Adding Gemini support

[ykeremy]

LiteLLM docs for Gemini: https://litellm.vercel.app/docs/providers/gemini

Required steps for integrating a new LLM model:

1. Define the required variables for the new models

skyvern/skyvern/config.py

Lines 52 to 72 in 5706295

	#####################
	# LLM Configuration #
	#####################
	# ACTIVE LLM PROVIDER
	LLM_KEY: str = "OPENAI_GPT4V"
	# COMMON
	LLM_CONFIG_MAX_TOKENS: int = 4096
	LLM_CONFIG_TEMPERATURE: float = 0
	# LLM PROVIDER SPECIFIC
	ENABLE_OPENAI: bool = True
	ENABLE_ANTHROPIC: bool = False
	ENABLE_AZURE: bool = False
	# OPENAI
	OPENAI_API_KEY: str | None = None
	# ANTHROPIC
	ANTHROPIC_API_KEY: str | None = None
	# AZURE
	AZURE_DEPLOYMENT: str | None = None
	AZURE_API_KEY: str | None = None
	AZURE_API_BASE: str | None = None
	AZURE_API_VERSION: str | None = None

2. Implement the configuration for the new models and register them

skyvern/skyvern/forge/sdk/api/llm/config_registry.py

Lines 57 to 59 in 5706295

	if SettingsManager.get_settings().ENABLE_OPENAI:
	LLMConfigRegistry.register_config("OPENAI_GPT4_TURBO", LLMConfig("gpt-4-turbo-preview", ["OPENAI_API_KEY"], False))
	LLMConfigRegistry.register_config("OPENAI_GPT4V", LLMConfig("gpt-4-vision-preview", ["OPENAI_API_KEY"], True))

3. Update Skyvern setup script with the LLM configuration options

skyvern/setup.sh

Line 39 in 5706295

setup_llm_providers() {

[unaisshemim]

Can you assign this to me

[ykeremy]

🎉 Let us know if you have any question / need any help. Happy coding!

[unaisshemim]

Is there any thing should be changed in the .env.example file

[unaisshemim]

Is there any specific code formatter using here

[github-actions]

This issue is stale because it has been open for 30 days with no activity.