How to find the ENDPOINT_URL for the models like HF_API_ITT_BASE?

Short Course Q&A Building Generative AI applications with Gradio
1

trying to run the notebook ‘Short courses/Building Generative AI Applications with Gradio/Image captioning App’ in a local Jupyter Notebook…

I assume that I did not get the right endpoint_url…
HF_API_ITT_BASE = “https://ehoxl9yrjiy4m82k.us-east-1.aws.endpoints.huggingface.cloud”

(I already installed all required packages, like python-dotenv, gradio, ipywidgets). I opened an account at hugging face and got my personal HF_API_KEY. I created an .env file and put all the required keys and urls into it…)

If this is a URL problem: Where to find/create the required URL(s)?

See the screen shot for the code and the error message.

Bildschirmfoto 2023-08-25 um 15.59.43
Bildschirmfoto 2023-08-25 um 15.59.43882×855 161 KB

Many thanks for your hints/support!

2

I have the same error, even I had opened my own model endpoints at hugging face.

4

Yup, instructions in this course very vague… It should have been more clear and precise…

I got this api url by following below steps :

  1. Copy model name used : Which is Salesforce/blip-image-captioning-base.
  2. Go To : https://huggingface.co/models and search for above model : Salesforce/blip-image-captioning-base
  3. Open that model
  4. Click on Deploy. You will see an option Interface API
  5. Clicking on that will reveal API_URL which is free to use directly in your project.
1 Like
5

Yes, I also found it very strange that the course focuses on gradio, yet it does not clearly state how to setup the endpoints correctly, so that we’re able to also use gradio outside of the course notebooks.

Hugging Face also has another course on the platform: Open Source Models with Hugging Face. The videos w/ code they have there also include some examples with gradio that were a bit more helpful in that regard.