Reference documentation and code samples for the Google Cloud Ai Platform V1 Client class EventMetadata.
Metadata relating to a LLM response event.
Generated from protobuf message google.cloud.aiplatform.v1.EventMetadata
Namespace
Google \ Cloud \ AIPlatform \ V1Methods
__construct
Constructor.
data
array
Optional. Data for populating the Message object.
↳ grounding_metadata
↳ partial
bool
Optional. Indicates whether the text content is part of a unfinished text stream. Only used for streaming mode and when the content is plain text.
↳ turn_complete
bool
Optional. Indicates whether the response from the model is complete. Only used for streaming mode.
↳ interrupted
bool
Optional. Flag indicating that LLM was interrupted when generating the content. Usually it's due to user interruption during a bidi streaming.
↳ long_running_tool_ids
string[]
Optional. Set of ids of the long running function calls. Agent client will know from this field about which function call is long running. Only valid for function call event.
↳ branch
string
Optional. The branch of the event. The format is like agent_1.agent_2.agent_3, where agent_1 is the parent of agent_2, and agent_2 is the parent of agent_3. Branch is used when multiple child agents shouldn't see their siblings' conversation history.
↳ custom_metadata
↳ input_transcription
↳ output_transcription
getGroundingMetadata
Optional. Metadata returned to client when grounding is enabled.
hasGroundingMetadata
clearGroundingMetadata
setGroundingMetadata
Optional. Metadata returned to client when grounding is enabled.
$this
getPartial
Optional. Indicates whether the text content is part of a unfinished text stream. Only used for streaming mode and when the content is plain text.
bool
setPartial
Optional. Indicates whether the text content is part of a unfinished text stream. Only used for streaming mode and when the content is plain text.
var
bool
$this
getTurnComplete
Optional. Indicates whether the response from the model is complete.
Only used for streaming mode.
bool
setTurnComplete
Optional. Indicates whether the response from the model is complete.
Only used for streaming mode.
var
bool
$this
getInterrupted
Optional. Flag indicating that LLM was interrupted when generating the content. Usually it's due to user interruption during a bidi streaming.
bool
setInterrupted
Optional. Flag indicating that LLM was interrupted when generating the content. Usually it's due to user interruption during a bidi streaming.
var
bool
$this
getLongRunningToolIds
Optional. Set of ids of the long running function calls.
Agent client will know from this field about which function call is long running. Only valid for function call event.
setLongRunningToolIds
Optional. Set of ids of the long running function calls.
Agent client will know from this field about which function call is long running. Only valid for function call event.
var
string[]
$this
getBranch
Optional. The branch of the event.
The format is like agent_1.agent_2.agent_3, where agent_1 is the parent of agent_2, and agent_2 is the parent of agent_3. Branch is used when multiple child agents shouldn't see their siblings' conversation history.
string
setBranch
Optional. The branch of the event.
The format is like agent_1.agent_2.agent_3, where agent_1 is the parent of agent_2, and agent_2 is the parent of agent_3. Branch is used when multiple child agents shouldn't see their siblings' conversation history.
var
string
$this
getCustomMetadata
The custom metadata of the LlmResponse.
hasCustomMetadata
clearCustomMetadata
setCustomMetadata
The custom metadata of the LlmResponse.
$this
getInputTranscription
Optional. Audio transcription of user input.
hasInputTranscription
clearInputTranscription
setInputTranscription
Optional. Audio transcription of user input.
$this
getOutputTranscription
Optional. Audio transcription of model output.
hasOutputTranscription
clearOutputTranscription
setOutputTranscription
Optional. Audio transcription of model output.
$this
