The api call returns
The response is likely blocked by the safety filters.
Response:
{
"prompt_feedback": {
"block_reason": "PROHIBITED_CONTENT"
},
"usage_metadata": {
"prompt_token_count": 12864,
"total_token_count": 12864
}
}
400 User has requested a restricted HarmBlockThreshold setting BLOCK_NONE. You can get access either (a) through an allowlist via your Google account team, or (b) by switching your account type to monthly invoiced billing via this instruction: https://cloud.google.com/billing/docs/how-to/invoiced-billing.
And there is no explanation whatsoever on solving it.
Hi @pshah,
Welcome to Google Cloud Community!
The error message you're getting indicates two things:
Upon checking, there’s already an existing internal discussion to improve the safety settings.
Meanwhile, as a workaround, you may try the following approach:
1. Revise your prompt
I hope this helps.
Configure safety attributes | Generative AI on Vertex AI | Google Cloud
User | Count |
---|---|
1 | |
1 | |
1 | |
1 | |
1 |