From 5d5041eb2b4ba5963a20becacc641b8042f84655 Mon Sep 17 00:00:00 2001 From: Mark Backman Date: Sat, 29 Mar 2025 18:45:39 -0400 Subject: [PATCH] Renumber mem0 example, small changelog updates --- CHANGELOG.md | 12 ++++++++++-- examples/foundational/{35-mem0.py => 37-mem0.py} | 0 2 files changed, 10 insertions(+), 2 deletions(-) rename examples/foundational/{35-mem0.py => 37-mem0.py} (100%) diff --git a/CHANGELOG.md b/CHANGELOG.md index 1f524917b..dc0cdb47c 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -12,9 +12,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - Added `Mem0MemoryService`. Mem0 is a self-improving memory layer for LLM applications. Learn more at: https://mem0.ai/. -- Added `WhisperSTTServiceMLX` for whisper transcription on Apple Silicon. +- Added `WhisperSTTServiceMLX` for Whisper transcription on Apple Silicon. See example in `examples/foundational/13e-whisper-mlx.py`. Latency of - completed transcription using whisper large-v3-turbo on an M4 macbook is + completed transcription using Whisper large-v3-turbo on an M4 macbook is ~500ms. - Added `SmallWebRTCTransport`, a new P2P WebRTC transport. @@ -52,6 +52,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - Fixed an issue where `GoogleTTSService` was emitting two `TTSStoppedFrames`. +### Other + +- Added foundational example `37-mem0.py` demonstrating how to use the + `Mem0MemoryService`. + +- Added foundational example `13e-whisper-mlx.py` demonstrating how to use the + `WhisperSTTServiceMLX`. + ## [0.0.61] - 2025-03-26 ### Added diff --git a/examples/foundational/35-mem0.py b/examples/foundational/37-mem0.py similarity index 100% rename from examples/foundational/35-mem0.py rename to examples/foundational/37-mem0.py