Merge branch 'main' of github.com:pipecat-ai/pipecat

This commit is contained in:
Matej Marinko
2025-07-08 08:20:10 +02:00
482 changed files with 32975 additions and 7233 deletions

View File

@@ -47,7 +47,10 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
Pipeline([imagegen, transport.output()]),
params=PipelineParams(enable_metrics=True),
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
# Register an event handler so we can play the audio when the client joins

View File

@@ -93,10 +93,8 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -75,10 +75,8 @@ async def main():
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -158,7 +158,8 @@ async def main():
],
),
params=PipelineParams(
allow_interruptions=True, enable_metrics=True, enable_usage_metrics=True
enable_metrics=True,
enable_usage_metrics=True,
),
)

View File

@@ -133,10 +133,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -84,10 +84,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -83,10 +83,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -0,0 +1,153 @@
#
# 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.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.llm_response import (
LLMUserAggregatorParams,
)
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
from pipecat.services.openai.base_llm import BaseOpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
from pipecat.transports.services.daily import DailyParams
load_dotenv(override=True)
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
# instantiated. The function will be called when the desired transport gets
# selected.
transport_params = {
"daily": lambda: DailyParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
}
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
"""Run example using Speechmatics STT.
This example will use diarization within our STT service and output the words spoken by
each individual speaker and wrap them with XML tags for the LLM to process. Note the
instructions in the system context for the LLM. This greatly improves the conversation
experience by allowing the LLM to understand who is speaking in a multi-party call.
If you do not wish to use diarization, then set the `enable_speaker_diarization` parameter
to `False` or omit it altogether. The `text_format` will only be used if diarization is enabled.
By default, this example will use our ENHANCED operating point, which is optimized for
high accuracy. You can change this by setting the `operating_point` parameter to a different
value.
For more information on operating points, see the Speechmatics documentation:
https://docs.speechmatics.com/rt-api-ref
"""
logger.info(f"Starting bot")
stt = SpeechmaticsSTTService(
api_key=os.getenv("SPEECHMATICS_API_KEY"),
language=Language.EN,
enable_speaker_diarization=True,
text_format="<{speaker_id}>{text}</{speaker_id}>",
)
tts = ElevenLabsTTSService(
api_key=os.getenv("ELEVENLABS_API_KEY", ""),
voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
model="eleven_turbo_v2_5",
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
params=BaseOpenAILLMService.InputParams(temperature=0.75),
)
messages = [
{
"role": "system",
"content": (
"You are a helpful British assistant called Alfred. "
"Your goal is to demonstrate your capabilities in a succinct way. "
"Your output will be converted to audio so don't include special characters in your answers. "
"Always include punctuation in your responses. "
"Give very short replies - do not give longer replies unless strictly necessary. "
"Respond to what the user said in a concise, funny, creative and helpful way. "
"Use `<Sn/>` tags to identify different speakers - do not use tags in your replies."
),
},
]
context = OpenAILLMContext(messages)
context_aggregator = llm.create_context_aggregator(
context,
user_params=LLMUserAggregatorParams(aggregation_timeout=0.005),
)
pipeline = Pipeline(
[
transport.input(), # Transport user input
stt, # STT
context_aggregator.user(), # User responses
llm, # LLM
tts, # TTS
transport.output(), # Transport bot output
context_aggregator.assistant(), # Assistant spoken responses
]
)
task = PipelineTask(
pipeline,
params=PipelineParams(
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.
messages.append({"role": "system", "content": "Say a short hello to the user."})
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")
await task.cancel()
runner = PipelineRunner(handle_sigint=handle_sigint)
await runner.run(task)
if __name__ == "__main__":
from pipecat.examples.run import main
main(run_example, transport_params=transport_params)

View File

@@ -113,10 +113,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -87,10 +87,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -81,10 +81,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -35,7 +35,7 @@ transport_params = {
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
"twilio": lambda: TransportParams(
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
@@ -88,10 +88,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -84,10 +84,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -84,10 +84,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -86,10 +86,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -90,10 +90,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -84,11 +84,9 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
audio_out_sample_rate=24000,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -89,10 +89,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -87,10 +87,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -92,10 +92,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -80,10 +80,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -85,7 +85,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

View File

@@ -87,10 +87,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -61,7 +61,12 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
)
llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
model="gemini-2.5-flash",
# turn on thinking if you want it
# params=GoogleLLMService.InputParams(extra={"thinking_config": {"thinking_budget": 4096}}),)
)
messages = [
{
@@ -88,10 +93,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -86,10 +86,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -84,10 +84,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -89,10 +89,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -83,10 +83,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -80,10 +80,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -8,8 +8,8 @@ import argparse
import os
from dataclasses import dataclass
import google.ai.generativelanguage as glm
from dotenv import load_dotenv
from google.genai.types import Content, Part
from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer
@@ -164,9 +164,7 @@ class TanscriptionContextFixup(FrameProcessor):
and last_part.inline_data
and last_part.inline_data.mime_type == "audio/wav"
):
self._context.messages[-2] = glm.Content(
role="user", parts=[glm.Part(text=self._transcript)]
)
self._context.messages[-2] = Content(role="user", parts=[Part(text=self._transcript)])
def add_transcript_back_to_inference_output(self):
if not self._transcript:
@@ -216,7 +214,12 @@ transport_params = {
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
logger.info(f"Starting bot")
llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash-001")
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
model="gemini-2.5-flash",
# turn on thinking if you want it
# params=GoogleLLMService.InputParams(extra={"thinking_config": {"thinking_budget": 4096}}),
)
tts = GoogleTTSService(
voice_id="en-US-Chirp3-HD-Charon",
@@ -258,7 +261,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

View File

@@ -84,10 +84,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -77,8 +77,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),
)

View File

@@ -84,10 +84,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -83,10 +83,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -86,10 +86,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -70,10 +70,8 @@ async def main():
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -90,10 +90,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -89,10 +89,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -85,7 +85,13 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
]
)
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):

View File

@@ -101,7 +101,10 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(allow_interruptions=True),
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")

View File

@@ -101,7 +101,10 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(allow_interruptions=True),
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")

View File

@@ -101,7 +101,10 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(allow_interruptions=True),
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")

View File

@@ -84,7 +84,7 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
pipeline,
params=PipelineParams(
enable_metrics=True,
report_only_initial_ttfb=False,
enable_usage_metrics=True,
),
)

View File

@@ -0,0 +1,108 @@
#
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import argparse
import os
import time
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 Frame, TranscriptionFrame, UserStoppedSpeakingFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.services.sambanova.stt import SambaNovaSTTService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
from pipecat.transports.services.daily import DailyParams
load_dotenv(override=True)
STOP_SECS = 2.0
class TranscriptionLogger(FrameProcessor):
"""Measures transcription latency.
Uses the (intentionally) long STOP_SECS parameter to give the transcription time to finish,
then outputs the timing between when the VAD first classified audio input as not-speech and
the delivery of the last transcription frame.
"""
def __init__(self):
super().__init__()
self._last_transcription_time = time.time()
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
if isinstance(frame, UserStoppedSpeakingFrame):
logger.debug(
f"Transcription latency: {(STOP_SECS - (time.time() - self._last_transcription_time)):.2f}"
)
if isinstance(frame, TranscriptionFrame):
self._last_transcription_time = time.time()
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
# instantiated. The function will be called when the desired transport gets
# selected.
transport_params = {
"daily": lambda: DailyParams(
audio_in_enabled=True,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
),
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
),
}
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
logger.info(f"Starting bot")
stt = SambaNovaSTTService(
model="Whisper-Large-v3",
api_key=os.getenv("SAMBANOVA_API_KEY"),
)
tl = TranscriptionLogger()
pipeline = Pipeline([transport.input(), stt, tl])
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
await task.cancel()
runner = PipelineRunner(handle_sigint=handle_sigint)
await runner.run(task)
if __name__ == "__main__":
from pipecat.examples.run import main
main(run_example, transport_params=transport_params)

View File

@@ -0,0 +1,89 @@
#
# 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.frames.frames import Frame, TranscriptionFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
from pipecat.transports.services.daily import DailyParams
load_dotenv(override=True)
class TranscriptionLogger(FrameProcessor):
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
if isinstance(frame, TranscriptionFrame):
print(f"Transcription: {frame.text}")
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
# instantiated. The function will be called when the desired transport gets
# selected.
transport_params = {
"daily": lambda: DailyParams(audio_in_enabled=True),
"twilio": lambda: FastAPIWebsocketParams(audio_in_enabled=True),
"webrtc": lambda: TransportParams(audio_in_enabled=True),
}
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
"""Run example using Speechmatics STT.
This example will use diarization within our STT service and output the words spoken by
each individual speaker and wrap them with XML tags.
If you do not wish to use diarization, then set the `enable_speaker_diarization` parameter
to `False` or omit it altogether. The `text_format` will only be used if diarization is enabled.
By default, this example will use our ENHANCED operating point, which is optimized for
high accuracy. You can change this by setting the `operating_point` parameter to a different
value.
For more information on operating points, see the Speechmatics documentation:
https://docs.speechmatics.com/rt-api-ref
"""
logger.info(f"Starting bot")
stt = SpeechmaticsSTTService(
api_key=os.getenv("SPEECHMATICS_API_KEY"),
language=Language.EN,
enable_speaker_diarization=True,
text_format="<{speaker_id}>{text}</{speaker_id}>",
)
tl = TranscriptionLogger()
pipeline = Pipeline([transport.input(), stt, tl])
task = PipelineTask(pipeline)
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
await task.cancel()
runner = PipelineRunner(handle_sigint=handle_sigint)
await runner.run(task)
if __name__ == "__main__":
from pipecat.examples.run import main
main(run_example, transport_params=transport_params)

View File

@@ -134,10 +134,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -127,8 +127,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),
)

View File

@@ -172,8 +172,8 @@ If you need to use a tool, simply use the tool. Do not tell the user the tool yo
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),
)

View File

@@ -16,7 +16,7 @@ from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import TTSSpeakFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -116,7 +116,13 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
]
)
task = PipelineTask(pipeline)
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):

View File

@@ -17,7 +17,7 @@ from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.examples.run import get_transport_client_id, maybe_capture_participant_camera
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -158,7 +158,13 @@ indicate you should use the get_image tool are:
]
)
task = PipelineTask(pipeline)
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):

View File

@@ -183,7 +183,6 @@ indicate you should use the get_image tool are:
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

View File

@@ -121,7 +121,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

View File

@@ -111,7 +111,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

View File

@@ -120,7 +120,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

View File

@@ -119,7 +119,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

View File

@@ -42,7 +42,7 @@ transport_params = {
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
"twilio": lambda: TransportParams(
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
@@ -117,7 +117,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

View File

@@ -126,10 +126,8 @@ Start by asking me for my location. Then, use 'get_weather_current' to give me a
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -126,10 +126,8 @@ Start by asking me for my location. Then, use 'get_weather_current' to give me a
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -120,10 +120,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -90,10 +90,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -116,7 +116,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

View File

@@ -122,7 +122,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

View File

@@ -118,10 +118,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -134,10 +134,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -0,0 +1,152 @@
#
# 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.adapters.schemas.function_schema import FunctionSchema
from pipecat.adapters.schemas.tools_schema import ToolsSchema
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import TTSSpeakFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.llm_response import LLMUserAggregatorParams
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.sambanova.llm import SambaNovaLLMService
from pipecat.services.sambanova.stt import SambaNovaSTTService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
from pipecat.transports.services.daily import DailyParams
load_dotenv(override=True)
async def fetch_weather_from_api(params: FunctionCallParams):
await params.result_callback({"conditions": "nice", "temperature": "75"})
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
# instantiated. The function will be called when the desired transport gets
# selected.
transport_params = {
"daily": lambda: DailyParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
}
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
logger.info(f"Starting bot")
stt = SambaNovaSTTService(
model="Whisper-Large-v3",
api_key=os.getenv("SAMBANOVA_API_KEY"),
)
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
)
llm = SambaNovaLLMService(
api_key=os.getenv("SAMBANOVA_API_KEY"),
model="Llama-4-Maverick-17B-128E-Instruct",
)
# You can also register a function_name of None to get all functions
# sent to the same callback with an additional function_name parameter.
llm.register_function("get_current_weather", fetch_weather_from_api)
@llm.event_handler("on_function_calls_started")
async def on_function_calls_started(service, function_calls):
await tts.queue_frame(TTSSpeakFrame("Let me check on that."))
weather_function = FunctionSchema(
name="get_current_weather",
description="Get the current weather",
properties={
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"format": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "The temperature unit to use. Infer this from the user's location.",
},
},
required=["location"],
)
tools = ToolsSchema(standard_tools=[weather_function])
messages = [
{
"role": "system",
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
},
]
context = OpenAILLMContext(messages, tools)
context_aggregator = llm.create_context_aggregator(
context, user_params=LLMUserAggregatorParams(aggregation_timeout=0.05)
)
pipeline = Pipeline(
[
transport.input(),
stt,
context_aggregator.user(),
llm,
tts,
transport.output(),
context_aggregator.assistant(),
]
)
task = PipelineTask(
pipeline,
params=PipelineParams(
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")
await task.cancel()
runner = PipelineRunner(handle_sigint=handle_sigint)
await runner.run(task)
if __name__ == "__main__":
from pipecat.examples.run import main
main(run_example, transport_params=transport_params)

View File

@@ -0,0 +1,146 @@
#
# Copyright (c) 2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import argparse
import os
from dotenv import load_dotenv
from loguru import logger
from pipecat.adapters.schemas.tools_schema import ToolsSchema
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import TTSSpeakFrame
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.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
from pipecat.transports.services.daily import DailyParams
load_dotenv(override=True)
async def get_current_weather(params: FunctionCallParams, location: str, format: str):
"""
Get the current weather.
Args:
location (str): The city and state, e.g. "San Francisco, CA".
format (str): The temperature unit to use. Must be either "celsius" or "fahrenheit". Infer this from the user's location.
"""
await params.result_callback({"conditions": "nice", "temperature": "75"})
async def get_restaurant_recommendation(params: FunctionCallParams, location: str):
"""
Get a restaurant recommendation.
Args:
location (str): The city and state, e.g. "San Francisco, CA".
"""
await params.result_callback({"name": "The Golden Dragon"})
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
# instantiated. The function will be called when the desired transport gets
# selected.
transport_params = {
"daily": lambda: DailyParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
}
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
logger.info(f"Starting bot")
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
)
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
# You can also register a function_name of None to get all functions
# sent to the same callback with an additional function_name parameter.
llm.register_direct_function(get_current_weather)
llm.register_direct_function(get_restaurant_recommendation)
@llm.event_handler("on_function_calls_started")
async def on_function_calls_started(service, function_calls):
await tts.queue_frame(TTSSpeakFrame("Let me check on that."))
tools = ToolsSchema(standard_tools=[get_current_weather, get_restaurant_recommendation])
messages = [
{
"role": "system",
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
},
]
context = OpenAILLMContext(messages, tools)
context_aggregator = llm.create_context_aggregator(context)
pipeline = Pipeline(
[
transport.input(),
stt,
context_aggregator.user(),
llm,
tts,
transport.output(),
context_aggregator.assistant(),
]
)
task = PipelineTask(
pipeline,
params=PipelineParams(
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")
await task.cancel()
runner = PipelineRunner(handle_sigint=handle_sigint)
await runner.run(task)
if __name__ == "__main__":
from pipecat.examples.run import main
main(run_example, transport_params=transport_params)

View File

@@ -147,7 +147,13 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
]
)
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):

View File

@@ -135,7 +135,13 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
]
)
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):

View File

@@ -33,7 +33,7 @@ transport_params = {
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
"twilio": lambda: TransportParams(
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
@@ -90,8 +90,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),
)

View File

@@ -117,9 +117,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
report_only_initial_ttfb=True,
enable_usage_metrics=True,
),
)

View File

@@ -186,10 +186,8 @@ Remember, your responses should be short. Just one or two sentences, usually."""
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -179,10 +179,8 @@ Remember, your responses should be short. Just one or two sentences, usually."""
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -223,10 +223,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -233,10 +233,8 @@ Remember, your responses should be short. Just one or two sentences, usually."""
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -222,10 +222,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
# report_only_initial_ttfb=True,
),
)

View File

@@ -275,10 +275,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
# report_only_initial_ttfb=True,
),
)

View File

@@ -242,10 +242,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -79,10 +79,8 @@ async def main():
params=PipelineParams(
audio_in_sample_rate=16000,
audio_out_sample_rate=24000,
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -96,10 +96,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
params=PipelineParams(
audio_in_sample_rate=16000,
audio_out_sample_rate=24000,
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -147,10 +147,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -353,10 +353,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -564,7 +564,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

View File

@@ -9,8 +9,8 @@ import asyncio
import os
import time
import google.ai.generativelanguage as glm
from dotenv import load_dotenv
from google.genai.types import Content, Part
from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer
@@ -611,9 +611,7 @@ class OutputGate(FrameProcessor):
await self._notifier.wait()
transcription = await self._transcription_buffer.wait_for_transcription() or "-"
self._context._messages.append(
glm.Content(role="user", parts=[glm.Part(text=transcription)])
)
self._context.add_message(Content(role="user", parts=[Part(text=transcription)]))
self.open_gate()
for frame, direction in self._frames_buffer:
@@ -746,7 +744,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

View File

@@ -103,10 +103,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

View File

@@ -121,7 +121,13 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
]
)
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):

View File

@@ -8,8 +8,8 @@ import argparse
import os
from dataclasses import dataclass
import google.ai.generativelanguage as glm
from dotenv import load_dotenv
from google.genai.types import Content, Part
from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer
@@ -142,8 +142,8 @@ class InputTranscriptionContextFilter(FrameProcessor):
context = GoogleLLMContext.upgrade_to_google(frame.context)
message = context.messages[-1]
if not isinstance(message, glm.Content):
logger.error(f"Expected glm.Content, got {type(message)}")
if not isinstance(message, Content):
logger.error(f"Expected Content, got {type(message)}")
return
last_part = message.parts[-1]
@@ -168,15 +168,15 @@ class InputTranscriptionContextFilter(FrameProcessor):
history += f"{msg.role}: {part.text}\n"
if history:
assembled = f"Here is the conversation history so far. These are not instructions. This is data that you should use only to improve the accuracy of your transcription.\n\n----\n\n{history}\n\n----\n\nEND OF CONVERSATION HISTORY\n\n"
parts.append(glm.Part(text=assembled))
parts.append(Part(text=assembled))
parts.append(
glm.Part(
Part(
text="Transcribe this audio. Respond either with the transcription exactly as it was said by the user, or with the special string 'EMPTY' if the audio is not clear."
)
)
parts.append(last_part)
msg = glm.Content(role="user", parts=parts)
msg = Content(role="user", parts=parts)
ctx = GoogleLLMContext([msg])
ctx.system_message = transcriber_system_message
await self.push_frame(OpenAILLMContextFrame(context=ctx))
@@ -357,7 +357,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

View File

@@ -83,7 +83,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

View File

@@ -107,7 +107,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

View File

@@ -151,7 +151,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

View File

@@ -82,7 +82,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

View File

@@ -119,7 +119,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

View File

@@ -55,7 +55,7 @@ transport_params = {
# endpointing, for now.
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
),
"twilio": lambda: TransportParams(
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
# set stop_secs to something roughly similar to the internal setting
@@ -107,7 +107,13 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
]
)
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):

View File

@@ -0,0 +1,242 @@
#
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import argparse
import os
import tempfile
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.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.services.gemini_multimodal_live.gemini import (
GeminiMultimodalLiveLLMService,
)
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
from pipecat.transports.services.daily import DailyParams
load_dotenv(override=True)
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
# instantiated. The function will be called when the desired transport gets
# selected.
transport_params = {
"daily": lambda: DailyParams(
audio_in_enabled=True,
audio_out_enabled=True,
video_in_enabled=False,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
),
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
video_in_enabled=False,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
video_in_enabled=False,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
),
}
sample_file_path = ""
async def create_sample_file():
if sample_file_path:
return sample_file_path
else:
"""Create a sample text file for testing the File API."""
content = """# Sample Document for Gemini File API Test
This is a test document to demonstrate the Gemini File API functionality.
## Key Information:
- This document was created for testing purposes
- It contains information about AI assistants
- The document should be analyzed by Gemini
- The secret phrase for the test is "Pineapple Pizza"
## AI Assistant Capabilities:
1. Natural language processing
2. File analysis and understanding
3. Context-aware conversations
4. Multi-modal interactions
## Conclusion:
This document serves as a test case for the Gemini File API integration with Pipecat.
The AI should be able to reference and discuss the contents of this file.
"""
# Create a temporary file
with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as f:
f.write(content)
return f.name
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
logger.info(f"Starting File API bot")
# Create a sample file to upload
sample_file_path = await create_sample_file()
logger.info(f"Created sample file: {sample_file_path}")
system_instruction = """
You are a helpful AI assistant with access to a document that has been uploaded for analysis.
The document contains test information.
You should be able to:
- Reference and discuss the contents of the uploaded document
- Answer questions about what's in the document
- Use the information from the document in our conversation
Your output will be converted to audio so don't include special characters in your answers.
Be friendly and demonstrate your ability to work with the uploaded file.
"""
# Initialize Gemini service with File API support
llm = GeminiMultimodalLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
system_instruction=system_instruction,
voice_id="Charon", # Aoede, Charon, Fenrir, Kore, Puck
transcribe_user_audio=True,
)
# Upload the sample file to Gemini File API
logger.info("Uploading file to Gemini File API...")
file_info = None
try:
file_info = await llm.file_api.upload_file(
sample_file_path, display_name="Sample Test Document"
)
logger.info(f"File uploaded successfully: {file_info['file']['name']}")
# Get file URI and mime type
file_uri = file_info["file"]["uri"]
mime_type = "text/plain"
# Create context with file reference
context = OpenAILLMContext(
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "Greet the user and let them know you have access to a document they can ask you about. Mention that you can discuss its contents.",
},
{
"type": "file_data",
"file_data": {"mime_type": mime_type, "file_uri": file_uri},
},
],
}
]
)
logger.info("File reference added to conversation context")
except Exception as e:
logger.error(f"Error uploading file: {e}")
# Continue with a basic context if file upload fails
context = OpenAILLMContext(
[
{
"role": "user",
"content": "Greet the user and explain that there was an issue with file upload, but you're ready to help with other tasks.",
}
]
)
# Create context aggregator
context_aggregator = llm.create_context_aggregator(context)
# Build the pipeline
pipeline = Pipeline(
[
transport.input(),
context_aggregator.user(),
llm,
transport.output(),
context_aggregator.assistant(),
]
)
# Configure the pipeline task
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),
)
# Handle client connection event
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):
logger.info(f"Client connected")
# Kick off the conversation using standard context frame
await task.queue_frames([context_aggregator.user().get_context_frame()])
# Handle client disconnection events
@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()
# Run the pipeline
runner = PipelineRunner(handle_sigint=False)
await runner.run(task)
# Clean up: delete the uploaded file and temporary file
if file_info:
try:
await llm.file_api.delete_file(file_info["file"]["name"])
logger.info("Cleaned up uploaded file from Gemini")
except Exception as e:
logger.error(f"Error cleaning up file: {e}")
# Remove temporary file
try:
os.unlink(sample_file_path)
logger.info("Cleaned up temporary file")
except Exception as e:
logger.error(f"Error removing temporary file: {e}")
if __name__ == "__main__":
from pipecat.examples.run import main
upload_example_file = input("""
Please pass in a TEXT filepath to test upload.
NOTE: Files are stored on Google's servers for 48 hours.
Press Enter to use a default test file.
text filepath : """)
if upload_example_file:
print(f"Uploading file: {upload_example_file}")
sample_file_path = upload_example_file.strip()
else:
print(f"Using default file")
main(run_example, transport_params=transport_params)

View File

@@ -92,8 +92,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),
)

View File

@@ -152,7 +152,13 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
]
)
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):

View File

@@ -84,10 +84,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
observers=[UserBotLatencyLogObserver()],
)

View File

@@ -133,10 +133,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
observers=[
CustomObserver(),

View File

@@ -130,7 +130,10 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(allow_interruptions=True),
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
observers=[LLMSearchLoggerObserver()],
)

View File

@@ -239,7 +239,6 @@ Your response will be turned into speech so use only simple words and punctuatio
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

View File

@@ -146,7 +146,13 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
]
)
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):

Some files were not shown because too many files have changed in this diff Show More