1.31.0 (2023-08-21)
Features
- Add disable_retries option to custom jobs. (db518b0)
- LLM - Added support for
stop_sequencesin inference (6f7ea84) - LLM - Exposed the
TextGenerationResponse.raw_prediction_response(f8f2b9c) - LLM - Made tuning asynchronous when tuning becomes GA (226ab8b)
- LLM - release model evaluation for TextGenerationModel to public preview (8df5185)
- LLM - Released
TextGenerationModeltuning to GA (62ff30d) - LLM - Support streaming prediction for chat models (ce60cf7)
- LLM - Support streaming prediction for code chat models (0359f1d)
- LLM - Support streaming prediction for code generation models (3a8348b)
- LLM - Support streaming prediction for text generation models (fb527f3)
- LLM - TextEmbeddingModel - Added support for structural inputs (
TextEmbeddingInput),auto_truncateparameter and resultstatistics(cbf9b6e) - LVM - Added support for Image Generation models (b3729c1)
- LVM - Released
ImageCaptioningModelto GA (7575046) - LVM - Released
ImageQnAModelto GA (fd5cb02) - LVM - Released
MultiModalEmbeddingModelto GA (e99f366) - LVM - Removed the
widthandheightparameters fromImageGenerationModel.generate_imagessince the service has dropped support for image sizes and aspect ratios (52897e6) - Scheduled pipelines client GA. (62b8b23)