github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 20:54:54 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #10791] cant upload local image for cli #69143

New Issue
Closed
opened 2026-05-04 17:16:30 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-05-04 17:16:30 -05:00
Owner
Copy Link

Originally created by @zswodegit on GitHub (May 21, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10791

What is the issue?

hi,
im trying to do inference with multi-modal like the tutorial did, but always failed, if i need to export some environment variable ?

Image

Relevant log output

OS

macOS, Linux

GPU

Nvidia

CPU

No response

Ollama version

0.7.0

Originally created by @zswodegit on GitHub (May 21, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10791 ### What is the issue? hi, im trying to do inference with multi-modal like the tutorial did, but always failed, if i need to export some environment variable ? ![Image](https://github.com/user-attachments/assets/15c74592-d0ed-496c-9c4f-5053b7bb9729) ### Relevant log output ```shell ``` ### OS macOS, Linux ### GPU Nvidia ### CPU _No response_ ### Ollama version 0.7.0
GiteaMirror added the bug label 2026-05-04 17:16:30 -05:00
GiteaMirror commented 2026-05-04 17:16:33 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 21, 2025):

This should work. Is aaa.jpg a well-formed JPG file? What's the output of

file aaa.jpg
<!-- gh-comment-id:2897209703 --> @rick-github commented on GitHub (May 21, 2025): This should work. Is aaa.jpg a well-formed JPG file? What's the output of ``` file aaa.jpg ```
GiteaMirror commented 2026-05-04 17:16:33 -05:00
Author
Owner
Copy Link

@zswodegit commented on GitHub (May 22, 2025):

This should work. Is aaa.jpg a well-formed JPG file? What's the output of

file aaa.jpg

i fix it by modify the system promt in Modelfile, but i have been unable to successfully send requests with image, still same issue
url = "http://localhost:11434/api/generate"

headers = { "Content-Type": "application/json" }

data = { "model": "qwenvl", "prompt": "describe this image：/home/nvidia/zsx/pic/aaa.jpg", "image_url": "/home/nvidia/zsx/pic/aaa.jpg" }

response = requests.post(url, headers=headers, json=data)

print(response.status_code)

response1 = response.text.encode('utf-8')

print(response1.decode('utf-8'))

Image

<!-- gh-comment-id:2899724202 --> @zswodegit commented on GitHub (May 22, 2025): > This should work. Is aaa.jpg a well-formed JPG file? What's the output of > > ``` > file aaa.jpg > ``` i fix it by modify the system promt in Modelfile, but i have been unable to successfully send requests with image, still same issue `url = "http://localhost:11434/api/generate"` ` headers = { "Content-Type": "application/json" } ` ` data = { "model": "qwenvl", "prompt": "describe this image：/home/nvidia/zsx/pic/aaa.jpg", "image_url": "/home/nvidia/zsx/pic/aaa.jpg" } ` ` response = requests.post(url, headers=headers, json=data) ` ` print(response.status_code) ` ` response1 = response.text.encode('utf-8') ` ` print(response1.decode('utf-8')) ` ![Image](https://github.com/user-attachments/assets/4f2adde9-cc86-4abf-978e-55aee8b2d365)
GiteaMirror commented 2026-05-04 17:16:33 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 22, 2025):

ollama doesn't use image_url.

#!/usr/bin/env python3

import requests
import base64

url = "http://localhost:11434/api/generate"
headers = { "Content-Type": "application/json" }
image = '/home/nvidia/zsx/pic/aaa.jpg'

with open(image, "rb") as image_file:
    image_data = image_file.read()
    base64_image = base64.b64encode(image_data).decode('utf-8')

data = { "model": "qwen2.5vl", "prompt": "describe this image", "images": [base64_image] }

response = requests.post(url, headers=headers, json=data)

print(response.status_code)
print(response.text)
<!-- gh-comment-id:2901034170 --> @rick-github commented on GitHub (May 22, 2025): ollama doesn't use `image_url`. ```python #!/usr/bin/env python3 import requests import base64 url = "http://localhost:11434/api/generate" headers = { "Content-Type": "application/json" } image = '/home/nvidia/zsx/pic/aaa.jpg' with open(image, "rb") as image_file: image_data = image_file.read() base64_image = base64.b64encode(image_data).decode('utf-8') data = { "model": "qwen2.5vl", "prompt": "describe this image", "images": [base64_image] } response = requests.post(url, headers=headers, json=data) print(response.status_code) print(response.text) ```
GiteaMirror commented 2026-05-04 17:16:34 -05:00
Author
Owner
Copy Link

@zswodegit commented on GitHub (May 23, 2025):

ollama doesn't use image_url.

#!/usr/bin/env python3

import requests
import base64

url = "http://localhost:11434/api/generate"
headers = { "Content-Type": "application/json" }
image = '/home/nvidia/zsx/pic/aaa.jpg'

with open(image, "rb") as image_file:
image_data = image_file.read()
base64_image = base64.b64encode(image_data).decode('utf-8')

data = { "model": "qwen2.5vl", "prompt": "describe this image", "images": [base64_image] }

response = requests.post(url, headers=headers, json=data)

print(response.status_code)
print(response.text)

it works! i dont remember where i saw imagr_url , and its led me into a dead end. maybe its a vllm stuff? nvm anyways thx a lot!

<!-- gh-comment-id:2903371684 --> @zswodegit commented on GitHub (May 23, 2025): > ollama doesn't use `image_url`. > > #!/usr/bin/env python3 > > import requests > import base64 > > url = "http://localhost:11434/api/generate" > headers = { "Content-Type": "application/json" } > image = '/home/nvidia/zsx/pic/aaa.jpg' > > with open(image, "rb") as image_file: > image_data = image_file.read() > base64_image = base64.b64encode(image_data).decode('utf-8') > > data = { "model": "qwen2.5vl", "prompt": "describe this image", "images": [base64_image] } > > response = requests.post(url, headers=headers, json=data) > > print(response.status_code) > print(response.text) it works! i dont remember where i saw `imagr_url` , and its led me into a dead end. maybe its a vllm stuff? nvm anyways thx a lot!
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#69143
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?