The big feature in this release is the option to add speech input (via the browser) and speech output (via Azure speech SDK). See how to enable the new features in the guide here: https://github.com/Azure-Samples/azure-search-openai-demo/blob/main/docs/deploy_features.md#enabling-speech-inputoutput

This release also includes some updates for the chat-with-vision approach.

What's Changed

• Don't set bypass rules for ComputerVision type of Cognitive Services by @pamelafox in https://github.com/Azure-Samples/azure-search-openai-demo/pull/1657
• Update GPT-4 version in readme by @pamelafox in https://github.com/Azure-Samples/azure-search-openai-demo/pull/1663
• Use chat model for query rewriting by @pamelafox in https://github.com/Azure-Samples/azure-search-openai-demo/pull/1659
• Add speech recognizer and synthesis on browser interface by @sowu880 in https://github.com/Azure-Samples/azure-search-openai-demo/pull/113

New Contributors

• @sowu880 made their first contribution in https://github.com/Azure-Samples/azure-search-openai-demo/pull/113

Full Changelog: https://github.com/Azure-Samples/azure-search-openai-demo/compare/2024-05-28...2024-05-29