Rtvi

class pipecat.services.google.rtvi.RTVISearchResponseMessageData(*, search_result, rendered_content, origins)[source]

Bases: BaseModel

Parameters:

  • search_result (str | None)

  • rendered_content (str | None)

  • origins (List[LLMSearchOrigin])

search_result: str | None
rendered_content: str | None
origins: List[LLMSearchOrigin]
model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.google.rtvi.RTVIBotLLMSearchResponseMessage(*, label='rtvi-ai', type='bot-llm-search-response', data)[source]

Bases: BaseModel

Parameters:

  • label (Literal['rtvi-ai'])

  • type (Literal['bot-llm-search-response'])

  • data (RTVISearchResponseMessageData)

label: Literal['rtvi-ai']
type: Literal['bot-llm-search-response']
data: RTVISearchResponseMessageData
model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.google.rtvi.GoogleRTVIObserver(rtvi)[source]

Bases: RTVIObserver

Parameters:

rtvi (RTVIProcessor)

async on_push_frame(data)[source]

Process a frame being pushed through the pipeline.

Parameters:

  • src – Source processor pushing the frame

  • dst – Destination processor receiving the frame

  • frame – The frame being pushed

  • direction – Direction of frame flow in pipeline

  • timestamp – Time when frame was pushed

  • data (FramePushed)