add gemeni pro support (#1307)

.env.example

@@ -33,6 +33,11 @@ AZURE_GPT4O_MINI_API_KEY=""
 AZURE_GPT4O_MINI_API_BASE=""
 AZURE_GPT4O_MINI_API_VERSION=""
 
+# ENABLE_GEMINI: Set to true to enable Gemini as a language model provider.
+ENABLE_GEMINI=false
+# GEMINI_API_KEY: Your Gemini API key for accessing models like GPT-4.
+GEMINI_API_KEY=""
+
 # LLM_KEY: The chosen language model to use. This should be one of the models
 # provided by the enabled LLM providers (e.g., OPENAI_GPT4_TURBO, OPENAI_GPT4V, ANTHROPIC_CLAUDE3, AZURE_OPENAI_GPT4V).
 LLM_KEY=""

README.md

@@ -284,6 +284,7 @@ More extensive documentation can be found on our [documentation website](https:/
 | `ENABLE_ANTHROPIC` | Register Anthropic models| Boolean | `true`, `false` |
 | `ENABLE_AZURE` | Register Azure OpenAI models | Boolean | `true`, `false` |
 | `ENABLE_BEDROCK` | Register AWS Bedrock models| Boolean | `true`, `false` |
+| `ENABLE_GEMINI` | Register Gemini models| Boolean | `true`, `false` |
 | `LLM_KEY` | The name of the model you want to use | String | Currently supported llm keys: `OPENAI_GPT4_TURBO`, `OPENAI_GPT4V`, `OPENAI_GPT4O`, `OPENAI_GPT4O_MINI`, `ANTHROPIC_CLAUDE3`, `ANTHROPIC_CLAUDE3_OPUS`, `ANTHROPIC_CLAUDE3_SONNET`, `ANTHROPIC_CLAUDE3_HAIKU`, `ANTHROPIC_CLAUDE3.5_SONNET`, `BEDROCK_ANTHROPIC_CLAUDE3_OPUS`, `BEDROCK_ANTHROPIC_CLAUDE3_SONNET`, `BEDROCK_ANTHROPIC_CLAUDE3_HAIKU`, `BEDROCK_ANTHROPIC_CLAUDE3.5_SONNET`, `AZURE_OPENAI` |
 | `OPENAI_API_KEY` | OpenAI API Key | String | `sk-1234567890` |
 | `OPENAI_API_BASE` | OpenAI API Base, optional | String | `https://openai.api.base` |
@@ -293,6 +294,7 @@ More extensive documentation can be found on our [documentation website](https:/
 | `AZURE_DEPLOYMENT` | Azure OpenAI Deployment Name | String | `skyvern-deployment`|
 | `AZURE_API_BASE` | Azure deployment api base url| String | `https://skyvern-deployment.openai.azure.com/`|
 | `AZURE_API_VERSION` | Azure API Version| String | `2024-02-01`|
+| `GEMINI_API_KEY` | Gemini API Key| String | `your_google_gemini_api_key`|
 
 # Feature Roadmap
 This is our planned roadmap for the next few months. If you have any suggestions or would like to see a feature added, please don't hesitate to reach out to us [via email](mailto:founders@skyvern.com) or [discord](https://discord.gg/fG2XXEuQX3).

setup.sh

@@ -98,6 +98,23 @@ setup_llm_providers() {
         update_or_add_env_var "ENABLE_AZURE" "false"
     fi
 
+    #Gemini Configuartion
+    echo "To enable Gemini, you must have an Gemini API key."
+    read -p "Do you want to enable Gemini (y/n)? " enable_gemini
+    if [[ "$enable_gemini" == "y" ]]; then
+        read -p "Enter your Gemini API key: " gemini_api_key
+        if [ -z "$gemini_api_key" ]; then
+            echo "Error: Gemini API key is required."
+            echo "Gemini will not be enabled."
+        else
+            update_or_add_env_var "GEMINI_API_KEY" "$gemini_api_key"
+            update_or_add_env_var "ENABLE_GEMINI" "true"
+            model_options+=("GEMINI_PRO")
+        fi
+    else
+        update_or_add_env_var "ENABLE_GEMINI" "false"
+    fi
+
     # Model Selection
     if [ ${#model_options[@]} -eq 0 ]; then
         echo "No LLM providers enabled. You won't be able to run Skyvern unless you enable at least one provider. You can re-run this script to enable providers or manually update the .env file."

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

@@ -51,6 +51,7 @@ if not any(
         settings.ENABLE_AZURE,
         settings.ENABLE_AZURE_GPT4O_MINI,
         settings.ENABLE_BEDROCK,
+        settings.ENABLE_GEMINI,
     ]
 ):
     raise NoProviderEnabledError()
@@ -246,3 +247,15 @@ if settings.ENABLE_AZURE_GPT4O_MINI:
             add_assistant_prefix=False,
         ),
     )
+
+if settings.ENABLE_GEMINI:
+    LLMConfigRegistry.register_config(
+        "GEMINI_PRO",
+        LLMConfig(
+            "gemini/gemini-pro-vision",
+            ["GEMINI_API_KEY"],
+            supports_vision=True,
+            add_assistant_prefix=False,
+            max_output_tokens=8192,
+        ),
+    )