Automate browser based workflows with AI
Python aiapiautomationbrowserbrowser-automationcomputergptllmplaywrightpowerautomatepuppeteerpythonrpaseleniumvisionworkflow
feat: Add new model provider Novita AI (#1508)
Jasone54977ef29bb
diff --git a/.env.example b/.env.exampleindex 8da78f369..c9867fe46 100644--- a/.env.example+++ b/.env.example@@ -38,6 +38,11 @@ ENABLE_GEMINI=false# GEMINI_API_KEY: Your Gemini API key for accessing models like GPT-4.GEMINI_API_KEY=""+# ENABLE_NOVITA: Set to true to enable Novita AI as a language model provider.+ENABLE_NOVITA=false+# NOVITA_API_KEY: Your Novita AI API key.+NOVITA_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=""diff --git a/README.md b/README.mdindex 8a1b1167e..cdfca86d4 100644--- a/README.md+++ b/README.md@@ -276,6 +276,7 @@ More extensive documentation can be found on our [documentation website](https:/| Ollama | Coming soon (contributions welcome) || Gemini | Coming soon (contributions welcome) || Llama 3.2 | Coming soon (contributions welcome) |+| Novita AI | Llama 3.1 (8B, 70B), Llama 3.2 (1B, 3B, 11B Vision) |#### Environment Variables| Variable | Description| Type | Sample Value|@@ -285,8 +286,9 @@ More extensive documentation can be found on our [documentation website](https:/| `ENABLE_AZURE` | Register Azure OpenAI models | Boolean | `true`, `false` || `ENABLE_BEDROCK` | Register AWS Bedrock models. To use AWS Bedrock, you need to make sure your [AWS configurations](https://github.com/boto/boto3?tab=readme-ov-file#using-boto3) are set up correctly first. | Boolean | `true`, `false` || `ENABLE_GEMINI` | Register Gemini models| Boolean | `true`, `false` |+| `ENABLE_NOVITA`| Register Novita AI 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`, `GEMINI_PRO`, `GEMINI_FLASH`, `BEDROCK_AMAZON_NOVA_PRO`, `BEDROCK_AMAZON_NOVA_LITE`|-| `SECONDARY_LLM_KEY` | The name of the model for mini agents skyvern runs with | 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`, `GEMINI_PRO`, `GEMINI_FLASH`|+| `SECONDARY_LLM_KEY` | The name of the model for mini agents skyvern runs with | 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`, `GEMINI_PRO`, `GEMINI_FLASH`, `NOVITA_LLAMA_3_3_70B`, `NOVITA_LLAMA_3_2_1B`, `NOVITA_LLAMA_3_2_3B`, `NOVITA_LLAMA_3_2_11B_VISION`, `NOVITA_LLAMA_3_1_8B`, `NOVITA_LLAMA_3_1_70B`, `NOVITA_LLAMA_3_1_405B`, `NOVITA_LLAMA_3_8B`, `NOVITA_LLAMA_3_70B`|| `OPENAI_API_KEY` | OpenAI API Key | String | `sk-1234567890` || `OPENAI_API_BASE` | OpenAI API Base, optional | String | `https://openai.api.base` || `OPENAI_ORGANIZATION` | OpenAI Organization ID, optional | String | `your-org-id` |diff --git a/setup.sh b/setup.shindex ceac5c0ef..c06a2d41e 100755--- a/setup.sh+++ b/setup.sh@@ -115,6 +115,33 @@ setup_llm_providers() {update_or_add_env_var "ENABLE_GEMINI" "false"fi+ # Novita AI Configuration+ echo "To enable Novita AI, you must have an Novita AI API key."+ read -p "Do you want to enable Novita AI (y/n)? " enable_novita+ if [[ "$enable_novita" == "y" ]]; then+ read -p "Enter your Novita AI API key: " novita_api_key+ if [ -z "$novita_api_key" ]; then+ echo "Error: Novita AI API key is required."+ echo "Novita AI will not be enabled."+ else+ update_or_add_env_var "NOVITA_API_KEY" "$novita_api_key"+ update_or_add_env_var "ENABLE_NOVITA" "true"+ model_options+=(+ "NOVITA_LLAMA_3_3_70B"+ "NOVITA_LLAMA_3_2_1B"+ "NOVITA_LLAMA_3_2_3B"+ "NOVITA_LLAMA_3_2_11B_VISION"+ "NOVITA_LLAMA_3_1_8B"+ "NOVITA_LLAMA_3_1_70B"+ "NOVITA_LLAMA_3_1_405B"+ "NOVITA_LLAMA_3_8B"+ "NOVITA_LLAMA_3_70B"+ )+ fi+ else+ update_or_add_env_var "ENABLE_NOVITA" "false"+ fi+# Model Selectionif [ ${#model_options[@]} -eq 0 ]; thenecho "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."diff --git a/skyvern/config.py b/skyvern/config.pyindex 065de7a3c..aa82ecd55 100644--- a/skyvern/config.py+++ b/skyvern/config.py@@ -124,6 +124,11 @@ class Settings(BaseSettings):# GEMINIGEMINI_API_KEY: str | None = None+ # NOVITA AI+ ENABLE_NOVITA: bool = False+ NOVITA_API_KEY: str | None = None+ NOVITA_API_VERSION: str = "v3"+# TOTP SettingsTOTP_LIFESPAN_MINUTES: int = 10VERIFICATION_CODE_INITIAL_WAIT_TIME_SECS: int = 40diff --git a/skyvern/forge/sdk/api/llm/api_handler_factory.py b/skyvern/forge/sdk/api/llm/api_handler_factory.pyindex b0b080264..17bdee7d4 100644--- a/skyvern/forge/sdk/api/llm/api_handler_factory.py+++ b/skyvern/forge/sdk/api/llm/api_handler_factory.py@@ -147,7 +147,11 @@ class LLMAPIHandlerFactory:ai_suggestion=ai_suggestion,)if step:- llm_cost = litellm.completion_cost(completion_response=response)+ try:+ llm_cost = litellm.completion_cost(completion_response=response)+ except Exception as e:+ LOG.exception("Failed to calculate LLM cost", error=str(e))+ llm_cost = 0prompt_tokens = response.get("usage", {}).get("prompt_tokens", 0)completion_tokens = response.get("usage", {}).get("completion_tokens", 0)await app.DATABASE.update_step(@@ -289,7 +293,11 @@ class LLMAPIHandlerFactory:)if step:- llm_cost = litellm.completion_cost(completion_response=response)+ try:+ llm_cost = litellm.completion_cost(completion_response=response)+ except Exception as e:+ LOG.exception("Failed to calculate LLM cost", error=str(e))+ llm_cost = 0prompt_tokens = response.get("usage", {}).get("prompt_tokens", 0)completion_tokens = response.get("usage", {}).get("completion_tokens", 0)await app.DATABASE.update_step(diff --git a/skyvern/forge/sdk/api/llm/config_registry.py b/skyvern/forge/sdk/api/llm/config_registry.pyindex 46f68696c..4c0a87e6f 100644--- a/skyvern/forge/sdk/api/llm/config_registry.py+++ b/skyvern/forge/sdk/api/llm/config_registry.py@@ -52,6 +52,7 @@ if not any(settings.ENABLE_AZURE_GPT4O_MINI,settings.ENABLE_BEDROCK,settings.ENABLE_GEMINI,+ settings.ENABLE_NOVITA,]):raise NoProviderEnabledError()@@ -287,3 +288,140 @@ if settings.ENABLE_GEMINI:max_output_tokens=8192,),)++if settings.ENABLE_NOVITA:+ LLMConfigRegistry.register_config(+ "NOVITA_LLAMA_3_3_70B",+ LLMConfig(+ "openai/meta-llama/llama-3.3-70b-instruct",+ ["NOVITA_API_KEY"],+ supports_vision=False,+ add_assistant_prefix=False,+ litellm_params=LiteLLMParams(+ api_base="https://api.novita.ai/v3/openai",+ api_key=settings.NOVITA_API_KEY,+ api_version=settings.NOVITA_API_VERSION,+ model_info={"model_name": "openai/meta-llama/llama-3.3-70b-instruct"},+ ),+ ),+ )+ LLMConfigRegistry.register_config(+ "NOVITA_LLAMA_3_2_1B",+ LLMConfig(+ "openai/meta-llama/llama-3.2-1b-instruct",+ ["NOVITA_API_KEY"],+ supports_vision=False,+ add_assistant_prefix=False,+ litellm_params=LiteLLMParams(+ api_base="https://api.novita.ai/v3/openai",+ api_key=settings.NOVITA_API_KEY,+ api_version=settings.NOVITA_API_VERSION,+ model_info={"model_name": "openai/meta-llama/llama-3.2-1b-instruct"},+ ),+ ),+ )+ LLMConfigRegistry.register_config(+ "NOVITA_LLAMA_3_2_3B",+ LLMConfig(+ "openai/meta-llama/llama-3.2-3b-instruct",+ ["NOVITA_API_KEY"],+ supports_vision=False,+ add_assistant_prefix=False,+ litellm_params=LiteLLMParams(+ api_base="https://api.novita.ai/v3/openai",+ api_key=settings.NOVITA_API_KEY,+ api_version=settings.NOVITA_API_VERSION,+ model_info={"model_name": "openai/meta-llama/llama-3.2-3b-instruct"},+ ),+ ),+ )+ LLMConfigRegistry.register_config(+ "NOVITA_LLAMA_3_2_11B_VISION",+ LLMConfig(+ "openai/meta-llama/llama-3.2-11b-vision-instruct",+ ["NOVITA_API_KEY"],+ supports_vision=True,+ add_assistant_prefix=False,+ litellm_params=LiteLLMParams(+ api_base="https://api.novita.ai/v3/openai",+ api_key=settings.NOVITA_API_KEY,+ api_version=settings.NOVITA_API_VERSION,+ model_info={"model_name": "openai/meta-llama/llama-3.2-11b-vision-instruct"},+ ),+ ),+ )+ LLMConfigRegistry.register_config(+ "NOVITA_LLAMA_3_1_8B",+ LLMConfig(+ "openai/meta-llama/llama-3.1-8b-instruct",+ ["NOVITA_API_KEY"],+ supports_vision=False,+ add_assistant_prefix=False,+ litellm_params=LiteLLMParams(+ api_base="https://api.novita.ai/v3/openai",+ api_key=settings.NOVITA_API_KEY,+ api_version=settings.NOVITA_API_VERSION,+ model_info={"model_name": "openai/meta-llama/llama-3.1-8b-instruct"},+ ),+ ),+ )+ LLMConfigRegistry.register_config(+ "NOVITA_LLAMA_3_1_70B",+ LLMConfig(+ "openai/meta-llama/llama-3.1-70b-instruct",+ ["NOVITA_API_KEY"],+ supports_vision=False,+ add_assistant_prefix=False,+ litellm_params=LiteLLMParams(+ api_base="https://api.novita.ai/v3/openai",+ api_key=settings.NOVITA_API_KEY,+ api_version=settings.NOVITA_API_VERSION,+ model_info={"model_name": "openai/meta-llama/llama-3.1-70b-instruct"},+ ),+ ),+ )+ LLMConfigRegistry.register_config(+ "NOVITA_LLAMA_3_1_405B",+ LLMConfig(+ "openai/meta-llama/llama-3.1-405b-instruct",+ ["NOVITA_API_KEY"],+ supports_vision=False,+ add_assistant_prefix=False,+ litellm_params=LiteLLMParams(+ api_base="https://api.novita.ai/v3/openai",+ api_key=settings.NOVITA_API_KEY,+ api_version=settings.NOVITA_API_VERSION,+ model_info={"model_name": "openai/meta-llama/llama-3.1-405b-instruct"},+ ),+ ),+ )+ LLMConfigRegistry.register_config(+ "NOVITA_LLAMA_3_8B",+ LLMConfig(+ "openai/meta-llama/llama-3-8b-instruct",+ ["NOVITA_API_KEY"],+ supports_vision=False,+ add_assistant_prefix=False,+ litellm_params=LiteLLMParams(+ api_base="https://api.novita.ai/v3/openai",+ api_key=settings.NOVITA_API_KEY,+ api_version=settings.NOVITA_API_VERSION,+ model_info={"model_name": "openai/meta-llama/llama-3-8b-instruct"},+ ),+ ),+ )+ LLMConfigRegistry.register_config(+ "NOVITA_LLAMA_3_70B",+ LLMConfig(+ "openai/meta-llama/llama-3-70b-instruct",+ ["NOVITA_API_KEY"],+ supports_vision=False,+ add_assistant_prefix=False,+ litellm_params=LiteLLMParams(+ api_base="https://api.novita.ai/v3/openai",+ api_key=settings.NOVITA_API_KEY,+ api_version=settings.NOVITA_API_VERSION,+ model_info={"model_name": "openai/meta-llama/llama-3-70b-instruct"},+ ),+ ),+ )