[BUG] -m gemini-pro-vision asking for OPENAI_API_KEY

[FelipeLujan]

Found a bug? Please fill out the sections below. 👍

Describe the bug

Ran operate -m gemini-pro-vision, entered my gemini API key from google AIstudio, but when I request something I always get

[Self-Operating Computer | gemini-pro-vision]
Hello, I can help you with anything. What would you like done?
[User]
turn on night mode
[Self-Operating Computer][Operate] That did not work. Trying another method 
[Self-Operating Computer][Error] -> The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable 

Steps to Reproduce

1. Install with pip
2. run operate -m gemini-pro-vision and enter API key
3. insert any prompt
4. also tried by setting up the GOOGLE_API_KEY env variable in a .env file as well as export GOOGLE_API_KEY=abc123

Expected Behavior

The machine, self-operates

Actual Behavior:

Error in the console

Environment

• OS: Mac os sonomo 14.3
• Model Used (e.g., GPT-4v, Gemini Pro Vision): Gemini pro vision
• Framework Version (optional):

Screenshots

Additional context

Add any other context about the problem here.

[ItosEO]

thw same problem

[shengjh]

use --verbose, it seems that the execution of the instructions given by the gemini failed, so try to request the instructions of chatgpt.