Class swarmauri_standard.llms.GeminiProModel.GeminiProModel

swarmauri_standard.llms.GeminiProModel.GeminiProModel

GeminiProModel(api_key, **kwargs)

Bases: LLMBase

GeminiProModel is a class interface for interacting with the Gemini language model API.

ATTRIBUTE	DESCRIPTION
api_key	API key for authentication with the Gemini API. TYPE: str
allowed_models	List of allowed model names for selection. TYPE: List[str]
name	Default name of the model in use. TYPE: str
type	Type identifier for GeminiProModel. TYPE: Literal

Provider resources: https://deepmind.google/technologies/gemini/pro/

Initializes the GeminiProModel object with the given API key.

PARAMETER	DESCRIPTION
api_key	The API key for the GeminiProModel. TYPE: SecretStr

Source code in swarmauri_standard/llms/GeminiProModel.py

def __init__(self, api_key: SecretStr, **kwargs):
    """
    Initializes the GeminiProModel object with the given API key.

    Args:
        api_key (SecretStr): The API key for the GeminiProModel.
    """
    super().__init__(api_key=api_key, **kwargs)

    self._client = httpx.Client(
        base_url="https://generativelanguage.googleapis.com/v1beta",
        headers={"Content-Type": "application/json"},
        timeout=self.timeout,
    )

    self._async_client = httpx.AsyncClient(
        base_url="https://generativelanguage.googleapis.com/v1beta",
        headers={"Content-Type": "application/json"},
        timeout=self.timeout,
    )

api_key instance-attribute

api_key

allowed_models class-attribute instance-attribute

allowed_models = [
    "gemini-2.0-flash",
    "gemini-2.0-flash-lite",
    "gemini-2.0-pro-exp-02-05",
    "gemini-1.5-flash",
    "gemini-1.5-flash-8b",
    "gemini-1.5-pro",
]

name class-attribute instance-attribute

name = 'gemini-2.0-flash'

timeout class-attribute instance-attribute

timeout = 600.0

type class-attribute instance-attribute

type = 'GeminiProModel'

model_config class-attribute instance-attribute

model_config = ConfigDict(
    extra="allow", arbitrary_types_allowed=True
)

id class-attribute instance-attribute

id = Field(default_factory=generate_id)

members class-attribute instance-attribute

members = None

owners class-attribute instance-attribute

owners = None

host class-attribute instance-attribute

host = None

default_logger class-attribute

default_logger = None

logger class-attribute instance-attribute

logger = None

resource class-attribute instance-attribute

resource = Field(default=LLM.value, frozen=True)

version class-attribute instance-attribute

version = '0.1.0'

include_usage class-attribute instance-attribute

include_usage = True

BASE_URL class-attribute instance-attribute

BASE_URL = None

predict

predict(conversation, temperature=0.7, max_tokens=25)

Generates a prediction for the given conversation using the specified parameters.

PARAMETER	DESCRIPTION
conversation	The conversation object containing the history of messages. TYPE: Conversation
temperature	The sampling temperature to use. Defaults to 0.7. TYPE: float DEFAULT: 0.7
max_tokens	The maximum number of tokens to generate. Defaults to 256. TYPE: int DEFAULT: 25

RETURNS	DESCRIPTION
Conversation	The updated conversation object with the new message added. TYPE: Conversation

RAISES	DESCRIPTION
HTTPStatusError	If the HTTP request to the generation endpoint fails.

Source code in swarmauri_standard/llms/GeminiProModel.py

@retry_on_status_codes((429, 529), max_retries=1)
def predict(
    self,
    conversation: Conversation,
    temperature: float = 0.7,
    max_tokens: int = 25,
) -> Conversation:
    """
    Generates a prediction for the given conversation using the specified parameters.

    Args:
        conversation (Conversation): The conversation object containing the history of messages.
        temperature (float, optional): The sampling temperature to use. Defaults to 0.7.
        max_tokens (int, optional): The maximum number of tokens to generate. Defaults to 256.

    Returns:
        Conversation: The updated conversation object with the new message added.

    Raises:
        httpx.HTTPStatusError: If the HTTP request to the generation endpoint fails.
    """
    generation_config = {
        "temperature": temperature,
        "top_p": 0.95,
        "top_k": 0,
        "max_output_tokens": max_tokens,
    }

    system_context = self._get_system_context(conversation.history)
    formatted_messages = self._format_messages(conversation.history)
    next_message = formatted_messages.pop()

    payload = {
        "contents": next_message,
        "generationConfig": generation_config,
        "safetySettings": self._safety_settings,
    }
    if system_context:
        payload["systemInstruction"] = system_context

    with DurationManager() as prompt_timer:
        response = self._client.post(
            f"/{self.name}:generateContent?key={self.api_key.get_secret_value()}",
            json=payload,
        )
        response.raise_for_status()

    response_data = response.json()

    message_content = response_data["candidates"][0]["content"]["parts"][0]["text"]

    usage_data = response_data["usageMetadata"]

    if self.include_usage and usage_data:
        usage = self._prepare_usage_data(usage_data, prompt_timer.duration)
        conversation.add_message(AgentMessage(content=message_content, usage=usage))
    else:
        conversation.add_message(AgentMessage(content=message_content))

    return conversation

apredict async

apredict(conversation, temperature=0.7, max_tokens=256)

Asynchronously generates a response for a given conversation using the GeminiProModel.

PARAMETER	DESCRIPTION
conversation	The conversation object containing the history of messages. TYPE: Conversation
temperature	Sampling temperature for response generation. Defaults to 0.7. TYPE: float DEFAULT: 0.7
max_tokens	Maximum number of tokens in the generated response. Defaults to 256. TYPE: int DEFAULT: 256

RETURNS	DESCRIPTION
Conversation	The updated conversation object with the generated response added. TYPE: Conversation

RAISES	DESCRIPTION
HTTPStatusError	If the HTTP request to the generation endpoint fails.

Source code in swarmauri_standard/llms/GeminiProModel.py

@retry_on_status_codes((429, 529), max_retries=1)
async def apredict(
    self,
    conversation: Conversation,
    temperature: float = 0.7,
    max_tokens: int = 256,
) -> Conversation:
    """
    Asynchronously generates a response for a given conversation using the GeminiProModel.

    Args:
        conversation (Conversation): The conversation object containing the history of messages.
        temperature (float, optional): Sampling temperature for response generation. Defaults to 0.7.
        max_tokens (int, optional): Maximum number of tokens in the generated response. Defaults to 256.

    Returns:
        Conversation: The updated conversation object with the generated response added.

    Raises:
        httpx.HTTPStatusError: If the HTTP request to the generation endpoint fails.
    """
    generation_config = {
        "temperature": temperature,
        "top_p": 0.95,
        "top_k": 0,
        "max_output_tokens": max_tokens,
    }

    system_context = self._get_system_context(conversation.history)
    formatted_messages = self._format_messages(conversation.history)
    next_message = formatted_messages.pop()

    payload = {
        "contents": next_message,
        "generationConfig": generation_config,
        "safetySettings": self._safety_settings,
    }
    if system_context:
        payload["systemInstruction"] = system_context

    with DurationManager() as prompt_timer:
        response = await self._async_client.post(
            f"/{self.name}:generateContent?key={self.api_key.get_secret_value()}",
            json=payload,
        )
        response.raise_for_status()

    response_data = response.json()
    message_content = response_data["candidates"][0]["content"]["parts"][0]["text"]
    usage_data = response_data["usageMetadata"]

    if self.include_usage and usage_data:
        usage = self._prepare_usage_data(usage_data, prompt_timer.duration)
        conversation.add_message(AgentMessage(content=message_content, usage=usage))
    else:
        conversation.add_message(AgentMessage(content=message_content))

    return conversation

stream

stream(conversation, temperature=0.7, max_tokens=256)

Streams the response from the model based on the given conversation.

PARAMETER	DESCRIPTION
conversation	The conversation object containing the history of messages. TYPE: Conversation
temperature	The temperature setting for the generation. Defaults to 0.7. TYPE: float DEFAULT: 0.7
max_tokens	The maximum number of tokens to generate. Defaults to 256. TYPE: int DEFAULT: 256

YIELDS	DESCRIPTION
str	Chunks of the generated response text. TYPE:: str

RAISES	DESCRIPTION
HTTPStatusError	If the HTTP request to the model fails.

Source code in swarmauri_standard/llms/GeminiProModel.py

@retry_on_status_codes((429, 529), max_retries=1)
def stream(
    self,
    conversation: Conversation,
    temperature: float = 0.7,
    max_tokens: int = 256,
) -> Iterator[str]:
    """
    Streams the response from the model based on the given conversation.

    Args:
        conversation (Conversation): The conversation object containing the history of messages.
        temperature (float, optional): The temperature setting for the generation. Defaults to 0.7.
        max_tokens (int, optional): The maximum number of tokens to generate. Defaults to 256.

    Yields:
        str: Chunks of the generated response text.

    Raises:
        httpx.HTTPStatusError: If the HTTP request to the model fails.

    """
    generation_config = {
        "temperature": temperature,
        "top_p": 0.95,
        "top_k": 0,
        "max_output_tokens": max_tokens,
    }

    system_context = self._get_system_context(conversation.history)
    formatted_messages = self._format_messages(conversation.history)

    next_message = formatted_messages.pop()

    payload = {
        "contents": next_message,
        "generationConfig": generation_config,
        "safetySettings": self._safety_settings,
    }
    if system_context:
        payload["systemInstruction"] = system_context

    with DurationManager() as prompt_timer:
        response = self._client.post(
            f"/{self.name}:streamGenerateContent?alt=sse&key={self.api_key.get_secret_value()}",
            json=payload,
        )

        response.raise_for_status()

    full_response = ""
    with DurationManager() as completion_timer:
        for line in response.iter_lines():
            json_str = line.replace("data: ", "")
            if json_str:
                response_data = json.loads(json_str)
                chunk = response_data["candidates"][0]["content"]["parts"][0][
                    "text"
                ]
                full_response += chunk
                yield chunk

                if "usageMetadata" in response_data:
                    usage_data = response_data["usageMetadata"]

    if self.include_usage and usage_data:
        usage = self._prepare_usage_data(
            usage_data, prompt_timer.duration, completion_timer.duration
        )
        conversation.add_message(AgentMessage(content=full_response, usage=usage))
    else:
        conversation.add_message(AgentMessage(content=full_response))

astream async

astream(conversation, temperature=0.7, max_tokens=256)

Asynchronously streams generated content for a given conversation.

PARAMETER	DESCRIPTION
conversation	The conversation object containing the history of messages. TYPE: Conversation
temperature	The temperature for the generation process. Defaults to 0.7. TYPE: float DEFAULT: 0.7
max_tokens	The maximum number of tokens to generate. Defaults to 256. TYPE: int DEFAULT: 256

YIELDS	DESCRIPTION
str	Chunks of generated content as they are received. TYPE:: AsyncIterator[str]

RAISES	DESCRIPTION
HTTPStatusError	If the HTTP request to the generation service fails.

Source code in swarmauri_standard/llms/GeminiProModel.py

@retry_on_status_codes((429, 529), max_retries=1)
async def astream(
    self,
    conversation: Conversation,
    temperature: float = 0.7,
    max_tokens: int = 256,
) -> AsyncIterator[str]:
    """
    Asynchronously streams generated content for a given conversation.

    Args:
        conversation (Conversation): The conversation object containing the history of messages.
        temperature (float, optional): The temperature for the generation process. Defaults to 0.7.
        max_tokens (int, optional): The maximum number of tokens to generate. Defaults to 256.

    Yields:
        str: Chunks of generated content as they are received.

    Raises:
        httpx.HTTPStatusError: If the HTTP request to the generation service fails.

    """
    generation_config = {
        "temperature": temperature,
        "top_p": 0.95,
        "top_k": 0,
        "max_output_tokens": max_tokens,
    }

    system_context = self._get_system_context(conversation.history)
    formatted_messages = self._format_messages(conversation.history)

    next_message = formatted_messages.pop()

    payload = {
        "contents": next_message,
        "generationConfig": generation_config,
        "safetySettings": self._safety_settings,
    }
    if system_context:
        payload["systemInstruction"] = system_context

    with DurationManager() as prompt_timer:
        response = await self._async_client.post(
            f"/{self.name}:streamGenerateContent?alt=sse&key={self.api_key.get_secret_value()}",
            json=payload,
        )
        response.raise_for_status()

    full_response = ""
    with DurationManager() as completion_timer:
        async for line in response.aiter_lines():
            json_str = line.replace("data: ", "")
            if json_str:
                response_data = json.loads(json_str)
                chunk = response_data["candidates"][0]["content"]["parts"][0][
                    "text"
                ]
                full_response += chunk
                yield chunk

                if "usageMetadata" in response_data:
                    usage_data = response_data["usageMetadata"]

    if self.include_usage and usage_data:
        usage = self._prepare_usage_data(
            usage_data, prompt_timer.duration, completion_timer.duration
        )
        conversation.add_message(AgentMessage(content=full_response, usage=usage))
    else:
        conversation.add_message(AgentMessage(content=full_response))

batch

batch(conversations, temperature=0.7, max_tokens=256)

Synchronously process multiple conversations.

PARAMETER	DESCRIPTION
conversations	A list of Conversation objects to be processed. TYPE: List[Conversation]
temperature	The sampling temperature to use. Defaults to 0.7. TYPE: float DEFAULT: 0.7
max_tokens	The maximum number of tokens to generate. Defaults to 256. TYPE: int DEFAULT: 256

RETURNS	DESCRIPTION
List	A list of predictions for each conversation. TYPE: List

Source code in swarmauri_standard/llms/GeminiProModel.py

def batch(
    self,
    conversations: List[Conversation],
    temperature: float = 0.7,
    max_tokens: int = 256,
) -> List:
    """
    Synchronously process multiple conversations.

    Args:
        conversations (List[Conversation]): A list of Conversation objects to be processed.
        temperature (float, optional): The sampling temperature to use. Defaults to 0.7.
        max_tokens (int, optional): The maximum number of tokens to generate. Defaults to 256.

    Returns:
        List: A list of predictions for each conversation.
    """
    return [
        self.predict(
            conv,
            temperature=temperature,
            max_tokens=max_tokens,
        )
        for conv in conversations
    ]

abatch async

abatch(
    conversations,
    temperature=0.7,
    max_tokens=256,
    max_concurrent=5,
)

Asynchronously processes a batch of conversations using the apredict method.

PARAMETER	DESCRIPTION
conversations	A list of Conversation objects to be processed. TYPE: List[Conversation]
temperature	The temperature parameter for the prediction. Defaults to 0.7. TYPE: float DEFAULT: 0.7
max_tokens	The maximum number of tokens for the prediction. Defaults to 256. TYPE: int DEFAULT: 256
max_concurrent	The maximum number of concurrent tasks. Defaults to 5. TYPE: int DEFAULT: 5

RETURNS	DESCRIPTION
List	A list of results from the apredict method for each conversation. TYPE: List

Source code in swarmauri_standard/llms/GeminiProModel.py

async def abatch(
    self,
    conversations: List[Conversation],
    temperature: float = 0.7,
    max_tokens: int = 256,
    max_concurrent: int = 5,
) -> List:
    """
    Asynchronously processes a batch of conversations using the `apredict` method.

    Args:
        conversations (List[Conversation]): A list of Conversation objects to be processed.
        temperature (float, optional): The temperature parameter for the prediction. Defaults to 0.7.
        max_tokens (int, optional): The maximum number of tokens for the prediction. Defaults to 256.
        max_concurrent (int, optional): The maximum number of concurrent tasks. Defaults to 5.

    Returns:
        List: A list of results from the `apredict` method for each conversation.
    """
    semaphore = asyncio.Semaphore(max_concurrent)

    async def process_conversation(conv) -> Conversation:
        async with semaphore:
            return await self.apredict(
                conv,
                temperature=temperature,
                max_tokens=max_tokens,
            )

    tasks = [process_conversation(conv) for conv in conversations]
    return await asyncio.gather(*tasks)

get_allowed_models

get_allowed_models()

Queries the LLMProvider API endpoint to retrieve the list of allowed models.

RETURNS	DESCRIPTION
List[str]	List[str]: A list of allowed model names.

Source code in swarmauri_standard/llms/GeminiProModel.py

def get_allowed_models(self) -> List[str]:
    """
    Queries the LLMProvider API endpoint to retrieve the list of allowed models.

    Returns:
        List[str]: A list of allowed model names.
    """
    response = self._client.get(
        f"https://generativelanguage.googleapis.com/v1beta/models?key={self.api_key.get_secret_value()}"
    )
    response.raise_for_status()
    return [model["name"] for model in response.json()["models"]]

register_model classmethod

register_model()

Decorator to register a base model in the unified registry.

RETURNS	DESCRIPTION
Callable	A decorator function that registers the model class. TYPE: Callable[[Type[BaseModel]], Type[BaseModel]]

Source code in swarmauri_base/DynamicBase.py

@classmethod
def register_model(cls) -> Callable[[Type[BaseModel]], Type[BaseModel]]:
    """
    Decorator to register a base model in the unified registry.

    Returns:
        Callable: A decorator function that registers the model class.
    """

    def decorator(model_cls: Type[BaseModel]):
        """Register ``model_cls`` as a base model."""
        model_name = model_cls.__name__
        if model_name in cls._registry:
            glogger.warning(
                "Model '%s' is already registered; skipping duplicate.", model_name
            )
            return model_cls

        cls._registry[model_name] = {"model_cls": model_cls, "subtypes": {}}
        glogger.debug("Registered base model '%s'.", model_name)
        DynamicBase._recreate_models()
        return model_cls

    return decorator

register_type classmethod

register_type(resource_type=None, type_name=None)

Decorator to register a subtype under one or more base models in the unified registry.

PARAMETER	DESCRIPTION
resource_type	The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase) are used. TYPE: Optional[Union[Type[T], List[Type[T]]]] DEFAULT: None
type_name	An optional custom type name for the subtype. TYPE: Optional[str] DEFAULT: None

RETURNS	DESCRIPTION
Callable	A decorator function that registers the subtype. TYPE: Callable[[Type[DynamicBase]], Type[DynamicBase]]

Source code in swarmauri_base/DynamicBase.py

@classmethod
def register_type(
    cls,
    resource_type: Optional[Union[Type[T], List[Type[T]]]] = None,
    type_name: Optional[str] = None,
) -> Callable[[Type["DynamicBase"]], Type["DynamicBase"]]:
    """
    Decorator to register a subtype under one or more base models in the unified registry.

    Parameters:
        resource_type (Optional[Union[Type[T], List[Type[T]]]]):
            The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase)
            are used.
        type_name (Optional[str]): An optional custom type name for the subtype.

    Returns:
        Callable: A decorator function that registers the subtype.
    """

    def decorator(subclass: Type["DynamicBase"]):
        """Register ``subclass`` as a subtype."""
        if resource_type is None:
            resource_types = [
                base for base in subclass.__bases__ if base is not cls
            ]
        elif not isinstance(resource_type, list):
            resource_types = [resource_type]
        else:
            resource_types = resource_type

        for rt in resource_types:
            if not issubclass(subclass, rt):
                raise TypeError(
                    f"'{subclass.__name__}' must be a subclass of '{rt.__name__}'."
                )
            final_type_name = type_name or getattr(
                subclass, "_type", subclass.__name__
            )
            base_model_name = rt.__name__

            if base_model_name not in cls._registry:
                cls._registry[base_model_name] = {"model_cls": rt, "subtypes": {}}
                glogger.debug(
                    "Created new registry entry for base model '%s'.",
                    base_model_name,
                )

            subtypes_dict = cls._registry[base_model_name]["subtypes"]
            if final_type_name in subtypes_dict:
                glogger.warning(
                    "Type '%s' already exists under '%s'; skipping duplicate.",
                    final_type_name,
                    base_model_name,
                )
                continue

            subtypes_dict[final_type_name] = subclass
            glogger.debug(
                "Registered '%s' as '%s' under '%s'.",
                subclass.__name__,
                final_type_name,
                base_model_name,
            )

        DynamicBase._recreate_models()
        return subclass

    return decorator

model_validate_toml classmethod

model_validate_toml(toml_data)

Validate a model from a TOML string.

Source code in swarmauri_base/TomlMixin.py

@classmethod
def model_validate_toml(cls, toml_data: str):
    """Validate a model from a TOML string."""
    try:
        # Parse TOML into a Python dictionary
        toml_content = tomllib.loads(toml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(toml_content))
    except tomllib.TOMLDecodeError as e:
        raise ValueError(f"Invalid TOML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_toml

model_dump_toml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a TOML representation of the model.

Source code in swarmauri_base/TomlMixin.py

def model_dump_toml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a TOML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into TOML
    return toml.dumps(filtered_data)

model_validate_yaml classmethod

model_validate_yaml(yaml_data)

Validate a model from a YAML string.

Source code in swarmauri_base/YamlMixin.py

@classmethod
def model_validate_yaml(cls, yaml_data: str):
    """Validate a model from a YAML string."""
    try:
        # Parse YAML into a Python dictionary
        yaml_content = yaml.safe_load(yaml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(yaml_content))
    except yaml.YAMLError as e:
        raise ValueError(f"Invalid YAML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_yaml

model_dump_yaml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a YAML representation of the model.

Source code in swarmauri_base/YamlMixin.py

def model_dump_yaml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a YAML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into YAML using safe mode
    return yaml.safe_dump(filtered_data, default_flow_style=False)

model_post_init

model_post_init(logger=None)

Assign a logger instance after model initialization.

Source code in swarmauri_base/LoggerMixin.py

def model_post_init(self, logger: Optional[FullUnion[LoggerBase]] = None) -> None:
    """Assign a logger instance after model initialization."""

    # Directly assign the provided FullUnion[LoggerBase] or fallback to the
    # class-level default.
    self.logger = self.logger or logger or self.default_logger

add_allowed_model

add_allowed_model(model)

Add a new model to the list of allowed models.

RAISES	DESCRIPTION
ValueError	If the model is already in the allowed models list.

Source code in swarmauri_base/llms/LLMBase.py

def add_allowed_model(self, model: str) -> None:
    """
    Add a new model to the list of allowed models.

    Raises:
        ValueError: If the model is already in the allowed models list.
    """
    if model in self.allowed_models:
        raise ValueError(f"Model '{model}' is already allowed.")
    self.allowed_models.append(model)

remove_allowed_model

remove_allowed_model(model)

Remove a model from the list of allowed models.

RAISES	DESCRIPTION
ValueError	If the model is not in the allowed models list.

Source code in swarmauri_base/llms/LLMBase.py

def remove_allowed_model(self, model: str) -> None:
    """
    Remove a model from the list of allowed models.

    Raises:
        ValueError: If the model is not in the allowed models list.
    """
    if model not in self.allowed_models:
        raise ValueError(f"Model '{model}' is not in the allowed models list.")
    self.allowed_models.remove(model)