWebUI or frameworks like LlamaIndex, which can both use Ollama for model serving.
GiteaMirror commented 2026-04-28 18:24:21 -05:00
Author
Owner
Copy Link

@dcasota commented on GitHub (Oct 18, 2024):

Selection is good. Why shouldn't founders and young entrepreneurs think about three years into the future, right? Ollama is actually the best example of an integrated solution in terms of Hugging Face and Python as the preferred language in examples.

<!-- gh-comment-id:2421615541 --> @dcasota commented on GitHub (Oct 18, 2024): Selection is good. Why shouldn't founders and young entrepreneurs think about three years into the future, right? Ollama is actually the best example of an integrated solution in terms of Hugging Face and Python as the preferred language in examples.
GiteaMirror commented 2026-04-28 18:24:22 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Oct 24, 2024):

Thanks for the issue @dcasota ! I'm going to consolidate this into #5762; I'd love to do something like this in the future.

<!-- gh-comment-id:2436035842 --> @pdevine commented on GitHub (Oct 24, 2024): Thanks for the issue @dcasota ! I'm going to consolidate this into #5762; I'd love to do something like this in the future.
GiteaMirror commented 2026-04-28 18:24:24 -05:00
Author
Owner
Copy Link

@dcasota commented on GitHub (Oct 24, 2024):

@pdevine I wasn‘t aware of #5762. Makes sense. Have a great business plan.

<!-- gh-comment-id:2436087554 --> @dcasota commented on GitHub (Oct 24, 2024): @pdevine I wasn‘t aware of #5762. Makes sense. Have a great business plan.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#51108
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?