[PR #3219] [MERGED] Add OCR of image support #4236

Closed
opened 2026-02-22 18:35:25 -05:00 by yindo · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/Mintplex-Labs/anything-llm/pull/3219
Author: @timothycarambat
Created: 2/14/2025
Status: Merged
Merged: 2/14/2025
Merged by: @timothycarambat

Base: masterHead: ocr-parse-images


📝 Commits (6)

📊 Changes

5 files changed (+118 additions, -2 deletions)

View changed files

📝 .github/workflows/dev-build.yaml (+1 -1)
collector/processSingleFile/convert/asImage.js (+48 -0)
📝 collector/utils/OCRLoader/index.js (+61 -0)
📝 collector/utils/constants.js (+7 -0)
📝 collector/utils/files/mime.js (+1 -1)

📄 Description

Pull Request Type

  • feat
  • 🐛 fix
  • ♻️ refactor
  • 💄 style
  • 🔨 chore
  • 📝 docs

What is in this change?

  • Extends OCR abilities to accept image/* mimes for text parsing.
  • This only functions via uploading images via document collector. Images uploaded into chats will be attachments still

Additional Information

Developer Validations

  • I ran yarn lint from the root of the repo & committed changes
  • Relevant documentation has been updated
  • I have tested my code functionality
  • Docker build succeeds locally

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/Mintplex-Labs/anything-llm/pull/3219 **Author:** [@timothycarambat](https://github.com/timothycarambat) **Created:** 2/14/2025 **Status:** ✅ Merged **Merged:** 2/14/2025 **Merged by:** [@timothycarambat](https://github.com/timothycarambat) **Base:** `master` ← **Head:** `ocr-parse-images` --- ### 📝 Commits (6) - [`2f89bba`](https://github.com/Mintplex-Labs/anything-llm/commit/2f89bbae744c4986d226256cd4e7aaf6e2977d7d) OCR PDFs as fallback in spawn thread - [`c463710`](https://github.com/Mintplex-Labs/anything-llm/commit/c463710b0f2f7a55a715d37450662b794e325174) wip - [`64b3210`](https://github.com/Mintplex-Labs/anything-llm/commit/64b3210db235bb81d54159b096b119c757ed1fe4) build our own worker fanout and wrapper - [`3e616fe`](https://github.com/Mintplex-Labs/anything-llm/commit/3e616fe53f742a7365873a01f83ce3bba7e999d3) norm pkgs - [`3a586bc`](https://github.com/Mintplex-Labs/anything-llm/commit/3a586bce657fb0f64ee0c93fe6baf52b0d38d330) Add image OCR support - [`fbd15ab`](https://github.com/Mintplex-Labs/anything-llm/commit/fbd15ab5016abc6e3eec0b4cec8b23d81e147840) merge with master ### 📊 Changes **5 files changed** (+118 additions, -2 deletions) <details> <summary>View changed files</summary> 📝 `.github/workflows/dev-build.yaml` (+1 -1) ➕ `collector/processSingleFile/convert/asImage.js` (+48 -0) 📝 `collector/utils/OCRLoader/index.js` (+61 -0) 📝 `collector/utils/constants.js` (+7 -0) 📝 `collector/utils/files/mime.js` (+1 -1) </details> ### 📄 Description ### Pull Request Type <!-- For change type, change [ ] to [x]. --> - [x] ✨ feat - [ ] 🐛 fix - [ ] ♻️ refactor - [ ] 💄 style - [ ] 🔨 chore - [ ] 📝 docs ### What is in this change? - Extends OCR abilities to accept `image/*` mimes for text parsing. - This _only functions_ via uploading images via document collector. Images uploaded into chats will be _attachments_ still <!-- Describe the changes in this PR that are impactful to the repo. --> ### Additional Information <!-- Add any other context about the Pull Request here that was not captured above. --> ### Developer Validations <!-- All of the applicable items should be checked. --> - [x] I ran `yarn lint` from the root of the repo & committed changes - [x] Relevant documentation has been updated - [x] I have tested my code functionality - [x] Docker build succeeds locally --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-02-22 18:35:25 -05:00
yindo closed this issue 2026-02-22 18:35:25 -05:00
yindo changed title from [PR #3219] Add OCR of image support to [PR #3219] [MERGED] Add OCR of image support 2026-06-05 15:17:32 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#4236