Enhancement: Support for Vertex AI model 'gemini-1.5-pro-002'

[schnaker85]

What features would you like to see added?

hi guys,

Currently, the supported models are for Vertex AI are

# Vertex AI
# GOOGLE_MODELS=gemini-1.5-flash-preview-0514,gemini-1.5-pro-preview-0514,gemini-1.0-pro-vision-001,gemini-1.0-pro-002,gemini-1.0-pro-001,gemini-pro-vision,gemini-1.0-pro,gemini-1.5-pro-001

We would like to use the gemini-1.5-pro-002. We already tried and it resulted in an error while processing the response. (We simply switched the model from gemini-1.5-pro-001 to gemini-1.5-pro-002).
See the attached Screenshot and the log entries.

Thanks and Cheers
dani

More details

Log Output:

2024-10-17T08:11:11.229Z debug: Creating VertexAI client
2024-10-17T08:11:11.236Z debug: [saveConvo] api/app/clients/BaseClient.js - saveMessageToDatabase #saveConvo
2024-10-17T08:11:18.338Z error: [handleAbortError] AI response error; aborting request: Aborted
2024-10-17T08:11:18.339Z warn: AI Response error for conversation a6f672c3-713e-4510-84d2-9b045d40a7e5 likely caused by Google censor/filter
2024-10-17T08:11:18.339Z error: [handleAbortError] error while trying to abort message Cannot set headers after they are sent to the client

Which components are impacted by your request?

No response

Pictures

Code of Conduct

• I agree to follow this project's Code of Conduct

[Dual-0]

works on my site:

[JeongJuhyeon]

works on my site:

Try with a longer prompt that will generate a longer completion. As you can in see the original post it works until a certain point where it stops generating.

I can confirm that I am seeing the same issue: #4283

Similar here: #4358

[djuillard]

I confirm I experience the same issue through Vertex AI. This is strange because when I use the exact same API with same json conf file with another API client (n8n), it works. I am not a developer, so I guess that there are some different ways to query the APIs....