Pablo Castro

CVP & Distinguished Engineer @ Microsoft. Working on knowledge systems for AI agents. Generally curious. Opinions are my own.

[Pablo Castro @pmc]

Let the query decide: Introducing "auto", a new retrieval reasoning effort mode in Foundry IQ that recovers 97.6% of the evidence recall of the highest effort level while using 46.9% fewer query planning tokens.

https://t.co/hpCFv0ulmW

[Pablo Castro @pmc]

@pamelafox This is a nice take on this: https://t.co/26Kkr51t3x

[Pablo Castro @pmc]

Autoresearcher: great progress! 1.0 recall, 0ms latency, I just hardcoded your workload.

It if looks like ML, it has the same problems as ML, overfitting is a thing for generated code. Define your tasks and constraints carefully

[Pablo Castro @pmc]

@kzu @Azure Hey! didn't know this was a thing, interesting idea. This is doable today with a bit of code in a custom skill, could be a nice addition to the Azure Search power skills repo https://t.co/Txr6VNigOZ

[LlamaIndex 🦙 @llama_index]

We're proud to announce the availability of an end-to-end LlamaIndex + @Azure solution at #MSIgnite today!

Learn more about our integration with Azure Open AI, Azure AI Embeddings, Azure AI Search and more!

If you're at Microsoft Ignite this week @seldo will be around all week, so feel free to reach out and meet up!

https://t.co/wrqvaUeW09

cc @msPartner

[Microsoft 365 Developer @Microsoft365Dev]

Hear from the leaders behind Microsoft's developer tools (@pmc, @yina_arenas, @jmillerdev, @toddanglin) this Thursday, November 7th at 9:00 AM PT: https://t.co/PEpbtSImKi

#Microsoft365Dev

[Microsoft Azure @Azure]

The new GPT-4o realtime API for audio enables developers to build apps with speech-to-speech interactions. Learn how to build your own VoiceRAG app using the new model here: https://t.co/DZJB1hQMjC

[Azure Weekly @AzureWeekly]

VoiceRAG: An App Pattern for RAG + Voice Using #Azure AI Search and the GPT-4o Realtime API for Audio from @pmc https://t.co/pfPM8lnjR2

[Pamela Fox @pamelafox]

Demo of real-time voice input for a RAG application:
https://t.co/TQNttsXhhd

Code @ https://t.co/VbgIu6P2JJ

[Microsoft Developer @msdev]

To support its massive user base, @OpenAI needed the best technology available; that's where Azure AI Search with Azure Cosmos DB came in.

Together, we’re tackling some of the biggest challenges of today and tomorrow. #MSBuild 💻

[Pablo Castro @pmc]

We had a great conversation with @boazashkenazy in this Shift AI podcast! We covered knowledge and reasoning, retrieval augmented generation, vectors databases, and of course Azure AI Search.

[Boaz Ashkenazy @boazashkenazy]

Excited for you to watch and listen to the latest episode of the Shift AI Podcast with @Microsoft Distnguished Engineer Pablo Castro.

Check out the @geekwire article that landed this morning.

https://t.co/Myn7dJpACO

#ShiftAIPodcast #SimplyAugmented #GeekWire #Microsoft

[LlamaIndex 🦙 @llama_index]

Build hybrid search and sub-question querying with Azure AI Search and LlamaIndex!

In this tutorial, Khye Wei of Microsoft shows you how you can use LlamaIndex with Azure's AI Search to create powerful RAG applications, including
➡️ Hybrid Search
➡️ Query rewriting
➡️ the LlamaIndex SubQuestionQueryEngine

https://t.co/OEKrjrwTby

[Microsoft Azure @Azure]

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: https://t.co/22UGTs4FmY #AzureAI

[Pablo Castro @pmc]

@shibayan It won't right now, it applies to new resources created starting on April 3rd.

[Pablo Castro @pmc]

Now Azure AI Search can handle up to 11x the vector volume as a vector database, offers 3x-6x the storage capacity, and up to twice the performance, with no price changes. Ready for RAG applications at all scales. #Azure #AI #RAG

https://t.co/I4I1KbLl9k

[Julien Dubois @juliendubois]

Semantic re-ranking with Azure AI Search is coming to @langchain4j !
Just finished my PR at https://t.co/GPUzNwycvy with the great help of @pmc 's team!!
I even added cool integration tests featuring French philosophers: https://t.co/JNJmqufwoo

[Julien Dubois @juliendubois]

Azure AI Search support is merged into @langchain4j !!

https://t.co/STEAVteOVK

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

[Yohan Lasorsa @sinedied]

@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 🙂

https://t.co/kRZ2A97ipq

[Pablo Castro @pmc]

Edgar Allan Poe:

"In the deep chasms of time, where shadows linger and fate whispers, a tardy arrival bears the sweetest nectar of hope, far surpassing the hollow echo of never to have ventured at all."

[Pablo Castro @pmc]

"better late than never" is boring, how would Shakespeare would say it, according to GPT-4:

"In tardiness, there’s worth; far worse to never come."

[Pablo Castro @pmc]

Douglas Adams version:

"In the grand, inexplicable clockwork of the universe, where time is an illusion and lunchtime doubly so, arriving late is just the universe's way of saying that, in the grand scheme of things, you're probably early for something else entirely."