Reorganize examples into topic-based subfolders
Move 304 examples from a flat numbered directory into 14 descriptive subfolders: getting-started, services (speech + function-calling), transcription, vision, realtime, persistent-context, context-summarization, update-settings (stt/tts/llm), turn-management, thinking-and-mcp, transports, video-avatar, video-processing, and features. Strip numbered prefixes from filenames (e.g. 07c-interruptible-deepgram.py becomes services/speech/deepgram.py) since the folder context makes them redundant. Keep numbered prefixes only in getting-started/ where ordering matters. Update eval script paths and README to match the new structure.
This commit is contained in:
Mark Backman
250
examples/thinking-and-mcp/mcp-stdio.py
Normal file
250
examples/thinking-and-mcp/mcp-stdio.py
Normal file
@@ -0,0 +1,250 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import io
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import shutil
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
from mcp import StdioServerParameters
|
||||
from PIL import Image
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import (
|
||||
Frame,
|
||||
FunctionCallResultFrame,
|
||||
LLMRunFrame,
|
||||
URLImageRawFrame,
|
||||
)
|
||||
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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.anthropic.llm import AnthropicLLMService
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.mcp_service import MCPClient
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
class UrlToImageProcessor(FrameProcessor):
|
||||
def __init__(self, aiohttp_session: aiohttp.ClientSession, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
self._aiohttp_session = aiohttp_session
|
||||
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
if isinstance(frame, FunctionCallResultFrame):
|
||||
await self.push_frame(frame, direction)
|
||||
image_url = self.extract_url(frame.result)
|
||||
if image_url:
|
||||
await self.run_image_process(image_url)
|
||||
# sometimes we get multiple image urls- process 1 at a time
|
||||
await asyncio.sleep(1)
|
||||
else:
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
def extract_url(self, text: str):
|
||||
try:
|
||||
data = json.loads(text)
|
||||
if "artObject" in data:
|
||||
return data["artObject"]["webImage"]["url"]
|
||||
if "artworks" in data and len(data["artworks"]):
|
||||
return data["artworks"][0]["webImage"]["url"]
|
||||
except (json.JSONDecodeError, KeyError, TypeError):
|
||||
pass
|
||||
|
||||
return None
|
||||
|
||||
async def run_image_process(self, image_url: str):
|
||||
try:
|
||||
logger.debug(f"handling image from url: '{image_url}'")
|
||||
async with self._aiohttp_session.get(image_url) as response:
|
||||
image_stream = io.BytesIO(await response.content.read())
|
||||
image = Image.open(image_stream)
|
||||
image = image.convert("RGB")
|
||||
frame = URLImageRawFrame(
|
||||
url=image_url, image=image.tobytes(), size=image.size, format="RGB"
|
||||
)
|
||||
await self.push_frame(frame)
|
||||
except Exception as e:
|
||||
error_msg = f"Error handling image url {image_url}: {str(e)}"
|
||||
logger.error(error_msg)
|
||||
|
||||
|
||||
# full list of tools available from rijksmuseum MCP:
|
||||
# - get_artwork_details
|
||||
# - get_artwork_image
|
||||
# - get_user_sets
|
||||
# - get_user_set_details
|
||||
# - open_image_in_browser
|
||||
# - get_artist_timeline
|
||||
|
||||
mcp_tools_filter = ["get_artwork_details", "get_artwork_image", "open_image_in_browser"]
|
||||
|
||||
|
||||
def open_image_output_filter(output: str):
|
||||
pattern = r"Successfully opened image in browser: "
|
||||
text_to_print = re.sub(pattern, "", output)
|
||||
print(f"🖼️ link to high resolution artwork: {text_to_print}")
|
||||
|
||||
|
||||
# We use lambdas to defer transport parameter creation until the transport
|
||||
# type is selected at runtime.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
video_out_enabled=True,
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
video_out_enabled=True,
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session for API calls
|
||||
async with aiohttp.ClientSession() as session:
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
system_prompt = f"""
|
||||
You are a helpful LLM in a voice call.
|
||||
Your goal is to demonstrate your capabilities in a succinct way.
|
||||
You have access to tools to search the Rijksmuseum collection.
|
||||
Offer, for example, to show a floral still life, use the `search_artwork` tool.
|
||||
The tool may respond with a JSON object with an `artworks` array. Choose the art from that array.
|
||||
Once the tool has responded, tell the user the title and use the `open_image_in_browser` tool.
|
||||
Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points.
|
||||
Respond to what the user said in a creative and helpful way.
|
||||
Don't overexplain what you are doing.
|
||||
Just respond with short sentences when you are carrying out tool calls.
|
||||
"""
|
||||
|
||||
llm = AnthropicLLMService(
|
||||
api_key=os.getenv("ANTHROPIC_API_KEY"),
|
||||
settings=AnthropicLLMService.Settings(
|
||||
system_instruction=system_prompt,
|
||||
),
|
||||
)
|
||||
|
||||
try:
|
||||
mcp = MCPClient(
|
||||
server_params=StdioServerParameters(
|
||||
command=shutil.which("npx"),
|
||||
# https://github.com/r-huijts/rijksmuseum-mcp
|
||||
args=["-y", "mcp-server-rijksmuseum"],
|
||||
env={"RIJKSMUSEUM_API_KEY": os.getenv("RIJKSMUSEUM_API_KEY")},
|
||||
),
|
||||
# Optional
|
||||
tools_filter=mcp_tools_filter, # Optional
|
||||
tools_output_filters={"open_image_in_browser": open_image_output_filter},
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(f"error setting up mcp")
|
||||
logger.exception("error trace:")
|
||||
|
||||
mcp_image = UrlToImageProcessor(aiohttp_session=session)
|
||||
|
||||
tools = {}
|
||||
try:
|
||||
tools = await mcp.register_tools(llm)
|
||||
except Exception as e:
|
||||
logger.error(f"error registering tools")
|
||||
logger.exception("error trace:")
|
||||
|
||||
context = LLMContext(tools=tools)
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
user_aggregator, # User spoken responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
mcp_image, # URL image -> output
|
||||
transport.output(), # Transport bot output
|
||||
assistant_aggregator, # Assistant spoken responses and tool context
|
||||
]
|
||||
)
|
||||
|
||||
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: {client}")
|
||||
# Kick off the conversation.
|
||||
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__":
|
||||
if not os.getenv("RIJKSMUSEUM_API_KEY"):
|
||||
logger.error(
|
||||
f"Please set RIJKSMUSEUM_API_KEY environment variable for this example. See https://github.com/r-huijts/rijksmuseum-mcp and https://www.rijksmuseum.nl/en/register?redirectUrl=https://www.https://www.rijksmuseum.nl/en/rijksstudio/my/profile"
|
||||
)
|
||||
import sys
|
||||
|
||||
sys.exit(1)
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
163
examples/thinking-and-mcp/mcp-streamable-http-gemini-live.py
Normal file
163
examples/thinking-and-mcp/mcp-streamable-http-gemini-live.py
Normal file
@@ -0,0 +1,163 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
from mcp.client.session_group import StreamableHttpParameters
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
|
||||
from pipecat.services.mcp_service import MCPClient
|
||||
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 use lambdas to defer transport parameter creation until the transport
|
||||
# type is selected at runtime.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
try:
|
||||
# Github MCP docs: https://github.com/github/github-mcp-server
|
||||
# Enable Github Copilot on your GitHub account. Free tier is ok. (https://github.com/settings/copilot)
|
||||
# Generate a personal access token. It must be a Fine-grained token, classic tokens are not supported. (https://github.com/settings/personal-access-tokens)
|
||||
# Set permissions you want to use (eg. "all repositories", "profile: read/write", etc)
|
||||
mcp = MCPClient(
|
||||
server_params=StreamableHttpParameters(
|
||||
url="https://api.githubcopilot.com/mcp/",
|
||||
headers={"Authorization": f"Bearer {os.getenv('GITHUB_PERSONAL_ACCESS_TOKEN')}"},
|
||||
)
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(f"error setting up mcp")
|
||||
logger.exception("error trace:")
|
||||
|
||||
tools = {}
|
||||
try:
|
||||
tools = await mcp.get_tools_schema()
|
||||
except Exception as e:
|
||||
logger.error(f"error registering tools")
|
||||
logger.exception("error trace:")
|
||||
|
||||
system = f"""
|
||||
You are a helpful LLM in a voice call.
|
||||
Your goal is to answer questions about the user's GitHub repositories and account.
|
||||
You have access to a number of tools provided by Github. Use any and all tools to help users.
|
||||
Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points.
|
||||
Don't overexplain what you are doing.
|
||||
Just respond with short sentences when you are carrying out tool calls.
|
||||
"""
|
||||
|
||||
llm = GeminiLiveLLMService(
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
system_instruction=system,
|
||||
tools=tools,
|
||||
)
|
||||
|
||||
await mcp.register_tools_schema(tools, llm)
|
||||
|
||||
context = LLMContext([{"role": "developer", "content": "Please introduce yourself."}])
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
user_aggregator, # User spoken responses
|
||||
llm, # LLM
|
||||
transport.output(), # Transport bot output
|
||||
assistant_aggregator, # Assistant spoken responses and tool context
|
||||
]
|
||||
)
|
||||
|
||||
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: {client}")
|
||||
# Kick off the conversation.
|
||||
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__":
|
||||
if not os.getenv("GITHUB_PERSONAL_ACCESS_TOKEN"):
|
||||
logger.error(
|
||||
f"Please set GITHUB_PERSONAL_ACCESS_TOKEN environment variable for this example."
|
||||
)
|
||||
import sys
|
||||
|
||||
sys.exit(1)
|
||||
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
162
examples/thinking-and-mcp/mcp-streamable-http.py
Normal file
162
examples/thinking-and-mcp/mcp-streamable-http.py
Normal file
@@ -0,0 +1,162 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
from mcp.client.session_group import StreamableHttpParameters
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.google.llm import GoogleLLMService
|
||||
from pipecat.services.mcp_service import MCPClient
|
||||
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 use lambdas to defer transport parameter creation until the transport
|
||||
# type is selected at runtime.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
system_prompt = f"""
|
||||
You are a helpful LLM in a voice call.
|
||||
Your goal is to answer questions about the user's GitHub repositories and account.
|
||||
You have access to a number of tools provided by Github. Use any and all tools to help users.
|
||||
Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points.
|
||||
Don't overexplain what you are doing.
|
||||
Just respond with short sentences when you are carrying out tool calls.
|
||||
"""
|
||||
|
||||
llm = GoogleLLMService(
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
system_instruction=system_prompt,
|
||||
)
|
||||
|
||||
try:
|
||||
# Github MCP docs: https://github.com/github/github-mcp-server
|
||||
# Enable Github Copilot on your GitHub account. Free tier is ok. (https://github.com/settings/copilot)
|
||||
# Generate a personal access token. It must be a Fine-grained token, classic tokens are not supported. (https://github.com/settings/personal-access-tokens)
|
||||
# Set permissions you want to use (eg. "all repositories", "profile: read/write", etc)
|
||||
mcp = MCPClient(
|
||||
server_params=StreamableHttpParameters(
|
||||
url="https://api.githubcopilot.com/mcp/",
|
||||
headers={"Authorization": f"Bearer {os.getenv('GITHUB_PERSONAL_ACCESS_TOKEN')}"},
|
||||
)
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(f"error setting up mcp")
|
||||
logger.exception("error trace:")
|
||||
|
||||
tools = {}
|
||||
try:
|
||||
tools = await mcp.register_tools(llm)
|
||||
except Exception as e:
|
||||
logger.error(f"error registering tools")
|
||||
logger.exception("error trace:")
|
||||
|
||||
context = LLMContext(tools=tools)
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
user_aggregator, # User spoken responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
assistant_aggregator, # Assistant spoken responses and tool context
|
||||
]
|
||||
)
|
||||
|
||||
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: {client}")
|
||||
# Kick off the conversation.
|
||||
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__":
|
||||
if not os.getenv("GITHUB_PERSONAL_ACCESS_TOKEN"):
|
||||
logger.error(
|
||||
f"Please set GITHUB_PERSONAL_ACCESS_TOKEN environment variable for this example."
|
||||
)
|
||||
import sys
|
||||
|
||||
sys.exit(1)
|
||||
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
252
examples/thinking-and-mcp/multiple-mcp.py
Normal file
252
examples/thinking-and-mcp/multiple-mcp.py
Normal file
@@ -0,0 +1,252 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import asyncio
|
||||
import io
|
||||
import json
|
||||
import os
|
||||
import shutil
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
from mcp import StdioServerParameters
|
||||
from mcp.client.session_group import StreamableHttpParameters
|
||||
from PIL import Image
|
||||
|
||||
from pipecat.adapters.schemas.tools_schema import ToolsSchema
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import (
|
||||
Frame,
|
||||
FunctionCallResultFrame,
|
||||
LLMRunFrame,
|
||||
URLImageRawFrame,
|
||||
)
|
||||
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,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.anthropic.llm import AnthropicLLMService
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.mcp_service import MCPClient
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
class UrlToImageProcessor(FrameProcessor):
|
||||
def __init__(self, aiohttp_session: aiohttp.ClientSession, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
self._aiohttp_session = aiohttp_session
|
||||
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
if isinstance(frame, FunctionCallResultFrame):
|
||||
await self.push_frame(frame, direction)
|
||||
image_url = self.extract_url(frame.result)
|
||||
if image_url:
|
||||
await self.run_image_process(image_url)
|
||||
# sometimes we get multiple image urls- process 1 at a time
|
||||
await asyncio.sleep(1)
|
||||
else:
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
def extract_url(self, text: str):
|
||||
try:
|
||||
data = json.loads(text)
|
||||
if "artObject" in data:
|
||||
return data["artObject"]["webImage"]["url"]
|
||||
if "artworks" in data and len(data["artworks"]):
|
||||
return data["artworks"][0]["webImage"]["url"]
|
||||
except (json.JSONDecodeError, KeyError, TypeError):
|
||||
pass
|
||||
|
||||
async def run_image_process(self, image_url: str):
|
||||
try:
|
||||
logger.debug(f"handling image from url: '{image_url}'")
|
||||
async with self._aiohttp_session.get(image_url) as response:
|
||||
image_stream = io.BytesIO(await response.content.read())
|
||||
image = Image.open(image_stream)
|
||||
image = image.convert("RGB")
|
||||
frame = URLImageRawFrame(
|
||||
url=image_url, image=image.tobytes(), size=image.size, format="RGB"
|
||||
)
|
||||
await self.push_frame(frame)
|
||||
except Exception as e:
|
||||
error_msg = f"Error handling image url {image_url}: {str(e)}"
|
||||
logger.error(error_msg)
|
||||
|
||||
|
||||
# We use lambdas to defer transport parameter creation until the transport
|
||||
# type is selected at runtime.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
video_out_enabled=True,
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
video_out_enabled=True,
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session for API calls
|
||||
async with aiohttp.ClientSession() as session:
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
system_prompt = f"""
|
||||
You are a helpful LLM in a voice call.
|
||||
Your goal is to demonstrate your capabilities in a succinct way.
|
||||
You have access to tools to search the Rijksmuseum collection and the user's GitHub repositories and account.
|
||||
Offer, for example, to show a floral still life, use the `search_artwork` tool.
|
||||
The tool may respond with a JSON object with an `artworks` array. Choose the art from that array.
|
||||
Once the tool has responded, tell the user the title and use the `open_image_in_browser` tool.
|
||||
You can also offer to answer users questions about their GitHub repositories and account.
|
||||
Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points.
|
||||
Respond to what the user said in a creative and helpful way.
|
||||
Don't overexplain what you are doing.
|
||||
Just respond with short sentences when you are carrying out tool calls.
|
||||
"""
|
||||
|
||||
llm = AnthropicLLMService(
|
||||
api_key=os.getenv("ANTHROPIC_API_KEY"),
|
||||
settings=AnthropicLLMService.Settings(
|
||||
system_instruction=system_prompt,
|
||||
),
|
||||
)
|
||||
|
||||
try:
|
||||
rijksmuseum_mcp = MCPClient(
|
||||
server_params=StdioServerParameters(
|
||||
command=shutil.which("npx"),
|
||||
# https://github.com/r-huijts/rijksmuseum-mcp
|
||||
args=["-y", "mcp-server-rijksmuseum"],
|
||||
env={"RIJKSMUSEUM_API_KEY": os.getenv("RIJKSMUSEUM_API_KEY")},
|
||||
)
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(f"error setting up rijksmuseum mcp")
|
||||
logger.exception("error trace:")
|
||||
try:
|
||||
# Github MCP docs: https://github.com/github/github-mcp-server
|
||||
# Enable Github Copilot on your GitHub account. Free tier is ok. (https://github.com/settings/copilot)
|
||||
# Generate a personal access token. It must be a Fine-grained token, classic tokens are not supported. (https://github.com/settings/personal-access-tokens)
|
||||
# Set permissions you want to use (eg. "all repositories", "profile: read/write", etc)
|
||||
github_mcp = MCPClient(
|
||||
server_params=StreamableHttpParameters(
|
||||
url="https://api.githubcopilot.com/mcp/",
|
||||
headers={
|
||||
"Authorization": f"Bearer {os.getenv('GITHUB_PERSONAL_ACCESS_TOKEN')}"
|
||||
},
|
||||
)
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(f"error setting up mcp.run")
|
||||
logger.exception("error trace:")
|
||||
|
||||
rijksmuseum_tools = {}
|
||||
github_tools = {}
|
||||
try:
|
||||
rijksmuseum_tools = await rijksmuseum_mcp.register_tools(llm)
|
||||
github_tools = await github_mcp.register_tools(llm)
|
||||
except Exception as e:
|
||||
logger.error(f"error registering tools")
|
||||
logger.exception("error trace:")
|
||||
|
||||
all_standard_tools = rijksmuseum_tools.standard_tools + github_tools.standard_tools
|
||||
all_tools = ToolsSchema(standard_tools=all_standard_tools)
|
||||
|
||||
context = LLMContext(tools=all_tools)
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
mcp_image_processor = UrlToImageProcessor(aiohttp_session=session)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
user_aggregator, # User spoken responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
mcp_image_processor, # URL image -> output
|
||||
transport.output(), # Transport bot output
|
||||
assistant_aggregator, # Assistant spoken responses and tool context
|
||||
]
|
||||
)
|
||||
|
||||
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: {client}")
|
||||
# Kick off the conversation.
|
||||
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__":
|
||||
if not os.getenv("RIJKSMUSEUM_API_KEY") or not os.getenv("GITHUB_PERSONAL_ACCESS_TOKEN"):
|
||||
logger.error(
|
||||
f"Please set `RIJKSMUSEUM_API_KEY` and `GITHUB_PERSONAL_ACCESS_TOKEN` environment variables. See https://github.com/r-huijts/rijksmuseum-mcp."
|
||||
)
|
||||
import sys
|
||||
|
||||
sys.exit(1)
|
||||
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
142
examples/thinking-and-mcp/thinking-anthropic.py
Normal file
142
examples/thinking-and-mcp/thinking-anthropic.py
Normal file
@@ -0,0 +1,142 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
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 (
|
||||
AssistantThoughtMessage,
|
||||
LLMContextAggregatorPair,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.anthropic.llm import AnthropicLLMService
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
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 use lambdas to defer transport parameter creation until the transport
|
||||
# type is selected at runtime.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
llm = AnthropicLLMService(
|
||||
api_key=os.getenv("ANTHROPIC_API_KEY"),
|
||||
settings=AnthropicLLMService.Settings(
|
||||
thinking=AnthropicLLMService.ThinkingConfig(
|
||||
type="enabled",
|
||||
budget_tokens=2048,
|
||||
),
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
||||
),
|
||||
)
|
||||
|
||||
context = LLMContext()
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
user_aggregator, # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
assistant_aggregator, # 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.
|
||||
context.add_message({"role": "developer", "content": "Say hello briefly."})
|
||||
# Here are some example prompts conducive to demonstrating
|
||||
# thinking (picked from Google and Anthropic docs).
|
||||
# context.add_message(
|
||||
# {
|
||||
# "role": "user",
|
||||
# "content": "Analogize photosynthesis and growing up. Keep your answer concise.",
|
||||
# # "content": "Compare and contrast electric cars and hybrid cars."
|
||||
# # "content": "Are there an infinite number of prime numbers such that n mod 4 == 3?"
|
||||
# }
|
||||
# )
|
||||
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()
|
||||
|
||||
@assistant_aggregator.event_handler("on_assistant_thought")
|
||||
async def on_assistant_thought(aggregator, message: AssistantThoughtMessage):
|
||||
logger.info(f"Thought (timestamp: {message.timestamp}): {message.content}")
|
||||
|
||||
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()
|
||||
167
examples/thinking-and-mcp/thinking-functions-anthropic.py
Normal file
167
examples/thinking-and-mcp/thinking-functions-anthropic.py
Normal file
@@ -0,0 +1,167 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
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 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 (
|
||||
AssistantThoughtMessage,
|
||||
LLMContextAggregatorPair,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.anthropic.llm import AnthropicLLMService
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.llm_service import FunctionCallParams
|
||||
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)
|
||||
|
||||
|
||||
async def check_flight_status(params: FunctionCallParams, flight_number: str):
|
||||
"""Check the status of a flight. Returns status (e.g., "on time", "delayed") and departure time.
|
||||
|
||||
Args:
|
||||
flight_number (str): The flight number, e.g. "AA100".
|
||||
"""
|
||||
await params.result_callback({"status": "delayed", "departure_time": "14:30"})
|
||||
|
||||
|
||||
async def book_taxi(params: FunctionCallParams, time: str):
|
||||
"""Book a taxi for a given time. Returns status (e.g., "done").
|
||||
|
||||
Args:
|
||||
time (str): The time to book the taxi for, e.g. "15:00".
|
||||
"""
|
||||
await params.result_callback({"status": "done"})
|
||||
|
||||
|
||||
# We use lambdas to defer transport parameter creation until the transport
|
||||
# type is selected at runtime.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
llm = AnthropicLLMService(
|
||||
api_key=os.getenv("ANTHROPIC_API_KEY"),
|
||||
settings=AnthropicLLMService.Settings(
|
||||
thinking=AnthropicLLMService.ThinkingConfig(
|
||||
type="enabled",
|
||||
budget_tokens=2048,
|
||||
),
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
||||
),
|
||||
)
|
||||
|
||||
llm.register_direct_function(check_flight_status)
|
||||
llm.register_direct_function(book_taxi)
|
||||
|
||||
tools = ToolsSchema(standard_tools=[check_flight_status, book_taxi])
|
||||
|
||||
context = LLMContext(tools=tools)
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
user_aggregator, # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
assistant_aggregator, # 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.
|
||||
context.add_message({"role": "developer", "content": "Say hello briefly."})
|
||||
# Here is an example prompt conducive to demonstrating thinking and
|
||||
# function calling.
|
||||
# This example comes from Gemini docs.
|
||||
# context.add_message(
|
||||
# {
|
||||
# "role": "user",
|
||||
# "content": "Check the status of flight AA100 and, if it's delayed, book me a taxi 2 hours before its departure time.",
|
||||
# }
|
||||
# )
|
||||
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()
|
||||
|
||||
@assistant_aggregator.event_handler("on_assistant_thought")
|
||||
async def on_assistant_thought(aggregator, message: AssistantThoughtMessage):
|
||||
logger.info(f"Thought (timestamp: {message.timestamp}): {message.content}")
|
||||
|
||||
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()
|
||||
168
examples/thinking-and-mcp/thinking-functions-google.py
Normal file
168
examples/thinking-and-mcp/thinking-functions-google.py
Normal file
@@ -0,0 +1,168 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
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 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 (
|
||||
AssistantThoughtMessage,
|
||||
LLMContextAggregatorPair,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.google.llm import GoogleLLMService
|
||||
from pipecat.services.llm_service import FunctionCallParams
|
||||
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)
|
||||
|
||||
|
||||
async def check_flight_status(params: FunctionCallParams, flight_number: str):
|
||||
"""Check the status of a flight. Returns status (e.g., "on time", "delayed") and departure time.
|
||||
|
||||
Args:
|
||||
flight_number (str): The flight number, e.g. "AA100".
|
||||
"""
|
||||
await params.result_callback({"status": "delayed", "departure_time": "14:30"})
|
||||
|
||||
|
||||
async def book_taxi(params: FunctionCallParams, time: str):
|
||||
"""Book a taxi for a given time. Returns status (e.g., "done").
|
||||
|
||||
Args:
|
||||
time (str): The time to book the taxi for, e.g. "15:00".
|
||||
"""
|
||||
await params.result_callback({"status": "done"})
|
||||
|
||||
|
||||
# We use lambdas to defer transport parameter creation until the transport
|
||||
# type is selected at runtime.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
llm = GoogleLLMService(
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
# model="gemini-3-pro-preview", # A more powerful reasoning model, but slower
|
||||
settings=GoogleLLMService.Settings(
|
||||
thinking=GoogleLLMService.ThinkingConfig(
|
||||
thinking_budget=-1, # Dynamic thinking
|
||||
include_thoughts=True,
|
||||
),
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
||||
),
|
||||
)
|
||||
|
||||
llm.register_direct_function(check_flight_status)
|
||||
llm.register_direct_function(book_taxi)
|
||||
|
||||
tools = ToolsSchema(standard_tools=[check_flight_status, book_taxi])
|
||||
|
||||
context = LLMContext(tools=tools)
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
user_aggregator, # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
assistant_aggregator, # 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.
|
||||
context.add_message({"role": "developer", "content": "Say hello briefly."})
|
||||
# Replace the above with one of these example prompts to demonstrate
|
||||
# thinking and function calling.
|
||||
# This example comes from Gemini docs.
|
||||
# context.add_message(
|
||||
# {
|
||||
# "role": "user",
|
||||
# "content": "Check the status of flight AA100 and, if it's delayed, book me a taxi 2 hours before its departure time.",
|
||||
# }
|
||||
# )
|
||||
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()
|
||||
|
||||
@assistant_aggregator.event_handler("on_assistant_thought")
|
||||
async def on_assistant_thought(aggregator, message: AssistantThoughtMessage):
|
||||
logger.info(f"Thought (timestamp: {message.timestamp}): {message.content}")
|
||||
|
||||
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()
|
||||
144
examples/thinking-and-mcp/thinking-google.py
Normal file
144
examples/thinking-and-mcp/thinking-google.py
Normal file
@@ -0,0 +1,144 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
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 (
|
||||
AssistantThoughtMessage,
|
||||
LLMContextAggregatorPair,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.google.llm import GoogleLLMService
|
||||
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 use lambdas to defer transport parameter creation until the transport
|
||||
# type is selected at runtime.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
llm = GoogleLLMService(
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
# model="gemini-3-pro-preview", # A more powerful reasoning model, but slower
|
||||
settings=GoogleLLMService.Settings(
|
||||
thinking=GoogleLLMService.ThinkingConfig(
|
||||
thinking_budget=-1, # Dynamic thinking
|
||||
include_thoughts=True,
|
||||
),
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
||||
),
|
||||
)
|
||||
|
||||
context = LLMContext()
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
user_aggregator, # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
assistant_aggregator, # 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.
|
||||
context.add_message({"role": "developer", "content": "Say hello briefly."})
|
||||
# Replace the above with one of these example prompts to demonstrate
|
||||
# thinking.
|
||||
# These examples come from Gemini and Anthropic docs.
|
||||
# context.add_message(
|
||||
# {
|
||||
# "role": "user",
|
||||
# "content": "Analogize photosynthesis and growing up. Keep your answer concise.",
|
||||
# # "content": "Compare and contrast electric cars and hybrid cars."
|
||||
# # "content": "Are there an infinite number of prime numbers such that n mod 4 == 3?"
|
||||
# }
|
||||
# )
|
||||
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()
|
||||
|
||||
@assistant_aggregator.event_handler("on_assistant_thought")
|
||||
async def on_assistant_thought(aggregator, message: AssistantThoughtMessage):
|
||||
logger.info(f"Thought (timestamp: {message.timestamp}): {message.content}")
|
||||
|
||||
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()
|
||||
Reference in New Issue
Block a user