langchain.ChatCohereDataset

kedro_datasets.langchain.ChatCohereDataset

ChatCohereDataset(credentials={}, kwargs={})

Bases: AbstractDataset[None, ChatCohere]

ChatCohereDataset loads a ChatCohere langchain model.

Example usage for the YAML API

catalog.yml

command:
    type: langchain.ChatCohereDataset
    kwargs:
        model: "command"
        temperature: 0.0
    credentials: cohere  # Optional, can use environment variables instead

credentials.yml (optional if using environment variables) If credentials are passed through credentials.yml, they take precedence over environment variables.

cohere:
    base_url: <cohere-api-base>  # Optional, defaults to Cohere default
    api_key: <cohere-api-key>   # Optional if COHERE_API_KEY is set

Or use environment variables:

export COHERE_API_KEY=<your-api-key>
export CO_API_URL=<cohere-api-base>  # Optional

Example usage for the Python API

from kedro_datasets.langchain import ChatCohereDataset

# With explicit credentials
llm = ChatCohereDataset(
    credentials={
        "api_key": "xxx",  # pragma: allowlist secret
        "base_url": "xxx",
    },
    kwargs={
        "model": "command",
        "temperature": 0.0,
    },
).load()

# Or without credentials (using environment variables)
llm = ChatCohereDataset(
    kwargs={
        "model": "command",
        "temperature": 0.0,
    },
).load()

# See: https://python.langchain.com/docs/integrations/chat/cohere
llm.invoke("Hello world!")

Parameters:

• credentials (Optional, default: {} ) –

  contains api_key and base_url. If not provided, will use environment variables COHERE_API_KEY and CO_API_URL.

• kwargs (dict[str, Any], default: {} ) –

  keyword arguments passed to the ChatCohere constructor.

Source code in kedro_datasets/langchain/chat_cohere_dataset.py

def __init__(self, credentials: dict[str, str] = {}, kwargs: dict[str, Any] = {}):
    """Constructor.

    Args:
        credentials (Optional): contains `api_key` and `base_url`.
            If not provided, will use environment variables COHERE_API_KEY and CO_API_URL.
        kwargs: keyword arguments passed to the ChatCohere constructor.
    """
    self.credentials = credentials or {}
    self.kwargs = kwargs or {}

credentials instance-attribute

credentials = credentials or {}

kwargs instance-attribute

kwargs = kwargs or {}

_describe

_describe()

Returns a description of the dataset.

Returns:

• dict[str, Any] –

  Dictionary containing the kwargs passed to ChatCohere.

Source code in kedro_datasets/langchain/chat_cohere_dataset.py

def _describe(self) -> dict[str, Any]:
    """Returns a description of the dataset.

    Returns:
        dict[str, Any]: Dictionary containing the kwargs passed to ChatCohere.
    """
    credentials = (
        {k: "***" for k in self.credentials.keys()} if self.credentials else {}
    )
    return {**credentials, **self.kwargs}

load

load()

Load and return a ChatCohere model instance.

Constructs a ChatCohere instance using the provided kwargs and optional credentials. If credentials are not provided, the ChatCohere instance will automatically use environment variables COHERE_API_KEY and CO_API_URL for authentication.

Returns:

• ChatCohere –

  A configured ChatCohere model instance.

Source code in kedro_datasets/langchain/chat_cohere_dataset.py

def load(self) -> ChatCohere:
    """Load and return a ChatCohere model instance.

    Constructs a ChatCohere instance using the provided kwargs and optional
    credentials. If credentials are not provided, the ChatCohere instance
    will automatically use environment variables COHERE_API_KEY and
    CO_API_URL for authentication.

    Returns:
        ChatCohere: A configured ChatCohere model instance.
    """
    return ChatCohere(**self.credentials, **self.kwargs)  # type: ignore[arg-type]

save

save(data)

Save operation is not supported for ChatCohereDataset.

Raises:

• DatasetError –

  Always raised as this dataset is read-only.

Source code in kedro_datasets/langchain/chat_cohere_dataset.py

def save(self, data: None) -> NoReturn:
    """Save operation is not supported for ChatCohereDataset.

    Raises:
        DatasetError: Always raised as this dataset is read-only.
    """
    raise DatasetError(f"{self.__class__.__name__} is a read only dataset type")