github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #8322] llama3.2-vision // llava - not receiving images via chat completions API #67386

New Issue
Closed
opened 2026-05-04 10:11:25 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-04 10:11:25 -05:00
Owner
Copy Link

Originally created by @TheFoot on GitHub (Jan 6, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8322

What is the issue?

When using either the llama3.2-vision:11b or llava:13b models, the LLM reports it does not receive an image. Llama is clearer than Llava (which just makes up something).

The CLI works (with absolute paths not relative):

% ollama run llama3.2-vision
>>> Describe this image: /Users/thefoot/Pictures/thefeet.png
Added image '/Users/thefoot/Pictures/thefeet.png'
This image features a digital illustration of nine feet, with the top three pairs [...]

Example API chat completions call:

curl --location 'http://localhost:11434/v1/chat/completions' \
--header 'Content-Type: application/json' \
--data '{
    "model": "llama3.2-vision:11b”,
    "messages": [
        {
            "role": "user",
            "content": "Describe this image",
            "images": [
                "iVBORw0KGgoAAAANSUhEUgAABAAAAAQACAYAAA [...]”
            ]
        }
    ],
    "temperature": 0.7,
    "max_tokens": 500,
    "stream": false
}'

Response message:

"message": {
                "role": "assistant",
                "content": "There is no image provided. Can you please describe the image or provide more context, so I can give a description?"
            }

Any idea if this is a bug, or have I done something wrong with the API call?

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.5.4

Originally created by @TheFoot on GitHub (Jan 6, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8322 ### What is the issue? When using either the llama3.2-vision:11b or llava:13b models, the LLM reports it does not receive an image. Llama is clearer than Llava (which just makes up something). The CLI works (with absolute paths not relative): ``` % ollama run llama3.2-vision >>> Describe this image: /Users/thefoot/Pictures/thefeet.png Added image '/Users/thefoot/Pictures/thefeet.png' This image features a digital illustration of nine feet, with the top three pairs [...] ``` Example API chat completions call: ``` curl --location 'http://localhost:11434/v1/chat/completions' \ --header 'Content-Type: application/json' \ --data '{ "model": "llama3.2-vision:11b”, "messages": [ { "role": "user", "content": "Describe this image", "images": [ "iVBORw0KGgoAAAANSUhEUgAABAAAAAQACAYAAA [...]” ] } ], "temperature": 0.7, "max_tokens": 500, "stream": false }' ``` Response message: ``` "message": { "role": "assistant", "content": "There is no image provided. Can you please describe the image or provide more context, so I can give a description?" } ``` Any idea if this is a bug, or have I done something wrong with the API call? ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.5.4
GiteaMirror added the bug label 2026-05-04 10:11:25 -05:00
GiteaMirror commented 2026-05-04 10:11:35 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 7, 2025):

OpenAI API requires that the images are a dict and the image blob has a DataURI prefix:

            "images": {
                "url": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAABAAAAAQACAYAAA [...]”
            }
<!-- gh-comment-id:2574199881 --> @rick-github commented on GitHub (Jan 7, 2025): OpenAI API [requires](https://platform.openai.com/docs/guides/vision#uploading-base64-encoded-images) that the images are a dict and the image blob has a DataURI prefix: ``` "images": { "url": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAABAAAAAQACAYAAA [...]” } ```
GiteaMirror commented 2026-05-04 10:11:37 -05:00
Author
Owner
Copy Link

@TheFoot commented on GitHub (Jan 7, 2025):

Ahh thank you! The below worked as per OpenAI spec:

"content": [
                {
                    "type": "text",
                    "text": "What is in this image?",
                },
                {
                    "type": "image_url",
                    "image_url": {"url": f"data:image/jpeg;base64,{base64_image}"},
                },
            ],
<!-- gh-comment-id:2574894439 --> @TheFoot commented on GitHub (Jan 7, 2025): Ahh thank you! The below worked as per OpenAI spec: ``` "content": [ { "type": "text", "text": "What is in this image?", }, { "type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{base64_image}"}, }, ], ```
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 bug
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#67386
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?