General feedback for Gemini API

[Sam_Saffron]

@rakyll is working on improving the Gemini API story following:

Brendan Dolan-Gavitt

And

Jaana Dogan ヤナ ドガン

I wanted to share some of my challenges here and see if the community have any others to share:

Generating content  |  Gemini API  |  Google AI for...

• The need for alt=sse in streamGenerateContent is very surprising, only documented as a side effect in the Shell example
• No actual response body examples are presented for the shell examples
• Tools are documented on separate pages, the first click through provides schema but does not provide examples (Caching  |  Gemini API  |  Google AI for Developers which is linked vs Présentation de l'appel de fonction avec l'API Gemini  |  Gemini API  |  Google AI for Developers which is also linked)

REST examples are missing in all sorts of spots:

• Explora las capacidades de audio con la API de Gemini  |  Gemini API  |  Google AI for Developers
• https://ai.google.dev/gemini-api/docs/code-execution?lang=python
• Generate JSON output with the Gemini API  |  Google AI for Developers
  etc…

It would be nice if the same examples text generation had carried through consistently. Generate text using the Gemini API  |  Google AI for Developers

• You have to do tons of digging to find model list and figure out which model you should use. gemini-1.5-pro-exp-0827 vs gemini-1.5-pro-exp-0801 vs gemini-1.5-pro-001 vs gemini-1.5-pro-latest

• Tool calls changing rules was somewhat confusing in experimental versions, rule changes should be documented: Gemini Pro Experimental 0801 is refusing to run functions - #11 by Sam_Saffron

• The API overall is quite verbose and nested, it makes it harder to implement compared to anthropic / open ai

Anyone else got feedback? Other feedback I saw here is:

• [Feedback] Focus on Developers First
• Safety settings are a surprise, especially compared to other vendors

[innovatix]

Also, @Sam_Saffron, there is no single, unified documentation that is straightforward and easy to follow. The current documentation is scattered across various channels.

[Vishal]

Hey Sam, thanks for sharing your challenges and this feedback! We’re currently working on adding REST examples throughout our documentation. Hoping to have those land within the next couple weeks.