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

Merge pull request #11 from daily-co/autopep

Browse Source 
Autopep linter fixes
This commit is contained in:
Moishe Lettvin
2024-01-25 12:17:26 -05:00
committed by GitHub
parent f0d9b0613e 5fdda43bed
commit 2886997693
27 changed files with 147 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/dailyai/conversation_wrappers.py
View File

@@ -5,6 +5,7 @@ from typing import AsyncGenerator, Awaitable, Callable
from dailyai.queue_aggregators import LLMContextAggregator
from dailyai.queue_frame import EndStreamQueueFrame, QueueFrame, TranscriptionQueueFrame
class InterruptibleConversationWrapper:
def __init__(
@@ -14,7 +15,7 @@ class InterruptibleConversationWrapper:
[str, LLMContextAggregator, LLMContextAggregator], Awaitable[None]
],
interrupt: Callable[[], None],
my_participant_id: str|None,
my_participant_id: str | None,
llm_messages: list[dict[str, str]],
llm_context_aggregator_in=LLMContextAggregator,
llm_context_aggregator_out=LLMContextAggregator,

11
src/dailyai/queue_aggregators.py
View File

@@ -5,6 +5,7 @@ from dailyai.services.ai_services import AIService
from typing import AsyncGenerator, List
class QueueTee:
async def run_to_queue_and_generate(
self,
@@ -24,15 +25,21 @@ class QueueTee:
for queue in output_queues:
await queue.put(frame)
class LLMContextAggregator(AIService):
def __init__(self, messages: list[dict], role:str, bot_participant_id=None, complete_sentences=True):
def __init__(
self,
messages: list[dict],
role: str,
bot_participant_id=None,
complete_sentences=True):
self.messages = messages
self.bot_participant_id = bot_participant_id
self.role = role
self.sentence = ""
self.complete_sentences = complete_sentences
async def process_frame(self, frame:QueueFrame) -> AsyncGenerator[QueueFrame, None]:
async def process_frame(self, frame: QueueFrame) -> AsyncGenerator[QueueFrame, None]:
# TODO: split up transcription by participant
if isinstance(frame, TextQueueFrame):
if self.complete_sentences:

12
src/dailyai/queue_frame.py
View File

@@ -2,39 +2,49 @@ from enum import Enum
from dataclasses import dataclass
from typing import Any
class QueueFrame:
pass
class ControlQueueFrame(QueueFrame):
pass
class StartStreamQueueFrame(ControlQueueFrame):
pass
class EndStreamQueueFrame(ControlQueueFrame):
pass
@dataclass()
class AudioQueueFrame(QueueFrame):
data: bytes
@dataclass()
class ImageQueueFrame(QueueFrame):
url: str | None
image: bytes
@dataclass()
class TextQueueFrame(QueueFrame):
text: str
@dataclass()
class TranscriptionQueueFrame(TextQueueFrame):
participantId: str
timestamp: str
@dataclass()
class LLMMessagesQueueFrame(QueueFrame):
messages: list[dict[str,str]] # TODO: define this more concretely!
messages: list[dict[str, str]] # TODO: define this more concretely!
class AppMessageQueueFrame(QueueFrame):
message: Any

9
src/dailyai/services/ai_services.py
View File

@@ -65,7 +65,7 @@ class AIService:
raise e
@abstractmethod
async def process_frame(self, frame:QueueFrame) -> AsyncGenerator[QueueFrame, None]:
async def process_frame(self, frame: QueueFrame) -> AsyncGenerator[QueueFrame, None]:
if isinstance(frame, ControlQueueFrame):
yield frame
@@ -75,6 +75,7 @@ class AIService:
if False:
yield QueueFrame()
class LLMService(AIService):
@abstractmethod
async def run_llm_async(self, messages) -> AsyncGenerator[str, None]:
@@ -146,7 +147,7 @@ class ImageGenService(AIService):
# Renders the image. Returns an Image object.
@abstractmethod
async def run_image_gen(self, sentence:str) -> tuple[str, bytes]:
async def run_image_gen(self, sentence: str) -> tuple[str, bytes]:
pass
async def process_frame(self, frame: QueueFrame) -> AsyncGenerator[QueueFrame, None]:
@@ -157,15 +158,16 @@ class ImageGenService(AIService):
(url, image_data) = await self.run_image_gen(frame.text)
yield ImageQueueFrame(url, image_data)
class STTService(AIService):
"""STTService is a base class for speech-to-text services."""
_frame_rate: int
def __init__(self, frame_rate: int = 16000, **kwargs):
super().__init__(**kwargs)
self._frame_rate = frame_rate
@abstractmethod
async def run_stt(self, audio: BinaryIO) -> str:
"""Returns transcript as a string"""
@@ -188,6 +190,7 @@ class STTService(AIService):
text = await self.run_stt(content)
yield TextQueueFrame(text)
@dataclass
class AIServiceConfig:
tts: TTSService

36
src/dailyai/services/azure_ai_services.py
View File

@@ -15,6 +15,7 @@ from PIL import Image
# See .env.example for Azure configuration needed
from azure.cognitiveservices.speech import SpeechSynthesizer, SpeechConfig, ResultReason, CancellationReason
class AzureTTSService(TTSService):
def __init__(self, speech_key=None, speech_region=None):
super().__init__()
@@ -23,18 +24,19 @@ class AzureTTSService(TTSService):
speech_region = speech_region or os.getenv("AZURE_SPEECH_SERVICE_REGION")
self.speech_config = SpeechConfig(subscription=speech_key, region=speech_region)
self.speech_synthesizer = SpeechSynthesizer(speech_config=self.speech_config, audio_config=None)
self.speech_synthesizer = SpeechSynthesizer(
speech_config=self.speech_config, audio_config=None)
async def run_tts(self, sentence) -> AsyncGenerator[bytes, None]:
self.logger.info("Running azure tts")
ssml = "<speak version='1.0' xml:lang='en-US' xmlns='http://www.w3.org/2001/10/synthesis' " \
"xmlns:mstts='http://www.w3.org/2001/mstts'>" \
"<voice name='en-US-SaraNeural'>" \
"<mstts:silence type='Sentenceboundary' value='20ms' />" \
"<mstts:express-as style='lyrical' styledegree='2' role='SeniorFemale'>" \
"<prosody rate='1.05'>" \
f"{sentence}" \
"</prosody></mstts:express-as></voice></speak> "
"xmlns:mstts='http://www.w3.org/2001/mstts'>" \
"<voice name='en-US-SaraNeural'>" \
"<mstts:silence type='Sentenceboundary' value='20ms' />" \
"<mstts:express-as style='lyrical' styledegree='2' role='SeniorFemale'>" \
"<prosody rate='1.05'>" \
f"{sentence}" \
"</prosody></mstts:express-as></voice></speak> "
result = await asyncio.to_thread(self.speech_synthesizer.speak_ssml, (ssml))
self.logger.info("Got azure tts result")
if result.reason == ResultReason.SynthesizingAudioCompleted:
@@ -47,6 +49,7 @@ class AzureTTSService(TTSService):
if cancellation_details.reason == CancellationReason.Error:
self.logger.info("Error details: {}".format(cancellation_details.error_details))
class AzureLLMService(LLMService):
def __init__(self, api_key=None, azure_endpoint=None, api_version=None, model=None):
super().__init__()
@@ -54,11 +57,13 @@ class AzureLLMService(LLMService):
azure_endpoint = azure_endpoint or os.getenv("AZURE_CHATGPT_ENDPOINT")
if not azure_endpoint:
raise Exception("No azure endpoint specified for Azure LLM, please set AZURE_CHATGPT_ENDPOINT in the environment or pass it to the AzureLLMService constructor")
raise Exception(
"No azure endpoint specified for Azure LLM, please set AZURE_CHATGPT_ENDPOINT in the environment or pass it to the AzureLLMService constructor")
model: str | None = model or os.getenv("AZURE_CHATGPT_DEPLOYMENT_ID")
if not model:
raise Exception("No model specified for Azure LLM, please set AZURE_CHATGPT_DEPLOYMENT_ID in the environment or pass it to the AzureLLMService constructor")
raise Exception(
"No model specified for Azure LLM, please set AZURE_CHATGPT_DEPLOYMENT_ID in the environment or pass it to the AzureLLMService constructor")
self.model: str = model
api_version = api_version or "2023-12-01-preview"
@@ -90,9 +95,16 @@ class AzureLLMService(LLMService):
else:
return None
class AzureImageGenServiceREST(ImageGenService):
def __init__(self, image_size:str, api_key=None, azure_endpoint=None, api_version=None, model=None):
def __init__(
self,
image_size: str,
api_key=None,
azure_endpoint=None,
api_version=None,
model=None):
super().__init__(image_size=image_size)
self.api_key = api_key or os.getenv("AZURE_DALLE_KEY")
self.azure_endpoint = azure_endpoint or os.getenv("AZURE_DALLE_ENDPOINT")
@@ -103,7 +115,7 @@ class AzureImageGenServiceREST(ImageGenService):
# TODO hoist the session to app-level
async with aiohttp.ClientSession() as session:
url = f"{self.azure_endpoint}openai/images/generations:submit?api-version={self.api_version}"
headers= { "api-key": self.api_key, "Content-Type": "application/json" }
headers = {"api-key": self.api_key, "Content-Type": "application/json"}
body = {
# Enter your prompt text here
"prompt": sentence,

15
src/dailyai/services/daily_transport_service.py
View File

@@ -30,6 +30,7 @@ from daily import (
VirtualSpeakerDevice,
)
class DailyTransportService(EventHandler):
_daily_initialized = False
_lock = threading.Lock()
@@ -111,7 +112,8 @@ class DailyTransportService(EventHandler):
if self.loop:
asyncio.run_coroutine_threadsafe(handler(*args, **kwargs), self.loop)
else:
raise Exception("No event loop to run coroutine. In order to use async event handlers, you must run the DailyTransportService in an asyncio event loop.")
raise Exception(
"No event loop to run coroutine. In order to use async event handlers, you must run the DailyTransportService in an asyncio event loop.")
else:
handler(*args, **kwargs)
except Exception as e:
@@ -126,8 +128,11 @@ class DailyTransportService(EventHandler):
if event_name not in [method[0] for method in methods]:
raise Exception(f"Event handler {event_name} not found")
if not event_name in self.event_handlers:
self.event_handlers[event_name] = [getattr(self, event_name), types.MethodType(handler, self)]
if event_name not in self.event_handlers:
self.event_handlers[event_name] = [
getattr(
self, event_name), types.MethodType(
handler, self)]
setattr(self, event_name, partial(self.patch_method, event_name))
else:
self.event_handlers[event_name].append(types.MethodType(handler, self))
@@ -317,7 +322,7 @@ class DailyTransportService(EventHandler):
def on_app_message(self, message, sender):
pass
def on_transcription_message(self, message:dict):
def on_transcription_message(self, message: dict):
if self.loop:
participantId = ""
if "participantId" in message:
@@ -360,7 +365,7 @@ class DailyTransportService(EventHandler):
frames_or_frame: QueueFrame | list[QueueFrame] = self.threadsafe_send_queue.get()
if isinstance(frames_or_frame, QueueFrame):
frames: list[QueueFrame] = [frames_or_frame]
elif isinstance(frames_or_frame, list):
elif isinstance(frames_or_frame, list):
frames: list[QueueFrame] = frames_or_frame
else:
raise Exception("Unknown type in output queue")

7
src/dailyai/services/deepgram_ai_services.py
View File

@@ -7,13 +7,14 @@ import requests
from collections.abc import AsyncGenerator
from dailyai.services.ai_services import TTSService
class DeepgramTTSService(TTSService):
def __init__(self, speech_key=None, voice=None):
super().__init__()
self.voice = voice or os.getenv("DEEPGRAM_VOICE") or "alpha-asteria-en-v2"
self.speech_key = speech_key or os.getenv("DEEPGRAM_API_KEY")
def get_mic_sample_rate(self):
return 24000
@@ -22,8 +23,8 @@ class DeepgramTTSService(TTSService):
base_url = "https://api.beta.deepgram.com/v1/speak"
request_url = f"{base_url}?model={self.voice}&encoding=linear16&container=none&sample_rate=16000"
headers = {"authorization": f"token {self.speech_key}"}
body = { "text": sentence }
body = {"text": sentence}
async with aiohttp.ClientSession() as session:
async with session.post(request_url, headers=headers, json=body) as r:
async for data in r.content:
yield data
yield data

6
src/dailyai/services/fal_ai_services.py
View File

@@ -8,6 +8,8 @@ from PIL import Image
from dailyai.services.ai_services import LLMService, TTSService, ImageGenService
# Fal expects FAL_KEY_ID and FAL_KEY_SECRET to be set in the env
class FalImageGenService(ImageGenService):
def __init__(self, image_size):
super().__init__(image_size)
@@ -18,9 +20,9 @@ class FalImageGenService(ImageGenService):
handler = fal.apps.submit(
"110602490-fast-sdxl",
arguments={
"prompt": sentence
"prompt": sentence
},
)
)
print("past fal handler init, about to wait for iter_events...")
for event in handler.iter_events():
if isinstance(event, fal.apps.InProgress):

3
src/dailyai/services/open_ai_services.py
View File

@@ -49,8 +49,9 @@ class OpenAILLMService(LLMService):
else:
return None
class OpenAIImageGenService(ImageGenService):
def __init__(self, image_size:str, api_key=None, model=None):
def __init__(self, image_size: str, api_key=None, model=None):
super().__init__(image_size=image_size)
api_key = api_key or os.getenv("OPEN_AI_KEY")
self.model = model or os.getenv("OPEN_AI_IMAGE_MODEL") or "dall-e-3"

14
src/dailyai/services/to_be_updated/cloudflare_ai_service.py
View File

@@ -4,6 +4,8 @@ from services.ai_service import AIService
# Note that Cloudflare's AI workers are still in beta.
# https://developers.cloudflare.com/workers-ai/
class CloudflareAIService(AIService):
def __init__(self):
super().__init__()
@@ -19,11 +21,11 @@ class CloudflareAIService(AIService):
return response.json()
# https://developers.cloudflare.com/workers-ai/models/llm/
def run_llm(self, messages, latest_user_message=None, stream = True):
def run_llm(self, messages, latest_user_message=None, stream=True):
input = {
"messages": [
{ "role": "system", "content": "You are a friendly assistant" },
{ "role": "user", "content": sentence }
{"role": "system", "content": "You are a friendly assistant"},
{"role": "user", "content": sentence}
]
}
@@ -57,9 +59,9 @@ class CloudflareAIService(AIService):
# https://developers.cloudflare.com/workers-ai/models/embedding/
def run_embeddings(self, texts, size="medium"):
models = {
"small": "@cf/baai/bge-small-en-v1.5", # 384 output dimensions
"medium": "@cf/baai/bge-base-en-v1.5", # 768 output dimensions
"large": "@cf/baai/bge-large-en-v1.5" #1024 output dimensions
"small": "@cf/baai/bge-small-en-v1.5", # 384 output dimensions
"medium": "@cf/baai/bge-base-en-v1.5", # 768 output dimensions
"large": "@cf/baai/bge-large-en-v1.5" # 1024 output dimensions
}
return self.run(models[size], {"text": texts})

3
src/dailyai/services/to_be_updated/deepgram_ai_service.py
View File

@@ -17,7 +17,8 @@ class DeepgramAIService(AIService):
def run_tts(self, sentence):
self.logger.info(f"Running deepgram tts for {sentence}")
base_url = "https://api.beta.deepgram.com/v1/speak"
voice = os.getenv("DEEPGRAM_VOICE") or "alpha-apollo-en-v1" # move this to an environment variable
# move this to an environment variable
voice = os.getenv("DEEPGRAM_VOICE") or "alpha-apollo-en-v1"
request_url = f"{base_url}?model={voice}&encoding=linear16&container=none"
headers = {"authorization": f"token {self.api_key}"}

16
src/dailyai/services/to_be_updated/google_ai_service.py
View File

@@ -2,9 +2,12 @@ from services.ai_service import AIService
import openai
import os
# To use Google Cloud's AI products, you'll need to install Google Cloud CLI and enable the TTS and in your project: https://cloud.google.com/sdk/docs/install
# To use Google Cloud's AI products, you'll need to install Google Cloud
# CLI and enable the TTS and in your project:
# https://cloud.google.com/sdk/docs/install
from google.cloud import texttospeech
class GoogleAIService(AIService):
def __init__(self):
super().__init__()
@@ -15,11 +18,14 @@ class GoogleAIService(AIService):
)
self.audio_config = texttospeech.AudioConfig(
audio_encoding = texttospeech.AudioEncoding.LINEAR16,
sample_rate_hertz = 16000
audio_encoding=texttospeech.AudioEncoding.LINEAR16,
sample_rate_hertz=16000
)
def run_tts(self, sentence):
synthesis_input = texttospeech.SynthesisInput(text = sentence.strip())
result = self.client.synthesize_speech(input=synthesis_input, voice=self.voice, audio_config=self.audio_config)
synthesis_input = texttospeech.SynthesisInput(text=sentence.strip())
result = self.client.synthesize_speech(
input=synthesis_input,
voice=self.voice,
audio_config=self.audio_config)
return result

14
src/dailyai/services/to_be_updated/huggingface_ai_service.py
View File

@@ -1,7 +1,12 @@
from services.ai_service import AIService
from transformers import pipeline
# These functions are just intended for testing, not production use. If you'd like to use HuggingFace, you should use your own models, or do some research into the specific models that will work best for your use case.
# These functions are just intended for testing, not production use. If
# you'd like to use HuggingFace, you should use your own models, or do
# some research into the specific models that will work best for your use
# case.
class HuggingFaceAIService(AIService):
def __init__(self):
super().__init__()
@@ -10,9 +15,12 @@ class HuggingFaceAIService(AIService):
classifier = pipeline("sentiment-analysis")
return classifier(sentence)
# available models at https://huggingface.co/Helsinki-NLP (**not all models use 2-character language codes**)
# available models at https://huggingface.co/Helsinki-NLP (**not all
# models use 2-character language codes**)
def run_text_translation(self, sentence, source_language, target_language):
translator = pipeline(f"translation", model=f"Helsinki-NLP/opus-mt-{source_language}-{target_language}")
translator = pipeline(
f"translation",
model=f"Helsinki-NLP/opus-mt-{source_language}-{target_language}")
return translator(sentence)[0]["translation_text"]

6
src/dailyai/services/to_be_updated/mock_ai_service.py
View File

@@ -4,6 +4,7 @@ import time
from PIL import Image
from services.ai_service import AIService
class MockAIService(AIService):
def __init__(self):
super().__init__()
@@ -20,8 +21,7 @@ class MockAIService(AIService):
time.sleep(1)
return (image_url, image)
def run_llm(self, messages, latest_user_message=None, stream = True):
def run_llm(self, messages, latest_user_message=None, stream=True):
for i in range(5):
time.sleep(1)
yield({"choices": [{"delta": {"content": f"hello {i}!"}}]})
yield ({"choices": [{"delta": {"content": f"hello {i}!"}}]})

11
src/dailyai/services/to_be_updated/playht_ai_service.py
View File

@@ -8,6 +8,7 @@ from pyht.protos.api_pb2 import Format
from services.ai_service import AIService
class PlayHTAIService(AIService):
def __init__(self, **kwargs):
super().__init__(**kwargs)
@@ -23,8 +24,7 @@ class PlayHTAIService(AIService):
voice="s3://voice-cloning-zero-shot/820da3d2-3a3b-42e7-844d-e68db835a206/sarah/manifest.json",
sample_rate=16000,
quality="higher",
format=Format.FORMAT_WAV
)
format=Format.FORMAT_WAV)
def close(self):
super().close()
@@ -43,14 +43,15 @@ class PlayHTAIService(AIService):
fh = io.BytesIO(b)
fh.seek(36)
(data, size) = struct.unpack('<4sI', fh.read(8))
self.logger.info(f"first attempt: data: {data}, size: {hex(size)}, position: {fh.tell()}")
self.logger.info(
f"first attempt: data: {data}, size: {hex(size)}, position: {fh.tell()}")
while data != b'data':
fh.read(size)
(data, size) = struct.unpack('<4sI', fh.read(8))
self.logger.info(f"subsequent data: {data}, size: {hex(size)}, position: {fh.tell()}, data != data: {data != b'data'}")
self.logger.info(
f"subsequent data: {data}, size: {hex(size)}, position: {fh.tell()}, data != data: {data != b'data'}")
self.logger.info("position: ", fh.tell())
in_header = False
else:
if len(chunk):
yield chunk

3
src/dailyai/tests/test_ai_services.py
View File

@@ -6,10 +6,12 @@ from typing import AsyncGenerator, Generator
from dailyai.services.ai_services import AIService
from dailyai.queue_frame import EndStreamQueueFrame, QueueFrame, TextQueueFrame
class SimpleAIService(AIService):
async def process_frame(self, frame: QueueFrame) -> AsyncGenerator[QueueFrame, None]:
yield frame
class TestBaseAIService(unittest.IsolatedAsyncioTestCase):
async def test_async_input(self):
service = SimpleAIService()
@@ -18,6 +20,7 @@ class TestBaseAIService(unittest.IsolatedAsyncioTestCase):
TextQueueFrame("hello"),
EndStreamQueueFrame()
]
async def iterate_frames() -> AsyncGenerator[QueueFrame, None]:
for frame in input_frames:
yield frame

4
src/samples/deprecated/simple-sample/simple-sample.py
View File

@@ -15,11 +15,12 @@ from dailyai.services.ai_services import AIServiceConfig
from dailyai.services.azure_ai_services import AzureImageGenService, AzureTTSService, AzureLLMService
from dailyai.services.deepgram_ai_services import DeepgramTTSService
def add_bot_to_room(room_url, token, expiration) -> None:
# A simple prompt for a simple sample.
message_handler = MessageHandler(
"""
"""
You are a sample bot in a WebRTC session. You'll receive input as transcriptions of user's
speech, and your responses will be converted to audio via a TTS service.
Answer user's questions and be friendly, and if you can, give some ideas about how someone
@@ -62,6 +63,7 @@ def add_bot_to_room(room_url, token, expiration) -> None:
services.tts.close()
services.llm.close()
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Simple Daily Bot Sample")
parser.add_argument("-u", "--url", type=str, required=True, help="URL of the Daily room")

8
src/samples/deprecated/static-sprite/sprite-sample.py
View File

@@ -20,6 +20,7 @@ from dailyai.message_handler.message_handler import MessageHandler
from dailyai.services.ai_services import AIServiceConfig
from dailyai.services.azure_ai_services import AzureImageGenService, AzureTTSService, AzureLLMService
class StaticSpriteResponse(OrchestratorResponse):
def __init__(
@@ -29,8 +30,8 @@ class StaticSpriteResponse(OrchestratorResponse):
output_queue
) -> None:
super().__init__(services, message_handler, output_queue)
self.image_bytes:bytes | None = None
self.filenames = None # override this in subclasses
self.image_bytes: bytes | None = None
self.filenames = None # override this in subclasses
def start_preparation(self) -> None:
full_path = os.path.join(os.path.dirname(__file__), "sprites/", self.filename)
@@ -82,7 +83,7 @@ def add_bot_to_room(room_url, token, expiration) -> None:
# A simple prompt for a simple sample.
message_handler = MessageHandler(
"""
"""
You are a sample bot in a WebRTC session. You'll receive input as transcriptions of user's
speech, and your responses will be converted to audio via a TTS service.
Answer user's questions and be friendly, and if you can, give some ideas about how someone
@@ -143,6 +144,7 @@ def add_bot_to_room(room_url, token, expiration) -> None:
services.image.close()
services.llm.close()
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Simple Daily Bot Sample")
parser.add_argument("-u", "--url", type=str, required=True, help="URL of the Daily room")

1
src/samples/foundational/01-say-one-thing.py
View File

@@ -4,6 +4,7 @@ import asyncio
from dailyai.services.daily_transport_service import DailyTransportService
from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
async def main(room_url):
# create a transport service object using environment variables for
# the transport service's API key, room url, and any other configuration.

6
src/samples/foundational/01a-greet-user.py
View File

@@ -7,6 +7,7 @@ from dailyai.services.daily_transport_service import DailyTransportService
from dailyai.services.azure_ai_services import AzureTTSService
from dailyai.services.deepgram_ai_services import DeepgramTTSService
async def main(room_url):
# create a transport service object using environment variables for
# the transport service's API key, room url, and any other configuration.
@@ -33,17 +34,20 @@ async def main(room_url):
# Register an event handler so we can play the audio when the participant joins.
print("settting up handler")
@transport.event_handler("on_participant_joined")
async def on_participant_joined(transport, participant):
print(f"participant joined: {participant['info']['userName']}")
if participant["info"]["isLocal"]:
return
audio_generator: AsyncGenerator[bytes, None] = tts.run_tts(f"Hello there, {participant['info']['userName']}!")
audio_generator: AsyncGenerator[bytes, None] = tts.run_tts(
f"Hello there, {participant['info']['userName']}!")
async for audio in audio_generator:
transport.output_queue.put(QueueFrame(FrameType.AUDIO, audio))
print("setting up call state handler")
@transport.event_handler("on_call_state_updated")
async def on_call_joined(transport, state):
print(f"call state callback: {state}")

1
src/samples/foundational/02-llm-say-one-thing.py
View File

@@ -6,6 +6,7 @@ from dailyai.services.daily_transport_service import DailyTransportService
from dailyai.services.azure_ai_services import AzureLLMService
from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
async def main(room_url):
meeting_duration_minutes = 1
transport = DailyTransportService(

6
src/samples/foundational/03-still-frame.py
View File

@@ -8,6 +8,7 @@ from dailyai.services.open_ai_services import OpenAIImageGenService
local_joined = False
participant_joined = False
async def main(room_url):
meeting_duration_minutes = 1
transport = DailyTransportService(
@@ -23,8 +24,9 @@ async def main(room_url):
imagegen = OpenAIImageGenService(image_size="1024x1024")
image_task = asyncio.create_task(
imagegen.run_to_queue(transport.send_queue, [TextQueueFrame("a cat in the style of picasso")])
)
imagegen.run_to_queue(
transport.send_queue, [
TextQueueFrame("a cat in the style of picasso")]))
@transport.event_handler("on_participant_joined")
async def on_participant_joined(transport, participant):

3
src/samples/foundational/04-utterance-and-speech.py
View File

@@ -7,7 +7,8 @@ from dailyai.services.azure_ai_services import AzureLLMService, AzureTTSService
from dailyai.queue_frame import EndStreamQueueFrame, LLMMessagesQueueFrame
from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
async def main(room_url:str):
async def main(room_url: str):
global transport
global llm
global tts

3
src/samples/foundational/05-sync-speech-and-text.py
View File

@@ -7,6 +7,7 @@ from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
from dailyai.services.daily_transport_service import DailyTransportService
from dailyai.services.fal_ai_services import FalImageGenService
async def main(room_url):
meeting_duration_minutes = 5
transport = DailyTransportService(
@@ -98,7 +99,7 @@ async def main(room_url):
await transport.run()
if __name__=="__main__":
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Simple Daily Bot Sample")
parser.add_argument(
"-u", "--url", type=str, required=True, help="URL of the Daily room to join"

3
src/samples/foundational/06-listen-and-respond.py
View File

@@ -8,7 +8,8 @@ from dailyai.services.daily_transport_service import DailyTransportService
from dailyai.services.azure_ai_services import AzureLLMService, AzureTTSService
from dailyai.queue_aggregators import LLMContextAggregator
async def main(room_url:str, token):
async def main(room_url: str, token):
global transport
global llm
global tts

2
src/samples/foundational/07-interruptible.py
View File

@@ -11,7 +11,7 @@ from dailyai.services.azure_ai_services import AzureLLMService
from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
async def main(room_url:str, token):
async def main(room_url: str, token):
global transport
global llm
global tts

9
src/samples/image-gen.py
View File

@@ -11,7 +11,8 @@ from dailyai.queue_frame import QueueFrame, FrameType
from dailyai.services.fal_ai_services import FalImageGenService
from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
async def main(room_url:str, token):
async def main(room_url: str, token):
global transport
global llm
global tts
@@ -32,7 +33,6 @@ async def main(room_url:str, token):
tts = AzureTTSService()
img = FalImageGenService()
async def handle_transcriptions():
print("handle_transcriptions got called")
@@ -41,7 +41,7 @@ async def main(room_url:str, token):
print(f"transcription message: {message}")
if message["session_id"] == transport.my_participant_id:
continue
finder = message["text"].find("start over")
finder = message["text"].find("start over")
print(f"finder: {finder}")
if finder >= 0:
async for audio in tts.run_tts(f"Resetting."):
@@ -69,7 +69,8 @@ async def main(room_url:str, token):
if participant["info"]["isLocal"]:
return
async for audio in tts.run_tts("Describe an image, and I'll create it."):
audio_generator = tts.run_tts(f"Hello, {participant['info']['userName']}! Describe an image and I'll create it. To start over, just say 'start over'.")
audio_generator = tts.run_tts(
f"Hello, {participant['info']['userName']}! Describe an image and I'll create it. To start over, just say 'start over'.")
async for audio in audio_generator:
transport.output_queue.put(QueueFrame(FrameType.AUDIO_FRAME, audio))