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

Merge pull request #2387 from pipecat-ai/mb/retry-chat-completion

Browse Source 
Retry chat completions for OpenAILLMService and its subclasses
This commit is contained in:
Mark Backman
2025-08-13 14:39:40 -07:00
committed by GitHub
parent c662a2d820 8714c9137f
commit d7f31e0cbd
8 changed files with 101 additions and 90 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
CHANGELOG.md
View File

@@ -13,6 +13,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
Gemini model can be prompted to insert styled speech to control the TTS
output.
- For `OpenAILLMService` and its subclasses, added the ability to retry
executing a chat completion after a timeout period. The new args are
`retry_timeout_secs` and `retry_on_timeout`. This feature is disabled by
default.
- Added Exotel support to Pipecat's development runner. You can now connect
using the runner with `uv run bot.py -t exotel` and an ngrok connection to
HTTP port 7860.