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

Progress on updating foundational examples to avoid using the newly-deprecated LLMMessagesFrame.

Browse Source 
Skipping over 07b-interruptible-langchain.py for now, as it requires deeper changes involving `LLMUserResponseAggregator` and `LLMAssistantResponseAggregator`.
This commit is contained in:
Paul Kompfner
2025-08-06 12:03:40 -04:00
parent 64e48e4660
commit f0391c3280
7 changed files with 47 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/foundational/05a-local-sync-speech-and-image.py
View File

@@ -15,7 +15,6 @@ from loguru import logger
from pipecat.frames.frames import (
Frame,
LLMMessagesFrame,
OutputAudioRawFrame,
TextFrame,
TTSAudioRawFrame,
@@ -25,6 +24,10 @@ from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.sync_parallel_pipeline import SyncParallelPipeline
from pipecat.pipeline.task import PipelineTask
from pipecat.processors.aggregators.openai_llm_context import (
OpenAILLMContext,
OpenAILLMContextFrame,
)
from pipecat.processors.aggregators.sentence import SentenceAggregator
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.services.cartesia.tts import CartesiaHttpTTSService
@@ -137,7 +140,7 @@ async def main():
)
task = PipelineTask(pipeline)
await task.queue_frame(LLMMessagesFrame(messages))
await task.queue_frame(OpenAILLMContextFrame(OpenAILLMContext(messages)))
await task.stop_when_done()
await runner.run(task)