Sonal Saldanha

Managed to implement gemini support [here](https://github.com/jxnl/instructor/pull/684). Not 100% compatible with all of instructor's concept given the mismatch in API design but it's a start. Would love some feedback.

This does sound like a sane default to me, especially when retries come into the picture. Would be cumbersome to have to set this env variable each time. But maybe...

> **Describe the solution you'd like** > Instructor should patch Claude's API and surface the `usage` dictionary as part of the output in the second tuple like so: `structured_output._raw_response.usage` works...

@ivanleomk my bad, looks like I missed a case. Updated & should work now.

> Not super familiar with Gemini, possible to show an example of how to setup GenerationConfig or how it's typically used? > > Want to make sure it works in...

> Any idea what's up with this? Also, have you tried the native tool calling from gemini ( https://ai.google.dev/gemini-api/docs/function-calling ) , wondering how it stacks up against your specific implementation...

> @ssonal how much would it take to implement function calling using this instead? > > https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/call-gemini-using-openai-library > > Wondering if it might be easier to ensure libs remain consistent...

> @ssonal Hmm have you tried not including a system prompt itself? I think that might not be a bad experiment to try. > @ivanleomk Sure, let me make this...

> @ssonal Hmm have you tried not including a system prompt itself? I think that might not be a bad experiment to try. > @ivanleomk updated with this change. All...

#726 should take care of this