Keyboard shortcuts

Press or to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

Deployment Configuration

When deploying a workflow, Agent Studio applies a DeploymentConfig that controls runtime behavior — LLM generation parameters, tool configuration, MCP server secrets, and environment variables.

DeploymentConfig

class DeploymentConfig(BaseModel):
    generation_config: Dict = {}
    tool_config: Dict[str, Dict[str, str]] = {}
    mcp_config: Dict[str, Dict[str, str]] = {}
    llm_config: Dict = {}
    environment: Dict = {}
FieldTypeDescription
generation_configobjectDefault LLM generation parameters applied to all language models
tool_configobjectTool-specific configuration keyed by tool instance ID
mcp_configobjectMCP server secrets keyed by MCP instance ID
llm_configobjectLLM API keys and endpoint overrides
environmentobjectAdditional environment variables passed to the deployment

Default Generation Config

When no overrides are provided, Agent Studio uses these defaults:

{
  "do_sample": true,
  "temperature": 0.1,
  "max_new_tokens": 4096,
  "top_p": 1,
  "top_k": 50,
  "num_beams": 1,
  "max_length": null
}

Language Model Configuration

At deployment time, each language model receives connection details:

class Input__LanguageModelConfig(BaseModel):
    provider_model: str              # Provider-specific model identifier (e.g., "gpt-4o")
    model_type: SupportedModelTypes  # Provider type enum
    api_base: Optional[str]          # Custom API endpoint
    api_key: Optional[str]           # Authentication key
    extra_headers: Optional[Dict[str, str]]  # Additional HTTP headers

    # AWS Bedrock specific
    aws_region_name: Optional[str]
    aws_access_key_id: Optional[str]
    aws_secret_access_key: Optional[str]
    aws_session_token: Optional[str]

Supported Model Types

TypeDescriptionRequired Fields
OPENAIOpenAI APIapi_key
OPENAI_COMPATIBLEOpenAI-compatible endpointsapi_base, api_key
AZURE_OPENAIAzure OpenAI Serviceapi_base, api_key
GEMINIGoogle Geminiapi_key
ANTHROPICAnthropic Claudeapi_key
CAIICloudera AI Inferenceapi_base, api_key
BEDROCKAWS Bedrockaws_region_name, aws_access_key_id, aws_secret_access_key

Deployment Targets

Agent Studio supports multiple deployment target types:

TargetDescription
workbench_modelCML Model endpoint — the primary deployment target
langgraph_serverLangGraph Server deployment
ai_inferenceCloudera AI Inference (planned)
model_registryModel Registry deployment (planned)

Workflow Source Types

Workflows can be deployed from multiple sources:

SourceDescription
workflowAn existing workflow in the current Agent Studio instance
workflow_templateA workflow template (instantiates first, then deploys)
workflow_artifactA pre-packaged tar.gz artifact
githubA GitHub repository URL (cloned and packaged by Agent Studio)

Environment Variables at Runtime

Deployed workflows receive these environment variables:

VariableDescription
AGENT_STUDIO_OPS_ENDPOINTPhoenix observability endpoint for trace export
AGENT_STUDIO_WORKFLOW_ARTIFACTPath to the extracted deployment artifact
AGENT_STUDIO_WORKFLOW_DEPLOYMENT_CONFIGJSON-encoded DeploymentConfig
AGENT_STUDIO_MODEL_EXECUTION_DIRWorking directory for model execution
CDSW_APIV2_KEYCML API v2 authentication key
CDSW_PROJECT_IDCML project identifier
CREWAI_DISABLE_TELEMETRYSet to disable CrewAI’s built-in telemetry