Files
pipecat/examples/vision/vision-moondream.py
Mark Backman 58a17c7b1b Include examples in type checking
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.
2026-04-21 15:43:31 -04:00

116 lines
3.2 KiB
Python

#
# Copyright (c) 2024-2026, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import os
from dotenv import load_dotenv
from loguru import logger
from PIL import Image
from pipecat.frames.frames import UserImageRawFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.moondream.vision import MoondreamService
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_out_enabled=True,
),
"webrtc": lambda: TransportParams(
audio_out_enabled=True,
),
}
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
tts = CartesiaTTSService(
api_key=os.environ["CARTESIA_API_KEY"],
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
vision = MoondreamService()
pipeline = Pipeline(
[
vision, # Vision
tts, # TTS
transport.output(), # Transport bot output
]
)
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")
if not runner_args.body:
script_dir = os.path.dirname(__file__)
runner_args.body = {
"image_path": os.path.join(script_dir, "assets", "cat.jpg"),
"question": "Describe this image",
}
image_path = runner_args.body["image_path"]
question = runner_args.body["question"]
# Describe the image.
image = Image.open(image_path)
await task.queue_frames(
[
UserImageRawFrame(
image=image.tobytes(),
format="RGB",
size=image.size,
text=question,
)
]
)
@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()