Using an LLM for query planning in RAG –> 40% better answer relevancetechcommunity.microsoft.com·1 pts·pmc00·0
Nearly 100x Compression for Vector Search with Minimal Quality Losstechcommunity.microsoft.com·3 pts·pmc00·0
VoiceRAG: A pattern for RAG and voice with the GPT-4o Realtime API for audiotechcommunity.microsoft.com·11 pts·pmc00·0
Up to 11x vector database capacity increase in Azure AI Search, no price changeazure.microsoft.com·1 pts·pmc00·1
Vector search and state of the art retrieval for Generative AI (Ignite talk) [video]ignite.microsoft.com·1 pts·pmc00·0
Vector search and hybrid retrieval, intro and evaluations on Azure Searchtechcommunity.microsoft.com·2 pts·pmc00·0
Outperforming vector search with hybrid retrieval and rankingtechcommunity.microsoft.com·3 pts·pmc00·0
A simple intro to how to create ChatGPT-like apps with your own data in Azureyoutube.com·1 pts·pmc00·0
Got ChatGPT to run (interpret? guess?) x86 assembly for the Fibonacci sequencetwitter.com·1 pts·pmc00·0
Show HN: Life is Short – Game of Life in 203 chars of HTML/JavaScriptshorterlife.github.io·10 pts·pmc00·0