Gemini 1&1.5 Pro Vertex AI returns empty Candidate with finish_reason 'OTHER' for a particular name.

[johnin]

I am making a virtual chat assistant in which you can get medical info by name. I prompted gemini-1.0/1.5 pro to return a json string when a name is given.
For Example:
USER: Check if any alerts were raised for Alexander in the past 3 hours
MODEL:  {"Name": \["Alexander"], "Duration": 180}

This works for most of the names and even some which are not even names.
USER: Check alerts for Why you do this gemini-1.5-pro-preview-0409
MODEL:{"Name": ["Why you do this gemini-1.5-pro-preview-0409"], "Duration": 1440}

But I get 0 Candidates and finish reason 'OTHER' for the name 'Saraswathi'.
USER: check alerts for saraswathi
candidates {
content {
role: "model"
}
finish_reason: OTHER
}
usage_metadata {
prompt_token_count: 822
total_token_count: 822
}
The name Saraswathi is also pretty common in India, so any exclusion is not viable.
I have seen other questions in this space talking about the same thing, but with no satisfactory solution paired to them. 

I have tested the same using Google AI Studio API using genai PythonSDK model 

'gemini-1.5-pro-latest' and it works as expected. Only VertexAI API is showcasing this problem. What should I do(on top of praying)?

generation_config = { 

"temperature": 0.2,

"top_p": 0.1,

"top_k": 1,

"max_output_tokens": 2048,

}

Thanks

[johnin]

Hi @lsolatorio can you please share some info on this situation?

[bentobox]

I've seen the same thing, only getting usage metadata back with no candidates at all, not even an empty array.