HuggingFace Error - Troubleshooting steps

[Careena_K]

While integrating the Hugging Face Inference API with a workflow, the following error appears in the node “Basic LLM Chain”:
An error occurred while fetching the blob.
This happens when trying to call the model meta-llama/Llama-3.2-3B-Instruct.
What could be the possible causes of this error, and how would you troubleshoot it to ensure the model works correctly for inference?

Describe the problem/error/question

What is the error message (if any)?

Please share your workflow

(Select the nodes on your canvas and use the keyboard shortcuts CMD+C/CTRL+C and CMD+V/CTRL+V to copy and paste the workflow.)

Share the output returned by the last node

Information on your n8n setup

• n8n version:
• Database (default: SQLite):
• n8n EXECUTIONS_PROCESS setting (default: own, main):
• Running n8n via (Docker, npm, n8n cloud, desktop app):
• Operating system:

[jabbson]

Hey @Careena_K hope all is good. Welcome to the community.

Would you like to share your workflow and a screenshot of your error?

[Careena_K]

[jabbson]

Could you please try posing this again, for some reason the forum got suspicious of that message

[Careena_K]

[Careena_K]

They are hiding my post so can’t send the screenshot. My work flow is i have added message and LLM Chain with hugging face but when i am adding API gives error. I have tried 7 times adding API everytime error.

[jabbson]

I’ll gladly take a look when either the post is unhidden. In the meantime if you could just share the workflow on it’s own, we could start there.

[bananabread]

I believe that the HuggingFace node has an issue right now with the credentials, which will probably explain why you are getting the error. You can verify this when you open your Hugging Face node and edit your API account connection.

If you see an error, means the issue is still not resolved.

Hope this helps, Cheers!

[y_li]

same issue

[bananabread]

Hello @y_li ! May I know what n8n version you are on?

You can find it in the bottom left of your dashboard, profile > settings.

The version will also be in the bottom left corner after that.

Cheers!