Microsoft has revealed a huge increase in storage capacity and vector index size for its Azure AI Search platform that comes with no additional price tag for customers using the AI-augmented search platform.
Users will benefit from an 11x vector index increase, as well as a six-times increase in total storage and double improvement in both indexing and query throughput, the tech giant confirmed.
Microsoft said the move is aimed at providing developers with expanded capabilities to scale generative AI applications by leveraging a “multi-billion vector search”.
The update also allows enterprises to run retrieval augmented generation (RAG) at scale without needing to compromise on the price tag, utilizing “more data per dollar.”
Azure AI search now supports RAG capabilities for ChatGPT, GPTs, and the Assistant API, acting as the retrieval system that ensures the continued functionality of the GPT store.
Microsoft said the size of ChatGPT’s user base signals the possibilities of Azure AI Search when it comes to RAG at scale, with other large-scale companies such as Otto Group and KPMG also reported to be using the platform.
RAG systems are a necessity in generative AI application development
These more advanced instances of RAG systems can be applied in numerous places across the global economy, Microsoft said, with teams in professional services, healthcare, and telecommunications citing the importance of vector search in generative AI.
These groups have discovered that, to build a generative AI application that performs as its designed, “using only one search practice like vector search, simply doesn’t work.”
Higher-quality retrieval systems cover a greater variety of scenarios for application functionalities, the firm noted.
These approaches include hybrid retrieval and semantic reranking, functions that aid developers in achieving their objectives both more effectively and more efficiently.
Get insight into generative AI potential in customer service
Microsoft made note of two companies that are currently showcasing the possibilities created by Azure AI search, Telus Health which is using advanced RAG to deliver a customer care application, and NIQ Brandbank which is optimizing its online presence through multi-vector retrieval.
The team at Telus Health was able to leverage AI search to enhance the platform, expanding its retrieval strategy and implementing hybrid search and semantic reranking to enhance question handling.
NIQ Brandbank takes a different approach to RAG as an enterprise solution, using multi-vector search to comb through research on the backend for use in its Content Health+ platform.
