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.

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

Client Error: Not Found for url: http://localhost:11434/api/generate #12

Closed
tin2tin opened this issue Jan 8, 2025 · 5 comments
Closed

Comments

@tin2tin
Copy link

tin2tin commented Jan 8, 2025

Using the API and Streamlit

File: C:\smallpdf-convert-20250108-172503\Mandpåbænken_1kap-billeder-9.jpg
Extracted Text: Error processing image: 404 Client Error: Not Found for url: http://localhost:11434/api/generate

@AlfandiMario
Copy link

Hi! I get the same error. Do you already solve it?

@tin2tin
Copy link
Author

tin2tin commented Jan 9, 2025

Try this:
image

Seemed to make a difference to the API/python code, but I gave up on processing a batch of 25 images after not finishing after 3 hours.

@amrrs
Copy link

amrrs commented Jan 9, 2025

@tin2tin 11b models would take a long time, i'd suggest go with something smaller https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct

@AlfandiMario
Copy link

Hi @tin2tin @amrrs thank you for answering. I already pull the model and check it with 'ollama list'. Even, my 11434 port is opened and no firewall. But I still got an same error

@AlfandiMario
Copy link

AlfandiMario commented Jan 10, 2025

Hi. I want to update that I already could run this program. I think it because I had not installed the ollama app before (https://ollama.com/download/linux) cause when I installed it, then pull and do 'ollama serve' it works well.

Also the selected model that appears in the streamlit should be the same with the pulled image (check with: ollama list)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants