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

examples: update google examples

Browse Source
This commit is contained in:
Aleix Conchillo Flaqué
2025-02-25 22:28:02 -08:00
parent bb89a036e5
commit f83c89c202
2 changed files with 4 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/foundational/22d-natural-conversation-gemini-audio.py
View File

@@ -389,7 +389,7 @@ class AudioAccumulator(FrameProcessor):
) )
self._user_speaking = False self._user_speaking = False
context = GoogleLLMContext() context = GoogleLLMContext()
context.add_audio_frames_message(text="Audio follows", audio_frames=self._audio_frames) context.add_audio_frames_message(audio_frames=self._audio_frames)
await self.push_frame(OpenAILLMContextFrame(context=context)) await self.push_frame(OpenAILLMContextFrame(context=context))
elif isinstance(frame, InputAudioRawFrame): elif isinstance(frame, InputAudioRawFrame):
# Append the audio frame to our buffer. Treat the buffer as a ring buffer, dropping the oldest # Append the audio frame to our buffer. Treat the buffer as a ring buffer, dropping the oldest

11
examples/phone-chatbot/bot_daily_gemini.py
View File

@@ -7,20 +7,15 @@ import argparse
import asyncio import asyncio
import os import os
import sys import sys
from dataclasses import dataclass
from typing import Optional from typing import Optional
import google.ai.generativelanguage as glm
from dotenv import load_dotenv from dotenv import load_dotenv
from loguru import logger from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import ( from pipecat.frames.frames import (
BotStoppedSpeakingFrame,
EndTaskFrame, EndTaskFrame,
Frame,
InputAudioRawFrame, InputAudioRawFrame,
SystemFrame,
TranscriptionFrame, TranscriptionFrame,
UserStartedSpeakingFrame, UserStartedSpeakingFrame,
UserStoppedSpeakingFrame, UserStoppedSpeakingFrame,
@@ -28,11 +23,11 @@ from pipecat.frames.frames import (
from pipecat.pipeline.pipeline import Pipeline from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContextFrame
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.services.ai_services import LLMService from pipecat.services.ai_services import LLMService
from pipecat.services.elevenlabs import ElevenLabsTTSService from pipecat.services.elevenlabs import ElevenLabsTTSService
from pipecat.services.google import GoogleLLMContext, GoogleLLMService from pipecat.services.google import GoogleLLMService
from pipecat.services.google.google import GoogleLLMContext
from pipecat.transports.services.daily import DailyDialinSettings, DailyParams, DailyTransport from pipecat.transports.services.daily import DailyDialinSettings, DailyParams, DailyTransport
load_dotenv(override=True) load_dotenv(override=True)
@@ -240,7 +235,7 @@ If it sounds like a human (saying hello, asking questions, etc.), call the funct
DO NOT say anything until you've determined if this is a voicemail or human.""" DO NOT say anything until you've determined if this is a voicemail or human."""
llm = GoogleLLMService( llm = GoogleLLMService(
model="models/gemini-2.0-flash-lite-preview-02-05", model="models/gemini-2.0-flash-lite",
api_key=os.getenv("GOOGLE_API_KEY"), api_key=os.getenv("GOOGLE_API_KEY"),
system_instruction=system_instruction, system_instruction=system_instruction,
tools=tools, tools=tools,