How can I set the safety filter in a Gemini proxy?
I have the following but i still get rejections on tame and normal things
safety_settings: [
{ category: 'HARM_CATEGORY_HARASSMENT', threshold: 'BLOCK_NONE' },
{ category: 'HARM_CATEGORY_HATE_SPEECH', threshold: 'BLOCK_NONE' },
{
category: 'HARM_CATEGORY_SEXUALLY_EXPLICIT',
threshold: 'BLOCK_NONE'
},
{
category: 'HARM_CATEGORY_DANGEROUS_CONTENT',
threshold: 'BLOCK_NONE'
}
]
}
Chat completion request error: Internal Server Error {"error":"Internal server error","proxy_note":"Error while executing proxy response middleware: googleAIBlockingResponseHandler (Cannot read properties of undefined (reading '0'))"}