github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #2300] [MERGED] Improvements to ollama run for multimodal models #36723

New Issue
Closed
opened 2026-04-22 21:22:20 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-22 21:22:20 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/2300
Author: @jmorganca
Created: 2/1/2024
Status: ✅ Merged
Merged: 2/2/2024
Merged by: @jmorganca

Base: main ← Head: jmorganca/multimodal-repl

📝 Commits (1)

  • 5dcb4d9 Improvements to ollama run for multimodal models

📊 Changes

1 file changed (+11 additions, -21 deletions)

View changed files

📝 cmd/interactive.go (+11 -21)

📄 Description

Depends on #2296

This PR makes two changes to how ollama run works:

  1. Images are sent for all messages
  2. Messages without images can now be sent to multimodal models (they are language models too!), and instead a better prompt placeholder is provided. This is important for messages that don't include images but are relevant to a multimodal conversation (e.g. I will provide you a list of messages, provide me the captions for each or tell me more about the image I provided earlier)
  3. Only send the system prompt once

🔄 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/2300 **Author:** [@jmorganca](https://github.com/jmorganca) **Created:** 2/1/2024 **Status:** ✅ Merged **Merged:** 2/2/2024 **Merged by:** [@jmorganca](https://github.com/jmorganca) **Base:** `main` ← **Head:** `jmorganca/multimodal-repl` --- ### 📝 Commits (1) - [`5dcb4d9`](https://github.com/ollama/ollama/commit/5dcb4d99c4f230e5ad27bcd368c23a8edcb0b191) Improvements to `ollama run` for multimodal models ### 📊 Changes **1 file changed** (+11 additions, -21 deletions) <details> <summary>View changed files</summary> 📝 `cmd/interactive.go` (+11 -21) </details> ### 📄 Description Depends on #2296 This PR makes two changes to how `ollama run` works: 1. Images are sent for all messages 2. Messages without images can now be sent to multimodal models (they are language models too!), and instead a better prompt placeholder is provided. This is important for messages that don't include images but are relevant to a multimodal conversation (e.g. `I will provide you a list of messages, provide me the captions for each` or `tell me more about the image I provided earlier`) 3. Only send the system prompt once --- <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 2026-04-22 21:22:20 -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#36723
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?