Files
pipecat/examples/foundational/26a-gemini-multimodal-live-transcription.py

130 lines
4.3 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import argparse
import os
from dotenv import load_dotenv
from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.audio.vad.vad_analyzer import VADParams
from pipecat.frames.frames import TranscriptionMessage
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.processors.transcript_processor import TranscriptProcessor
from pipecat.services.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
from pipecat.transports.base_transport import TransportParams
from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
load_dotenv(override=True)
async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespace):
logger.info(f"Starting bot")
# Initialize the SmallWebRTCTransport with the connection
transport = SmallWebRTCTransport(
webrtc_connection=webrtc_connection,
params=TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
# set stop_secs to something roughly similar to the internal setting
# of the Multimodal Live api, just to align events. This doesn't really
# matter because we can only use the Multimodal Live API's phrase
# endpointing, for now.
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
),
)
llm = GeminiMultimodalLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
voice_id="Aoede", # Puck, Charon, Kore, Fenrir, Aoede
# system_instruction="Talk like a pirate."
transcribe_user_audio=True,
# inference_on_context_initialization=False,
)
context = OpenAILLMContext(
[
{
"role": "user",
"content": "Say hello. Then ask if I want to hear a joke.",
},
# {"role": "assistant", "content": "Hello! Why don't scientists trust atoms?"},
# {
# "role": "user",
# "content": [
# {
# "type": "text",
# "text": "Oh, I know this one: because they make up everything.",
# }
# ],
# },
],
)
context_aggregator = llm.create_context_aggregator(context)
transcript = TranscriptProcessor()
pipeline = Pipeline(
[
transport.input(),
context_aggregator.user(),
transcript.user(),
llm,
transport.output(),
transcript.assistant(),
context_aggregator.assistant(),
]
)
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):
logger.info(f"Client connected")
# Kick off the conversation.
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
@transport.event_handler("on_client_closed")
async def on_client_closed(transport, client):
logger.info(f"Client closed connection")
await task.cancel()
# Register event handler for transcript updates
@transcript.event_handler("on_transcript_update")
async def on_transcript_update(processor, frame):
for msg in frame.messages:
if isinstance(msg, TranscriptionMessage):
timestamp = f"[{msg.timestamp}] " if msg.timestamp else ""
line = f"{timestamp}{msg.role}: {msg.content}"
logger.info(f"Transcript: {line}")
runner = PipelineRunner(handle_sigint=False)
await runner.run(task)
if __name__ == "__main__":
from run import main
main()