Azure AI Search, a modern retrieval system for AI applications, now has a drastically larger vector capacity—without a price increase. Customers can now run RAG at any scale and at a lower cost: msft.it/6012c0xmQ #AzureAI

Semantic re-ranking with Azure AI Search is coming to LangChain4j !
Just finished my PR at github.com/langchain4j/la… with the great help of Pablo Castro 's team!!
I even added cool integration tests featuring French philosophers: github.com/jdubois/langch…

Azure AI Search support is merged into LangChain4j !!

github.com/langchain4j/la…

This is a first implementation with vector search, we’ll add more advanced features (hybrid retrieval + semantic ranking) soon!

Microsoft Azure AI Search has finally landed into LangChain 🎉

It includes full support for Hybrid search and Semantic reranker, RAG is now easier than ever on Azure with LangChain.js! 🦜🔗
And we'll continue improving it, send us your feedback 🙂

github.com/langchain-ai/l…

Vector search in Azure AI Search is now GA and ready for production workloads. Semantic ranker, to boost RAG applications retrieval quality, is also GA.

btw - Azure Cognitive Search is now Azure AI Search.

techcommunity.microsoft.com/t5/ai-azure-ai…

Refine search results for highest relevance by adding a re-ranking step. Start using semantic ranking, built using state-of-the-art, deep learning re-ranking models. youtu.be/Xwx1DJ0OqCk #VectorSearch Join Jeremy Chapman Pablo Castro for the How, Why & What.

Improve your copilot apps— generate high-quality AI responses based on your organization data.
How to use keyword, vector, and hybrid search methods in Azure Cognitive Search. youtu.be/Xwx1DJ0OqCk #VectorSearch Join Jeremy Chapman Pablo Castro for the How, Why & What.

The best retrieval strategies for generative AI hint: you need more than just vector search from Pablo Castro buff.ly/49gyoP8 #Azure

Refine search results for highest relevance by adding a re-ranking step. Start using semantic ranking, built using state-of-the-art, deep learning re-ranking models. youtu.be/Xwx1DJ0OqCk #VectorSearch Join Jeremy Chapman Pablo Castro for the How, Why & What.

Improve your copilot apps— generate high-quality AI responses based on your organization data.
How to use keyword, vector, and hybrid search methods in Azure Cognitive Search. youtu.be/Xwx1DJ0OqCk #VectorSearch Join Jeremy Chapman Pablo Castro for the How, Why & What.

Had the chance to talk with the Microsoft Mechanics crew about vector search and how to improve retrieval quality for generative AI apps.

techcommunity.microsoft.com/t5/azure-ai-se…

We're seeing lots of generative AI apps that use retrieval-augmented generation: an LLM for reasoning and a vector database for knowledge. Better ranking means better facts fed to the LLM, here's how Azure Cognitive Search can help with that:
techcommunity.microsoft.com/t5/azure-ai-se…

Using LangChain makes it easier to build interesting generative AI scenarios. Langchain has built-in support for Azure Cognitive Search so you can use it as a vector database right out of the box. More in this blog post by Fabrizio and Gia.

techcommunity.microsoft.com/t5/azure-ai-se…

Vector Search in Azure Cognitive Search supports searching using multiple vectors in a single query, against the same or different vector fields.

Latest client libraries now support this :)

Python: pypi.org/project/azure-…
.NET: nuget.org/packages/Azure…

Hear Scott Hanselman 🌮 and Liam Cavanagh talk about the new vector search capability in Azure Cognitive Search in this episode of #AzureFriday . They touch on vector representations for different media types like sentences and images, discuss hybrid search, and show some nice live demos.