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

Update to use LLM, STT, TTS subclasses and remove setter methods

Browse Source
This commit is contained in:
Mark Backman
2024-10-01 14:37:07 -04:00
parent 88cca7bf68
commit 28643b453d
19 changed files with 395 additions and 685 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/foundational/07c-interruptible-deepgram.py
View File

@@ -50,7 +50,7 @@ async def main():
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice_id="aura-helios-en")
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")

16
examples/foundational/07e-interruptible-playht.py
View File

@@ -4,11 +4,15 @@
# SPDX-License-Identifier: BSD 2-Clause License
#
import aiohttp
import asyncio
import os
import sys
import aiohttp
from dotenv import load_dotenv
from loguru import logger
from runner import configure
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
@@ -17,17 +21,11 @@ from pipecat.processors.aggregators.llm_response import (
LLMAssistantResponseAggregator,
LLMUserResponseAggregator,
)
from pipecat.services.playht import PlayHTTTSService
from pipecat.services.openai import OpenAILLMService
from pipecat.services.playht import PlayHTTTSService
from pipecat.transports.services.daily import DailyParams, DailyTransport
from pipecat.vad.silero import SileroVADAnalyzer
from runner import configure
from loguru import logger
from dotenv import load_dotenv
load_dotenv(override=True)
logger.remove(0)
@@ -54,7 +52,7 @@ async def main():
tts = PlayHTTTSService(
user_id=os.getenv("PLAYHT_USER_ID"),
api_key=os.getenv("PLAYHT_API_KEY"),
voice_url="s3://voice-cloning-zero-shot/801a663f-efd0-4254-98d0-5c175514c3e8/jennifer/manifest.json",
voice_id="s3://voice-cloning-zero-shot/801a663f-efd0-4254-98d0-5c175514c3e8/jennifer/manifest.json",
)
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")

17
examples/foundational/07g-interruptible-openai-tts.py
View File

@@ -4,11 +4,15 @@
# SPDX-License-Identifier: BSD 2-Clause License
#
import aiohttp
import asyncio
import os
import sys
import aiohttp
from dotenv import load_dotenv
from loguru import logger
from runner import configure
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
@@ -17,17 +21,10 @@ from pipecat.processors.aggregators.llm_response import (
LLMAssistantResponseAggregator,
LLMUserResponseAggregator,
)
from pipecat.services.openai import OpenAITTSService
from pipecat.services.openai import OpenAILLMService
from pipecat.services.openai import OpenAILLMService, OpenAITTSService
from pipecat.transports.services.daily import DailyParams, DailyTransport
from pipecat.vad.silero import SileroVADAnalyzer
from runner import configure
from loguru import logger
from dotenv import load_dotenv
load_dotenv(override=True)
logger.remove(0)
@@ -51,7 +48,7 @@ async def main():
),
)
tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="alloy")
tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice_id="alloy")
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")

14
examples/foundational/16-gpu-container-local-bot.py
View File

@@ -5,10 +5,14 @@
#
import asyncio
import aiohttp
import os
import sys
import aiohttp
from dotenv import load_dotenv
from loguru import logger
from runner import configure
from pipecat.frames.frames import LLMMessagesFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
@@ -26,12 +30,6 @@ from pipecat.transports.services.daily import (
)
from pipecat.vad.silero import SileroVADAnalyzer
from runner import configure
from loguru import logger
from dotenv import load_dotenv
load_dotenv(override=True)
logger.remove(0)
@@ -57,7 +55,7 @@ async def main():
tts = DeepgramTTSService(
aiohttp_session=session,
api_key=os.getenv("DEEPGRAM_API_KEY"),
voice="aura-asteria-en",
voice_id="aura-asteria-en",
base_url="http://0.0.0.0:8080/v1/speak",
)