404 Error When Calling the Hugging Face Inference API via Dify

Dear Hugging Face Support Team,

I hope you are doing well.
We are integrating the Dify knowledge-base tool with the Hugging Face Inference API to generate embeddings (feature-extraction pipeline). We now consistently receive the following 404 error:

404 Client Error: Not Found for url: https://api-inference.huggingface.co/pipeline/feature-extraction/intfloat/multilingual-e5-large-instruct
(Request ID: Root=1-683b4db9-1e980b4c755dcffd2fc32730; bdc8fc2e-733e-4d9b-afee-955f5c940bdb)

Until about two weeks ago this model could be registered and used without any issues, but it suddenly started returning 404 errors.
Model page: intfloat/multilingual-e5-large-instruct · Hugging Face

Steps to reproduce

  1. In Dify, select Hugging Face Inference API as the embedding model.
  2. Enter an access token with only the read scope.
  3. Specify the model name intfloat/multilingual-e5-large-instruct.
  4. Save the settings and run a test → the 404 error appears.

What we have already checked

  • Although the token has only the read scope, another model (e.g., sentence-transformers/all-MiniLM-L6-v2) works fine through the same API.
  • The model page is accessible via the web interface.

Questions

  1. Has the feature-extraction endpoint for this model been disabled, or has the endpoint URL format changed?
  2. If the endpoint has changed, could you share the current correct URL format?
  3. Are there any other possible causes or misconfigurations we should investigate?

Your guidance would be greatly appreciated.
Thank you very much for your time and support.

2 Likes

For feature-extraction:

I’m encountering a 404 error when trying to access the chat completion endpoint for google/gemma-2-27b-it. Could you please confirm if this model’s API endpoint is still active or if there’s a new endpoint I should use?

Here is the error message I get:

bash

SalinEdit

404 Client Error: Not Found for url: https://router.huggingface.co/google/gemma-2-27b-it/v1/chat/completions

Thanks for the help!

1 Like

seems not deployed. Try: