Three options now obtainable in preview allow you to take pleasure in simplified administration of the client-managed key (CMK) encrypted workspace, benefit from our content material filtering system alongside fashions that you would be able to entry by Models as a Service, and usher in indexes from Cosmos DB for MongoDB vCore and Pinecone for use in RAG workflows. Service-side encryption of metadata (Simplified CMK structure): You can now benefit from the client-managed key-encryption workspace’s new structure, which is able to finally scale back prices and restrict the chance of working into Azure coverage conflicts. Protect your self and your customers from doubtlessly dangerous content material: You can now guard in opposition to doubtlessly dangerous content material for you and your customers, and make the most of the flexibleness to show content material filtering on or off primarily based on the wants of your online business. Use RAG patterns throughout a number of knowledge sources in AzureML & AI Studio: You will quickly be capable to convey your personal indexes with out having to create them from scratch, permitting you to fulfill prospects the place knowledge is already obtainable and supplying you with the flexibleness to make use of extra index sorts.
https://azure.microsoft.com/pt-br/updates/azure-machine-learning-public-preview-for-build-2024/
