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

[WIP] Universal (LLM-agnostic) context machinery to support runtime LLM switching.

Browse Source 
- Remove outdated comment
This commit is contained in:
Paul Kompfner
2025-08-14 14:46:53 -04:00
parent 560a6f2247
commit 2eddb6ffda
1 changed files with 0 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/pipecat/processors/aggregators/llm_response_universal.py
View File

@@ -169,11 +169,6 @@ class LLMContextAggregator(FrameProcessor):
self._aggregation = ""
# NOTE: the "universal" suffix is just meant to distinguish this aggregator
# from the old LLMUserContextAggregator while we gradually migrate service to
# use the new universal LLMContext and associated patterns. The suffix will go
# away once the migration is complete and the other LLMUserContextAggregator is
# deprecated.
class LLMUserAggregator(LLMContextAggregator):
"""User LLM aggregator that processes speech-to-text transcriptions.
@@ -511,11 +506,6 @@ class LLMUserAggregator(LLMContextAggregator):
self._emulating_vad = True
# NOTE: the "universal" suffix is just meant to distinguish this aggregator
# from the old LLMAssistantContextAggregator while we gradually migrate service
# to use the new universal LLMContext and associated patterns. The suffix will
# go away once the migration is complete and the other
# LLMAssistantContextAggregator is deprecated.
class LLMAssistantAggregator(LLMContextAggregator):
"""Assistant LLM aggregator that processes bot responses and function calls.