github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-18 06:06:18 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[PR #4857] [CLOSED] feat: initial steps allow image embeddings #16874

New Issue
Closed
opened 2026-04-16 05:45:59 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-16 05:45:59 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/4857
Author: @JoanFM
Created: 6/6/2024
Status: ❌ Closed

Base: main ← Head: feat-enable-image-embedding

📝 Commits (2)

  • 55aa339 feat: initial steps allow image embeddings
  • 316a97e feat: send image as Json

📊 Changes

4 files changed (+20 additions, -8 deletions)

View changed files

📝 api/types.go (+3 -0)
📝 llm/ext_server/server.cpp (+1 -0)
📝 llm/server.go (+15 -7)
📝 server/routes.go (+1 -1)

📄 Description

I would like to start the discussion about the possibility to add Image as an Input to the Embedding route.

I guess it would also need the llama.cpp runner to be able to handle it, for which I still need to look at.

Also, I would like to know if batch embeddings is something you would consider adding.

This PR would only be a first step in that direction doing a small refactoring and adding the Image to the Embedding Request.

🔄 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/4857 **Author:** [@JoanFM](https://github.com/JoanFM) **Created:** 6/6/2024 **Status:** ❌ Closed **Base:** `main` ← **Head:** `feat-enable-image-embedding` --- ### 📝 Commits (2) - [`55aa339`](https://github.com/ollama/ollama/commit/55aa33948b9358081af961f5c256b44e65fa2d37) feat: initial steps allow image embeddings - [`316a97e`](https://github.com/ollama/ollama/commit/316a97e43b6b381046e70edcc1320be4babdad99) feat: send image as Json ### 📊 Changes **4 files changed** (+20 additions, -8 deletions) <details> <summary>View changed files</summary> 📝 `api/types.go` (+3 -0) 📝 `llm/ext_server/server.cpp` (+1 -0) 📝 `llm/server.go` (+15 -7) 📝 `server/routes.go` (+1 -1) </details> ### 📄 Description I would like to start the discussion about the possibility to add Image as an Input to the Embedding route. I guess it would also need the llama.cpp runner to be able to handle it, for which I still need to look at. Also, I would like to know if `batch` embeddings is something you would consider adding. This PR would only be a first step in that direction doing a small refactoring and adding the Image to the Embedding Request. --- <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 2026-04-16 05:45:59 -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#16874
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?