Class ChatSession (1.55.0)

ChatSession(
    model: vertexai.language_models.ChatModel,
    context: typing.Optional[str] = None,
    examples: typing.Optional[
        typing.List[vertexai.language_models.InputOutputTextPair]
    ] = None,
    max_output_tokens: typing.Optional[int] = None,
    temperature: typing.Optional[float] = None,
    top_k: typing.Optional[int] = None,
    top_p: typing.Optional[float] = None,
    message_history: typing.Optional[
        typing.List[vertexai.language_models.ChatMessage]
    ] = None,
    stop_sequences: typing.Optional[typing.List[str]] = None,
)

ChatSession represents a chat session with a language model.

Within a chat session, the model keeps context and remembers the previous conversation.

Properties

message_history

List of previous messages.

Methods

send_message

send_message(
    message: str,
    *,
    max_output_tokens: typing.Optional[int] = None,
    temperature: typing.Optional[float] = None,
    top_k: typing.Optional[int] = None,
    top_p: typing.Optional[float] = None,
    stop_sequences: typing.Optional[typing.List[str]] = None,
    candidate_count: typing.Optional[int] = None,
    grounding_source: typing.Optional[
        typing.Union[
            vertexai.language_models._language_models.WebSearch,
            vertexai.language_models._language_models.VertexAISearch,
            vertexai.language_models._language_models.InlineContext,
        ]
    ] = None
) -> vertexai.language_models.MultiCandidateTextGenerationResponse

Sends message to the language model and gets a response.

Parameter
Name	Description
`message`	`str` Message to send to the model

send_message_async

send_message_async(
    message: str,
    *,
    max_output_tokens: typing.Optional[int] = None,
    temperature: typing.Optional[float] = None,
    top_k: typing.Optional[int] = None,
    top_p: typing.Optional[float] = None,
    stop_sequences: typing.Optional[typing.List[str]] = None,
    candidate_count: typing.Optional[int] = None,
    grounding_source: typing.Optional[
        typing.Union[
            vertexai.language_models._language_models.WebSearch,
            vertexai.language_models._language_models.VertexAISearch,
            vertexai.language_models._language_models.InlineContext,
        ]
    ] = None
) -> vertexai.language_models.MultiCandidateTextGenerationResponse

Asynchronously sends message to the language model and gets a response.

Parameter
Name	Description
`message`	`str` Message to send to the model

send_message_streaming

send_message_streaming(
    message: str,
    *,
    max_output_tokens: typing.Optional[int] = None,
    temperature: typing.Optional[float] = None,
    top_k: typing.Optional[int] = None,
    top_p: typing.Optional[float] = None,
    stop_sequences: typing.Optional[typing.List[str]] = None
) -> typing.Iterator[vertexai.language_models.TextGenerationResponse]

Sends message to the language model and gets a streamed response.

The response is only added to the history once it's fully read.

Parameter
Name	Description
`message`	`str` Message to send to the model

send_message_streaming_async

send_message_streaming_async(
    message: str,
    *,
    max_output_tokens: typing.Optional[int] = None,
    temperature: typing.Optional[float] = None,
    top_k: typing.Optional[int] = None,
    top_p: typing.Optional[float] = None,
    stop_sequences: typing.Optional[typing.List[str]] = None
) -> typing.AsyncIterator[vertexai.language_models.TextGenerationResponse]

Asynchronously sends message to the language model and gets a streamed response.

The response is only added to the history once it's fully read.

Parameter
Name	Description
`message`	`str` Message to send to the model