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

Update examples

Browse Source
This commit is contained in:
Mark Backman
2026-03-04 22:55:51 -05:00
parent 197885773f
commit 039a8f6c7d
207 changed files with 1241 additions and 852 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
examples/foundational/54b-context-summarization-manual-openai.py
View File

@@ -34,7 +34,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.openai.llm import OpenAILLMService
@@ -78,10 +78,21 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
system_prompt = """You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your
capabilities in a succinct way. 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.
If the user asks you to summarize the conversation, call the
summarize_conversation function. After summarization, briefly acknowledge
that the conversation history has been compressed.
"""
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), system_instruction=system_prompt)
llm.register_function("summarize_conversation", summarize_conversation)
@@ -97,22 +108,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
tools = ToolsSchema(standard_tools=[summarize_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 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. "
"If the user asks you to summarize the conversation, call the "
"summarize_conversation function. After summarization, briefly acknowledge "
"that the conversation history has been compressed."
),
},
]
context = LLMContext(messages, tools=tools)
context = LLMContext(tools=tools)
# Automatic summarization is NOT enabled here (enable_auto_context_summarization
# defaults to False). The summarizer is still created internally so that
@@ -147,7 +143,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
async def on_client_connected(transport, client):
logger.info("Client connected")
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMRunFrame()])
@transport.event_handler("on_client_disconnected")