Starstruk Logo MarkStarstruk

v0.0.21

pipecat-ai/pipecatv0.0.21May 23, 2024by aconchillo

AI Summary

This release adds vision capabilities to Anthropic, introduces a wake word filter, and refactors internal filtering logic while fixing several audio processing and aggregation bugs.

Key Highlights

  • Added vision support to the Anthropic service
  • Introduced `WakeCheckFilter` for detecting specific wake words
  • Renamed `Filter` to `FrameFilter` and moved it to `processors/filters`
  • Fixed audio aggregation issues and added buffer clearing on interruption

Breaking Changes

  • Renamed `Filter` to `FrameFilter` and moved it to `processors/filters`

New Features

  • Anthropic vision support
  • WakeCheckFilter

Full Release Notes

### Added

- Added vision support to Anthropic service.

- Added `WakeCheckFilter` which allows you to pass information downstream only if you say a certain phrase/word.

### Changed

- `Filter` has been renamed to `FrameFilter` and it's now under `processors/filters`.

### Fixed

- Fixed Anthropic service to use new frame types.

- Fixed an issue in `LLMUserResponseAggregator` and `UserResponseAggregator` that would cause frames after a brief pause to not be pushed to the LLM.

- Clear the audio output buffer if we are interrupted.

- Re-add exponential smoothing after volume calculation. This makes sure the volume value being used doesn't fluctuate so much.