wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'main' into sarvam/stt

Browse Source
This commit is contained in:
shreyas-sarvam
2025-10-31 23:09:47 +05:30
parent d905b21f72 334167e3d7
commit d680ec2e69
35 changed files with 571 additions and 200 deletions
Download Patch File Download Diff File Expand all files Collapse all files

132
examples/foundational/07c-interruptible-deepgram-http.py Normal file
View File

@@ -0,0 +1,132 @@
#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import os
import aiohttp
from dotenv import load_dotenv
from loguru import logger
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.audio.vad.vad_analyzer import VADParams
from pipecat.frames.frames import LLMRunFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.llm_context import LLMContext
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.deepgram.tts import DeepgramHttpTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
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(params=VADParams(stop_secs=0.2)),
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
),
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
),
}
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
async with aiohttp.ClientSession() as session:
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = DeepgramHttpTTSService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
voice="aura-2-andromeda-en",
aiohttp_session=session,
)
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
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 = LLMContext(messages)
context_aggregator = LLMContextAggregatorPair(context)
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,
),
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
)
@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": "Please introduce yourself to the user."})
await task.queue_frames([LLMRunFrame()])
@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=runner_args.handle_sigint)
await runner.run(task)
async def bot(runner_args: RunnerArguments):
"""Main bot entry point compatible with Pipecat Cloud."""
transport = await create_transport(runner_args, transport_params)
await run_bot(transport, runner_args)
if __name__ == "__main__":
from pipecat.runner.run import main
main()

2
examples/foundational/14d-function-calling-anthropic-video.py
View File

@@ -53,7 +53,7 @@ async def fetch_user_image(params: FunctionCallParams):
# Request a user image frame and indicate that it should be added to the
# context.
await params.llm.push_frame(
UserImageRequestFrame(user_id=user_id, text=question, add_to_context=True),
UserImageRequestFrame(user_id=user_id, text=question, append_to_context=True),
FrameDirection.UPSTREAM,
)

2
examples/foundational/14d-function-calling-aws-video.py
View File

@@ -53,7 +53,7 @@ async def fetch_user_image(params: FunctionCallParams):
# Request a user image frame and indicate that it should be added to the
# context.
await params.llm.push_frame(
UserImageRequestFrame(user_id=user_id, text=question, add_to_context=True),
UserImageRequestFrame(user_id=user_id, text=question, append_to_context=True),
FrameDirection.UPSTREAM,
)

2
examples/foundational/14d-function-calling-gemini-flash-video.py
View File

@@ -53,7 +53,7 @@ async def fetch_user_image(params: FunctionCallParams):
# Request a user image frame and indicate that it should be added to the
# context.
await params.llm.push_frame(
UserImageRequestFrame(user_id=user_id, text=question, add_to_context=True),
UserImageRequestFrame(user_id=user_id, text=question, append_to_context=True),
FrameDirection.UPSTREAM,
)

2
examples/foundational/14d-function-calling-moondream-video.py
View File

@@ -55,7 +55,7 @@ async def fetch_user_image(params: FunctionCallParams):
# image to be added to the context because we will process it with
# Moondream.
await params.llm.push_frame(
UserImageRequestFrame(user_id=user_id, text=question, add_to_context=False),
UserImageRequestFrame(user_id=user_id, text=question, append_to_context=False),
FrameDirection.UPSTREAM,
)

2
examples/foundational/14d-function-calling-openai-video.py
View File

@@ -54,7 +54,7 @@ async def fetch_user_image(params: FunctionCallParams):
# Request a user image frame and indicate that it should be added to the
# context.
await params.llm.push_frame(
UserImageRequestFrame(user_id=user_id, text=question, add_to_context=True),
UserImageRequestFrame(user_id=user_id, text=question, append_to_context=True),
FrameDirection.UPSTREAM,
)

7
examples/foundational/19-openai-realtime.py
View File

@@ -187,12 +187,7 @@ Remember, your responses should be short. Just one or two sentences, usually. Re
tools,
)
context_aggregator = LLMContextAggregatorPair(
context,
# `expect_stripped_words=False` needed when OpenAI Realtime used with
# "audio" modality (the default)
assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
)
context_aggregator = LLMContextAggregatorPair(context)
pipeline = Pipeline(
[

7
examples/foundational/19a-azure-realtime.py
View File

@@ -175,12 +175,7 @@ Remember, your responses should be short. Just one or two sentences, usually. Re
tools,
)
context_aggregator = LLMContextAggregatorPair(
context,
# `expect_stripped_words=False` needed when OpenAI Realtime used with
# "audio" modality (the default)
assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
)
context_aggregator = LLMContextAggregatorPair(context)
pipeline = Pipeline(
[

7
examples/foundational/26a-gemini-live-transcription.py
View File

@@ -92,12 +92,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# },
],
)
context_aggregator = LLMContextAggregatorPair(
context,
# `expect_stripped_words=False` needed when Gemini Live used with AUDIO
# modality (the default)
assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
)
context_aggregator = LLMContextAggregatorPair(context)
transcript = TranscriptProcessor()

7
examples/foundational/26b-gemini-live-function-calling.py
View File

@@ -144,12 +144,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
context = LLMContext(
[{"role": "user", "content": "Say hello."}],
)
context_aggregator = LLMContextAggregatorPair(
context,
# `expect_stripped_words=False` needed when Gemini Live used with AUDIO
# modality (the default)
assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
)
context_aggregator = LLMContextAggregatorPair(context)
pipeline = Pipeline(
[

7
examples/foundational/26c-gemini-live-video.py
View File

@@ -75,12 +75,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
},
],
)
context_aggregator = LLMContextAggregatorPair(
context,
# `expect_stripped_words=False` needed when Gemini Live used with AUDIO
# modality (the default)
assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
)
context_aggregator = LLMContextAggregatorPair(context)
pipeline = Pipeline(
[

7
examples/foundational/26e-gemini-live-google-search.py
View File

@@ -100,12 +100,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
}
],
)
context_aggregator = LLMContextAggregatorPair(
context,
# `expect_stripped_words=False` needed when Gemini Live used with AUDIO
# modality (the default)
assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
)
context_aggregator = LLMContextAggregatorPair(context)
pipeline = Pipeline(
[

7
examples/foundational/26f-gemini-live-files-api.py
View File

@@ -164,12 +164,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
# Create context aggregator
context_aggregator = LLMContextAggregatorPair(
context,
# `expect_stripped_words=False` needed when Gemini Live used with AUDIO
# modality (the default)
assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
)
context_aggregator = LLMContextAggregatorPair(context)
# Build the pipeline
pipeline = Pipeline(

7
examples/foundational/26g-gemini-live-groundingMetadata.py
View File

@@ -127,12 +127,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# Set up conversation context and management
context = LLMContext(messages)
context_aggregator = LLMContextAggregatorPair(
context,
# `expect_stripped_words=False` needed when Gemini Live used with AUDIO
# modality (the default)
assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
)
context_aggregator = LLMContextAggregatorPair(context)
pipeline = Pipeline(
[

7
examples/foundational/26h-gemini-live-vertex-function-calling.py
View File

@@ -140,12 +140,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
context = LLMContext([{"role": "user", "content": "Say hello."}])
context_aggregator = LLMContextAggregatorPair(
context,
# `expect_stripped_words=False` needed when Gemini Live used with AUDIO
# modality (the default)
assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
)
context_aggregator = LLMContextAggregatorPair(context)
pipeline = Pipeline(
[

7
examples/foundational/26i-gemini-live-graceful-end.py
View File

@@ -157,12 +157,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
context = LLMContext(
[{"role": "user", "content": "Say hello."}],
)
context_aggregator = LLMContextAggregatorPair(
context,
# `expect_stripped_words=False` needed when Gemini Live used with AUDIO
# modality (the default)
assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
)
context_aggregator = LLMContextAggregatorPair(context)
pipeline = Pipeline(
[

7
examples/foundational/46-video-processing.py
View File

@@ -111,12 +111,7 @@ async def run_bot(pipecat_transport):
]
context = LLMContext(messages)
context_aggregator = LLMContextAggregatorPair(
context,
# `expect_stripped_words=False` needed when Gemini Live used with AUDIO
# modality (the default)
assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
)
context_aggregator = LLMContextAggregatorPair(context)
# RTVI events for Pipecat client UI
rtvi = RTVIProcessor()