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

getting started on cleanup

Browse Source
This commit is contained in:
Moishe Lettvin
2024-01-25 13:50:10 -05:00
parent f0d9b0613e
commit 6da78dbf9c
2 changed files with 9 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
src/dailyai/services/azure_ai_services.py
View File

@@ -92,25 +92,27 @@ class AzureLLMService(LLMService):
class AzureImageGenServiceREST(ImageGenService): 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, aiohttp_client_session=None):
super().__init__(image_size=image_size) super().__init__(image_size=image_size)
self.api_key = api_key or os.getenv("AZURE_DALLE_KEY") self.api_key = api_key or os.getenv("AZURE_DALLE_KEY")
self.azure_endpoint = azure_endpoint or os.getenv("AZURE_DALLE_ENDPOINT") self.azure_endpoint = azure_endpoint or os.getenv("AZURE_DALLE_ENDPOINT")
self.api_version = api_version or "2023-06-01-preview" self.api_version = api_version or "2023-06-01-preview"
self.model = model or os.getenv("AZURE_DALLE_DEPLOYMENT_ID") self.model = model or os.getenv("AZURE_DALLE_DEPLOYMENT_ID")
self.aiohttp_client_session = aiohttp_client_session or aiohttp.ClientSession()
async def run_image_gen(self, sentence) -> tuple[str, bytes]: async def run_image_gen(self, sentence) -> tuple[str, bytes]:
# TODO hoist the session to app-level # TODO hoist the session to app-level
async with aiohttp.ClientSession() as session: async with self.aiohttp_client_session as session:
url = f"{self.azure_endpoint}openai/images/generations:submit?api-version={self.api_version}" 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 = { body = {
# Enter your prompt text here
"prompt": sentence, "prompt": sentence,
"size": self.image_size, "size": self.image_size,
"n": 1, "n": 1,
} }
async with session.post(url, headers=headers, json=body) as submission: async with self.aiohttp_client_session.post(
url, headers=headers, json=body
) as submission:
operation_location = submission.headers['operation-location'] operation_location = submission.headers['operation-location']
status = "" status = ""
@@ -135,38 +137,3 @@ class AzureImageGenServiceREST(ImageGenService):
image_stream = io.BytesIO(await response.content.read()) image_stream = io.BytesIO(await response.content.read())
image = Image.open(image_stream) image = Image.open(image_stream)
return (image_url, image.tobytes()) return (image_url, image.tobytes())
class AzureImageGenService(ImageGenService):
def __init__(self, api_key=None, azure_endpoint=None, api_version=None, model=None):
super().__init__()
api_key = api_key or os.getenv("AZURE_DALLE_KEY")
azure_endpoint = azure_endpoint or os.getenv("AZURE_DALLE_ENDPOINT")
api_version = api_version or "2023-06-01-preview"
self.model = model or os.getenv("AZURE_DALLE_DEPLOYMENT_ID")
self.client = AzureOpenAI(
api_key=api_key,
azure_endpoint=azure_endpoint,
api_version=api_version,
)
async def run_image_gen(self, sentence) -> tuple[str, bytes]:
self.logger.info("Generating azure image", sentence)
image = self.client.images.generate(
model=self.model,
prompt=sentence,
n=1,
size=self.image_size,
)
url = image["data"][0]["url"]
response = requests.get(url)
dalle_stream = io.BytesIO(response.content)
dalle_im = Image.open(dalle_stream.tobytes())
return (url, dalle_im)

6
src/samples/foundational/05-sync-speech-and-text.py
View File

@@ -2,7 +2,7 @@ import argparse
import asyncio import asyncio
from dailyai.queue_frame import AudioQueueFrame, ImageQueueFrame from dailyai.queue_frame import AudioQueueFrame, ImageQueueFrame
from dailyai.services.azure_ai_services import AzureLLMService from dailyai.services.azure_ai_services import AzureImageGenServiceREST, AzureLLMService
from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
from dailyai.services.daily_transport_service import DailyTransportService from dailyai.services.daily_transport_service import DailyTransportService
from dailyai.services.fal_ai_services import FalImageGenService from dailyai.services.fal_ai_services import FalImageGenService
@@ -22,9 +22,9 @@ async def main(room_url):
transport.camera_height = 1024 transport.camera_height = 1024
llm = AzureLLMService() llm = AzureLLMService()
dalle = FalImageGenService(image_size="1024x1024") #dalle = FalImageGenService(image_size="1024x1024")
tts = ElevenLabsTTSService(voice_id="ErXwobaYiN019PkySvjV") tts = ElevenLabsTTSService(voice_id="ErXwobaYiN019PkySvjV")
# dalle = OpenAIImageGenService(image_size="1024x1024") dalle = AzureImageGenServiceREST(image_size="1024x1024")
# Get a complete audio chunk from the given text. Splitting this into its own # Get a complete audio chunk from the given text. Splitting this into its own
# coroutine lets us ensure proper ordering of the audio chunks on the send queue. # coroutine lets us ensure proper ordering of the audio chunks on the send queue.