Hi there, we're using claygent enrichment with our own OpenAI key on our table, noticed that sometimes it results in:
error
timeout
low confidence
though not often, it's a bit tedious having to retry manually. is it possible if I want to configure an automated retry for those scenarios?
Currently, we don't have an automated retry feature for Claygent enrichment scenarios involving errors, timeouts, or low confidence results. However, to minimize these issues, ensure you have an appropriate OpenAI API access level that meets the required token per minute (TPM) rates for your usage. To improve your experience, you can: 1. Verify your OpenAI API usage limits through their platform 2. Complete the necessary account setup and payment verification with OpenAI 3. Monitor your API key's performance and adjust as needed Have you checked your OpenAI API access level and usage limits recently?
Looks like you're still looking for help. We're currently outside of our standard office hours (9 AM to 9 PM EST, Monday through Friday), so it may take a little longer for us to respond. If you’re dealing with a specific table, drop the URL below so we can help you quicker. Otherwise, someone from our team will be in touch soon!
Hakiem you can always filter the table down to only show those matching your criteria (error,low confidence, no response) and just rerun them. You shouldn’t be timing out unless you’re REALLY pushing the agent. Timeouts occur around 120 seconds. Look at the time spent on other agents and see if this is causing the fail. It’s likely your rate limits need to be increased. You can email OpenAI support explaining the situation and they are quite accommodating. You should be fine if you’re on tier 3.
Hey - Nicholas is right.
We don't have an automated retry option at the moment. I would recommend increasing your tier with OpenAI support. You can also add more prepaid funds to your OpenAI account which would allow you to have faster processing limits.
Sorry for the inconvenience, thank you.