58a17c7b1b
Remove `examples/` from the `pyrightconfig.json` ignore list and fix
the resulting type errors across all example files. Common fixes:
- Required API keys: `os.getenv("X")` -> `os.environ["X"]` so the
return type is `str` rather than `str | None`, and misconfiguration
fails fast.
- Narrow `LLMContextMessage` union members with `isinstance(..., dict)`
before dict-style access.
- `assert isinstance(params.llm, ...)` before calling service-specific
methods that aren't on the base `LLMService`.
- Guard optional frame fields (e.g. `LLMSearchResponseFrame.search_result`)
before use.
149 lines
4.7 KiB
Python
149 lines
4.7 KiB
Python
#
|
|
# Copyright (c) 2024-2026, Daily
|
|
#
|
|
# SPDX-License-Identifier: BSD 2-Clause License
|
|
#
|
|
|
|
"""
|
|
A conversational AI bot using Gemini for both LLM, STT and TTS.
|
|
|
|
This example demonstrates how to use Gemini's image generation capabilities.
|
|
|
|
Features showcased:
|
|
- Gemini LLM for conversation and image generation
|
|
- Google TTS and STT
|
|
|
|
Make sure to set your environment variables:
|
|
export GOOGLE_API_KEY=your_api_key_here
|
|
"""
|
|
|
|
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 (
|
|
LLMContextAggregatorPair,
|
|
LLMUserAggregatorParams,
|
|
)
|
|
from pipecat.runner.types import RunnerArguments
|
|
from pipecat.runner.utils import create_transport
|
|
from pipecat.services.google.llm import GoogleLLMService
|
|
from pipecat.services.google.stt import GoogleSTTService
|
|
from pipecat.services.google.tts import GoogleTTSService
|
|
from pipecat.transcriptions.language import Language
|
|
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
|
from pipecat.transports.daily.transport import DailyParams
|
|
|
|
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,
|
|
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")
|
|
|
|
stt = GoogleSTTService(
|
|
credentials=os.environ["GOOGLE_TEST_CREDENTIALS"],
|
|
settings=GoogleSTTService.Settings(
|
|
languages=[Language.EN_US],
|
|
),
|
|
)
|
|
|
|
tts = GoogleTTSService(
|
|
credentials=os.environ["GOOGLE_TEST_CREDENTIALS"],
|
|
settings=GoogleTTSService.Settings(
|
|
voice="en-US-Chirp3-HD-Charon",
|
|
language=Language.EN_US,
|
|
),
|
|
)
|
|
|
|
llm = GoogleLLMService(
|
|
api_key=os.environ["GOOGLE_API_KEY"],
|
|
settings=GoogleLLMService.Settings(
|
|
model="gemini-2.5-flash-image",
|
|
# model="gemini-3-pro-image-preview", # A more powerful model, but slower,
|
|
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, # STT
|
|
user_aggregator, # User responses
|
|
llm, # LLM
|
|
tts, # Gemini 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 with a styled introduction
|
|
context.add_message(
|
|
{"role": "developer", "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()
|