Error handling when a single topic fails with openAI GPT representation #2177
jeaninejuliettes
started this conversation in
Ideas
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I ran into the issue that some of the topics I have run into an issue (content violation) when trying to use the OpenAI representation (with both keywords and representative documents in the prompt). At the moment it looks like the whole process fails and stops. Since I'm processing quite a lot of data, I'd rather get a warning about this and let the model proceed with the other topics.
In my own script I'm using a custom OpenAI representation class at the moment where I adjusted this behaviour. But I was wondering if this is something that is already on the "wish-list"?
I'm using bertopic 0.16.4 at the moment.
Beta Was this translation helpful? Give feedback.
All reactions