Hi
I am trying to fully understand where processing takes place using gemini models when a particular location is selected. I need my data to be resident in the UK and I want to use Gen AI, so I will choose the europe-west2 region which is in London. This much is clear to me based on the link below
Generative AI on Vertex AI locations | Google Cloud
However, what is not clear to me is what the section in the screenshot below means:
It reads :
Important: Machine learning (ML) processing for gemini-1.0-pro-001, gemini-1.0-pro-002, gemini-1.0-pro-vision-001, imagegeneration@005, and all available Anthropic Claude models occurs within the US when requests are made to regionally-available APIs in the US, or within the EU when requests are made to regionally-available APIs in Europe.
My questions are what is "Machine learning (ML) processing" mean in this context is it all requests made to Gemini or just a subset of them or something else? If in my AP call I specify "europe-west2" does this mean that my request will be or may be processed in a different European region. The UK is not within the EU
Thanks
Hello BernardC,
Welcome to Google Cloud Community!
In the screenshot you provided, Machine learning (ML) processing specifically mentions certain models such as gemini-1.0-pro-001, gemini-1.0-pro-002, gemini-1.0-pro-vision-001, imagegeneration@005, and all available Anthropic Claude models. Here is the list included in the Anthropic Claude models:
Meaning all these models occur within the US when requests are made to regionally-available APIs in the US, or within the EU when requests are made to regionally-available APIs in Europe.
In your case, if in your API call you specified “europe-west2” and you are using a model that is not included in the listed above models, it means that your request will be processed in London, United Kingdom.
I hope the above information is helpful.
User | Count |
---|---|
2 | |
2 | |
1 | |
1 | |
1 |