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

Merge pull request #4270 from sathwikareddy02/nvidia-llm-update

Browse Source 
Enhance NVIDIA LLM reasoning tokens handling and allow keyless local …
This commit is contained in:
Filipi da Silva Fuchter
2026-04-22 10:47:54 -03:00
committed by GitHub
parent f425e946eb 91e5b1ad9a
commit 7858813871
2 changed files with 240 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
changelog/4270.changed.md Normal file
View File

@@ -0,0 +1 @@
- Updated `NvidiaLLMService` to emit model reasoning as `LLMThought*Frame`s (from both `reasoning_content` and `<think>...</think>` output), avoid mixing reasoning text into normal assistant content, and allow keyless local NIM endpoints while warning when the cloud endpoint is used without an API key.