Is the “Text Classifier” broken?

Questions
,
1

Describe the problem/error/question

The “Text Classifier” is not working, and giving me an error instead. I don’t understand why.

What is the error message (if any)?

Problem in node ‘Text Classifier‘
Failed to parse. Text: “[{“type”:“text”,“text”:”```json\n{\“Assistant Request\”:true,\“Non-Assistant Request\”:false,\“fallback\”:false}\n```“,“annotations”:}]”. Error: [ { “code”: “invalid_type”, “expected”: “object”, “received”: “array”, “path”: , “message”: “Expected object, received array” } ] Troubleshooting URL: LangChain overview - Docs by LangChain

Please share your workflow

Share the output returned by the last node

None, unfortunately.

Information on your n8n setup

  • n8n version: 1.113.2 (i believe)
  • Database (default: SQLite): None
  • n8n EXECUTIONS_PROCESS setting (default: own, main): own, main
  • Running n8n via (Docker, npm, n8n cloud, desktop app): Docker
  • Operating system: MacOS
2

Hello @Jannik1

Yes indeed, it’s broken when the “Use Responses API” option is enabled!

image
image408×385 15.8 KB

Just turn it off and it should work again.

2 Likes
3

Thank you so much! It does work now <3 Why is that the case? Do you know what happens under the hood / when it needs to be turned on or off?

4

The “Use Responses API” option is something new, and this looks like a bug in how the responses are parsed..

I think it will be fixed in an upcoming release once the team notices it.

5

Perfect, thank you very much

1 Like
6

This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.