Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[BUG]: Vision models don't retain memory of images past one prompt #2585

Open
sheneman opened this issue Nov 5, 2024 · 3 comments · May be fixed by #2919
Open

[BUG]: Vision models don't retain memory of images past one prompt #2585

sheneman opened this issue Nov 5, 2024 · 3 comments · May be fixed by #2919
Assignees
@timothycarambat
Labels
core-team-only feature request

Comments

@sheneman
Copy link

sheneman commented Nov 5, 2024

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

When I upload a file, I can use a vision model like llama3.2-vision:11b to describe it, but then subsequent prompts don't have any memory of the image.

image

I would expect that I can ask repeated questions of the image and that it would remain in my current context until my context window was exhausted.

Are there known steps to reproduce?

No response
@sheneman sheneman added the possible bug Bug was reported but is not confirmed or is unable to be replicated. label Nov 5, 2024
@nekopep
Copy link

nekopep commented Nov 20, 2024 •
edited
Loading

Tried on 1.2.3 docker version, pixtral 12B, and worked. <--- correction , no in fact I was lucky , see next comment...
image
At least on docker version looks right.

I just tried on 1.2.4 desktop version, pixtral 12B and it fails:
image

Looks like if data is not on first description he hallucinate colors... (on desktop version)

@nekopep
Copy link

nekopep commented Nov 20, 2024

Correction seen exact same behviour on docker :), 1.2.3, pixtral 12B.

image

@spencerthayer
Copy link

Any update?

@timothycarambat timothycarambat linked a pull request Dec 31, 2024 that will close this issue
Open
28 tasks
@timothycarambat timothycarambat added core-team-only feature request and removed possible bug Bug was reported but is not confirmed or is unable to be replicated. labels Dec 31, 2024
@timothycarambat timothycarambat self-assigned this Dec 31, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@timothycarambat timothycarambat

Labels
core-team-only feature request
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Support historical message image inputs/attachments for n+1 queries Mintplex-Labs/anything-llm
4 participants
@spencerthayer @nekopep @sheneman @timothycarambat