langchain_core.messages.ai.AIMessage

class langchain_core.messages.ai.AIMessage[source]

Bases: BaseMessage

Message from an AI.

AIMessage is returned from a chat model as a response to a prompt.

This message represents the output of the model and consists of both the raw output as returned by the model together standardized fields (e.g., tool calls, usage metadata) added by the LangChain framework.

Pass in content as positional arg.

Parameters

  • content – The content of the message.

  • kwargs – Additional arguments to pass to the parent class.

param additional_kwargs: dict [Optional]

Reserved for additional payload data associated with the message.

For example, for a message from an AI, this could include tool calls as encoded by the model provider.

param content: Union[str, List[Union[str, Dict]]] [Required]

The string contents of the message.

param example: bool = False

Use to denote that a message is part of an example conversation.

At the moment, this is ignored by most models. Usage is discouraged.

param id: Optional[str] = None

An optional unique identifier for the message. This should ideally be provided by the provider/model which created the message.

param invalid_tool_calls: List[InvalidToolCall] = []

If provided, tool calls with parsing errors associated with the message.

param name: Optional[str] = None

An optional name for the message.

This can be used to provide a human-readable name for the message.

Usage of this field is optional, and whether it’s used or not is up to the model implementation.

param response_metadata: dict [Optional]

Response metadata. For example: response headers, logprobs, token counts.

param tool_calls: List[ToolCall] = []

If provided, tool calls associated with the message.

param type: Literal['ai'] = 'ai'

The type of the message (used for deserialization). Defaults to “ai”.

param usage_metadata: Optional[UsageMetadata] = None

If provided, usage metadata for a message, such as token counts.

This is a standard representation of token usage that is consistent across models.

pretty_print() → None
Return type

None

pretty_repr(html: bool = False) → str[source]

Return a pretty representation of the message.

Parameters

html (bool) – Whether to return an HTML-formatted string. Defaults to False.

Returns

A pretty representation of the message.

Return type

str

Examples using AIMessage