Module `scenario.config.model`

Model configuration for Scenario.

This module provides configuration classes for LLM model settings used by user simulator and judge agents in the Scenario framework.

Expand source code

"""
Model configuration for Scenario.

This module provides configuration classes for LLM model settings used by
user simulator and judge agents in the Scenario framework.
"""

from typing import Optional
from pydantic import BaseModel


class ModelConfig(BaseModel):
    """
    Configuration for LLM model settings.

    This class encapsulates all the parameters needed to configure an LLM model
    for use with user simulator and judge agents in the Scenario framework.

    Attributes:
        model: The model identifier (e.g., "openai/gpt-4.1", "anthropic/claude-3-sonnet")
        api_base: Optional base URL where the model is hosted
        api_key: Optional API key for the model provider
        temperature: Sampling temperature for response generation (0.0 = deterministic, 1.0 = creative)
        max_tokens: Maximum number of tokens to generate in responses

    Example:
        ```
        model_config = ModelConfig(
            model="openai/gpt-4.1",
            api_base="https://api.openai.com/v1",
            api_key="your-api-key",
            temperature=0.1,
            max_tokens=1000
        )
        ```
    """

    model: str
    api_base: Optional[str] = None
    api_key: Optional[str] = None
    temperature: float = 0.0
    max_tokens: Optional[int] = None

Classes

class ModelConfig (**data: Any)

Configuration for LLM model settings.

This class encapsulates all the parameters needed to configure an LLM model for use with user simulator and judge agents in the Scenario framework.

Attributes

model: The model identifier (e.g., "openai/gpt-4.1", "anthropic/claude-3-sonnet")
api_base: Optional base URL where the model is hosted
api_key: Optional API key for the model provider
temperature: Sampling temperature for response generation (0.0 = deterministic, 1.0 = creative)
max_tokens: Maximum number of tokens to generate in responses

Example

model_config = ModelConfig(
    model="openai/gpt-4.1",
    api_base="https://api.openai.com/v1",
    api_key="your-api-key",
    temperature=0.1,
    max_tokens=1000
)

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Expand source code

class ModelConfig(BaseModel):
    """
    Configuration for LLM model settings.

    This class encapsulates all the parameters needed to configure an LLM model
    for use with user simulator and judge agents in the Scenario framework.

    Attributes:
        model: The model identifier (e.g., "openai/gpt-4.1", "anthropic/claude-3-sonnet")
        api_base: Optional base URL where the model is hosted
        api_key: Optional API key for the model provider
        temperature: Sampling temperature for response generation (0.0 = deterministic, 1.0 = creative)
        max_tokens: Maximum number of tokens to generate in responses

    Example:
        ```
        model_config = ModelConfig(
            model="openai/gpt-4.1",
            api_base="https://api.openai.com/v1",
            api_key="your-api-key",
            temperature=0.1,
            max_tokens=1000
        )
        ```
    """

    model: str
    api_base: Optional[str] = None
    api_key: Optional[str] = None
    temperature: float = 0.0
    max_tokens: Optional[int] = None

Ancestors

pydantic.main.BaseModel

Class variables

var api_base : str | None
var api_key : str | None
var max_tokens : int | None
var model : str
var model_config
var temperature : float