github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #12735] [CLOSED] feat: Enable image embeddings for vision models #39805

New Issue
Closed
opened 2026-04-23 00:48:06 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-23 00:48:06 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/12735
Author: @daboe01
Created: 10/22/2025
Status: ❌ Closed

Base: main ← Head: feat-image-embeddings

📝 Commits (6)

  • e61b0ab feat: Enable image embeddings for vision models
  • 5fe8378 feat: Enable image embeddings for vision models
  • 65c78e7 Enable image embeddings for vision models
  • 28d29de fixed: data routing issues
  • 95e2146 Merge branch 'main' into feat-image-embeddings
  • 0d4e397 feat: Enable multimodal embeddings

📊 Changes

405 files changed (+4313 additions, -114772 deletions)

View changed files

📝 .github/workflows/release.yaml (+38 -129)
📝 .github/workflows/test.yaml (+61 -16)
📝 CMakePresets.json (+7 -16)
📝 Dockerfile (+7 -7)
📝 README.md (+5 -26)
📝 api/types.go (+8 -6)
📝 app/.gitignore (+0 -10)
📝 app/README.md (+10 -95)
📝 app/assets/assets.go (+0 -2)
➖ app/assets/background.png (+0 -0)
📝 app/assets/tray.ico (+0 -0)
📝 app/assets/tray_upgrade.ico (+0 -0)
➖ app/auth/connect.go (+0 -26)
➖ app/cmd/app/AppDelegate.h (+0 -7)
➖ app/cmd/app/app.go (+0 -478)
➖ app/cmd/app/app_darwin.go (+0 -269)
➖ app/cmd/app/app_darwin.h (+0 -43)
➖ app/cmd/app/app_darwin.m (+0 -1125)
➖ app/cmd/app/app_windows.go (+0 -439)
➖ app/cmd/app/menu.h (+0 -27)

...and 80 more files

📄 Description

This commit introduces the following changes:

  • Adds a new /image-embedding endpoint to the ollamarunner to handle generating embeddings for images.
  • Updates the /api/embed handler to support multimodal requests, allowing both text and images to be passed in a single request.
  • Updates the LlamaServer interface and its implementation to handle image data for both mixed text/image embeddings and image-only embeddings.
  • Updates the ollamarunner's /embedding handler to accept and process images.

Fixes #7677

🔄 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/ollama/ollama/pull/12735 **Author:** [@daboe01](https://github.com/daboe01) **Created:** 10/22/2025 **Status:** ❌ Closed **Base:** `main` ← **Head:** `feat-image-embeddings` --- ### 📝 Commits (6) - [`e61b0ab`](https://github.com/ollama/ollama/commit/e61b0abadb6fc18d75acdb800ab01a35f8a00c58) feat: Enable image embeddings for vision models - [`5fe8378`](https://github.com/ollama/ollama/commit/5fe8378fdf1ceb87536ea5143f08c37c0d618c3d) feat: Enable image embeddings for vision models - [`65c78e7`](https://github.com/ollama/ollama/commit/65c78e7bb816bb57162747e670b923c22f0cb483) Enable image embeddings for vision models - [`28d29de`](https://github.com/ollama/ollama/commit/28d29de8d14e6949a09762d8b7be2776ea9ab3ff) fixed: data routing issues - [`95e2146`](https://github.com/ollama/ollama/commit/95e21462fcf7117194fdd40b1b8c6a16d8e1914e) Merge branch 'main' into feat-image-embeddings - [`0d4e397`](https://github.com/ollama/ollama/commit/0d4e39745b7c91e5cf63edf975d7aaca4e5d302e) feat: Enable multimodal embeddings ### 📊 Changes **405 files changed** (+4313 additions, -114772 deletions) <details> <summary>View changed files</summary> 📝 `.github/workflows/release.yaml` (+38 -129) 📝 `.github/workflows/test.yaml` (+61 -16) 📝 `CMakePresets.json` (+7 -16) 📝 `Dockerfile` (+7 -7) 📝 `README.md` (+5 -26) 📝 `api/types.go` (+8 -6) 📝 `app/.gitignore` (+0 -10) 📝 `app/README.md` (+10 -95) 📝 `app/assets/assets.go` (+0 -2) ➖ `app/assets/background.png` (+0 -0) 📝 `app/assets/tray.ico` (+0 -0) 📝 `app/assets/tray_upgrade.ico` (+0 -0) ➖ `app/auth/connect.go` (+0 -26) ➖ `app/cmd/app/AppDelegate.h` (+0 -7) ➖ `app/cmd/app/app.go` (+0 -478) ➖ `app/cmd/app/app_darwin.go` (+0 -269) ➖ `app/cmd/app/app_darwin.h` (+0 -43) ➖ `app/cmd/app/app_darwin.m` (+0 -1125) ➖ `app/cmd/app/app_windows.go` (+0 -439) ➖ `app/cmd/app/menu.h` (+0 -27) _...and 80 more files_ </details> ### 📄 Description This commit introduces the following changes: - Adds a new `/image-embedding` endpoint to the `ollamarunner` to handle generating embeddings for images. - Updates the `/api/embed` handler to support multimodal requests, allowing both text and images to be passed in a single request. - Updates the `LlamaServer` interface and its implementation to handle image data for both mixed text/image embeddings and image-only embeddings. - Updates the `ollamarunner`'s `/embedding` handler to accept and process images. Fixes #7677 --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-23 00:48:06 -05:00
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 pull-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#39805
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?