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

update CHANGELOG for 0.0.93

Browse Source
This commit is contained in:
Aleix Conchillo Flaqué
2025-11-07 09:38:42 -08:00
parent 0ed430e7e2
commit 4cf9e1409e
1 changed files with 11 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
CHANGELOG.md
View File

@@ -5,11 +5,15 @@ All notable changes to **Pipecat** will be documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
## [Unreleased] ## [0.0.93] - 2025-11-07
### Added ### Added
- Added support for passing in a `ToolsSchem` in lieu of a list of provider- - Added support for Sarvam Speech-to-Text service (`SarvamSTTService`) with
streaming WebSocket support for `saarika` (STT) and `saaras` (STT-translate)
models.
- Added support for passing in a `ToolsSchema` in lieu of a list of provider-
specific dicts when initializing `OpenAIRealtimeLLMService` or when updating specific dicts when initializing `OpenAIRealtimeLLMService` or when updating
it using `LLMUpdateSettingsFrame`. it using `LLMUpdateSettingsFrame`.
@@ -116,6 +120,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
supported languages before Pipecat's service classes are updated, while still supported languages before Pipecat's service classes are updated, while still
providing guidance on verified languages. providing guidance on verified languages.
### Removed
- Removed `needs_mcp_alternate_schema()` from `LLMService`. The mechanism that
relied on it went away.
### Fixed ### Fixed
- Restore backwards compatibility for vision/image features (broken in 0.0.92) - Restore backwards compatibility for vision/image features (broken in 0.0.92)
@@ -139,18 +148,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
- Fixed `GoogleLLMService` token counting to avoid double-counting tokens when - Fixed `GoogleLLMService` token counting to avoid double-counting tokens when
Gemini sends usage metadata across multiple streaming chunks. Gemini sends usage metadata across multiple streaming chunks.
### Removed
- Removed `needs_mcp_alternate_schema()` from `LLMService`. The mechanism that
relied on it went away.
## [0.0.92] - 2025-10-31 🎃 "The Haunted Edition" 👻 ## [0.0.92] - 2025-10-31 🎃 "The Haunted Edition" 👻
### Added ### Added
- Added supprt for Sarvam Speech-to-Text service (`SarvamSTTService`) with streaming WebSocket
support for `saarika` (STT) and `saaras` (STT-translate) models.
- Added a new `DeepgramHttpTTSService`, which delivers a meaningful reduction - Added a new `DeepgramHttpTTSService`, which delivers a meaningful reduction
in latency when compared to the `DeepgramTTSService`. in latency when compared to the `DeepgramTTSService`.