github-starred/ollama-ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-04-27 07:57:18 -05:00
Code Issues 2.2k Packages Projects Releases 100 Wiki Activity

Sending "hidden" messages for attachments #4881

New Issue
Closed
opened 2025-11-12 12:35:30 -06:00 by GiteaMirror · 1 comment
GiteaMirror commented 2025-11-12 12:35:30 -06:00
Owner
Copy Link

Originally created by @robotom on GitHub (Nov 13, 2024).

I'm building a frontend and trying to send attachment contents and an accompanying prompt (e.g. "analyze this and wait for user prompt before responding") as a "hidden" message so that it's not rendered to the user on the frontend. I'm trying to avoid seeing 10 pages of a doc rendered in the chat window.

Perhaps this is a frontend issue but I'm finding this more difficult to code than I think it should be...

Any ideas? Thanks!

Originally created by @robotom on GitHub (Nov 13, 2024). I'm building a frontend and trying to send attachment contents and an accompanying prompt (e.g. "analyze this and wait for user prompt before responding") as a "hidden" message so that it's not rendered to the user on the frontend. I'm trying to avoid seeing 10 pages of a doc rendered in the chat window. Perhaps this is a frontend issue but I'm finding this more difficult to code than I think it should be... Any ideas? Thanks!
GiteaMirror added the feature request label 2025-11-12 12:35:30 -06:00
GiteaMirror commented 2025-11-12 12:35:31 -06:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Nov 13, 2024):

@robotom For multimodal we only currently support images right now, not things like PDFs or other documents. The way to pass anything is through the API though, so if you preprocessed everything in the frontend (like reading a PDF) you can then process the contents and make a call to the LLM which wouldn't be displayed to the user through your front end.

Hopefully that makes sense. I'm going to go ahead and close the issue.

@pdevine commented on GitHub (Nov 13, 2024): @robotom For multimodal we only currently support images right now, not things like PDFs or other documents. The way to pass anything is through the API though, so if you preprocessed everything in the frontend (like reading a PDF) you can then process the contents and make a call to the LLM which wouldn't be displayed to the user through your front end. Hopefully that makes sense. I'm going to go ahead and close the issue.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
client2
cloud
compatibility
context-length
create
docker
documentation
embeddings
engine
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
install
integration
intel
js
linux
macos
memory
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
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-ollama#4881
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?