[GH-ISSUE #2585] [BUG]: Vision models don't retain memory of images past one prompt #1677

Closed
opened 2026-02-22 18:26:00 -05:00 by yindo · 3 comments
Owner

Originally created by @sheneman on GitHub (Nov 4, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2585

Originally assigned to: @timothycarambat on GitHub.

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

Originally created by @sheneman on GitHub (Nov 4, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/2585 Originally assigned to: @timothycarambat on GitHub. ### 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](https://github.com/user-attachments/assets/673655ec-3e02-4da1-83b6-16c9e8b60321) 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_
yindo added the core-team-onlyfeature request labels 2026-02-22 18:26:00 -05:00
yindo closed this issue 2026-02-22 18:26:00 -05:00
Author
Owner

@nekopep commented on GitHub (Nov 20, 2024):

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 commented on GitHub (Nov 20, 2024): Tried on 1.2.3 docker version, pixtral 12B, and worked. <--- correction , no in fact I was lucky , see next comment... ![image](https://github.com/user-attachments/assets/9cd1dfb0-240f-4bda-8bdd-d04cd9e64003) At least on docker version looks right. I just tried on 1.2.4 desktop version, pixtral 12B and it fails: ![image](https://github.com/user-attachments/assets/57f3cbc2-3fe4-4184-afce-6c837b9960e7) Looks like if data is not on first description he hallucinate colors... (on desktop version)
Author
Owner

@nekopep commented on GitHub (Nov 20, 2024):

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

image

@nekopep commented on GitHub (Nov 20, 2024): Correction seen exact same behviour on docker :), 1.2.3, pixtral 12B. ![image](https://github.com/user-attachments/assets/9e7084d3-8c6d-4ae4-a6de-70739a4ec26f)
Author
Owner

@spencerthayer commented on GitHub (Dec 22, 2024):

Any update?

@spencerthayer commented on GitHub (Dec 22, 2024): Any update?
yindo changed title from [BUG]: Vision models don't retain memory of images past one prompt to [GH-ISSUE #2585] [BUG]: Vision models don't retain memory of images past one prompt 2026-06-05 14:42:04 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#1677