55 stories
When a Weaviate query is slow, the first question is where the time went. Query profiling returns a per-stage, per-shard timing breakdown, making query performance issues visible.
Issue #1 of The State of Serene: what SereneDB is — lakehouse search and analytics for your agents — what it does today, and everything we shipped in June 2026.
Building a code-search system over 14 GB of programming solutions in a data lake — searching Parquet in place, without moving the data.
Microsoft Bing Webmaster Tools introduces four expanded AI performance capabilites in preview: Intents, Topics, Citation Share, and Compare, enhancing publishers' understanding of AI-generated content visibility and citation dynamics.
AI applications are only as good as the information they reason from. Without fresh, high-quality web data, they are less dependable. Today, Microsoft is launching Web IQ: a suite of AI-native grounding APIs built for the agentic era, connecting AI systems and agents to current, real-world…
Why SQL is the right language for Search-OLAP: BM25 scores and vector distances belong in the same query plan as your joins and aggregations.
Today, we’re introducing an evolution of Bing Image Search– a unique AI-guided experience that organizes results to reduce the feeling of being overwhelmed, making it easier to find what you’re looking for.
Keep embeddings next to your data: how SereneDB runs vector similarity and hybrid search and manages embeddings under one index, with no separate vector database to sync.
Tokenization makes or breaks hybrid search. See how Weaviate's accent folding, custom stopwords, and /v1/tokenize endpoint power multilingual BM25.
In an AI-powered search world, visibility is responsibility. Bing is rethinking search with safety by design at its core—combining risk detection, trusted content prioritization, and user controls to ensure that when it matters most, support is more visible than harm.
Three demos run the same SQL — Elasticsearch-grade ranked search plus relational analytics — over remote Parquet, local files and a native SereneDB table, without changing the query.
Search indexing was built to help humans decide what to read. Grounding is being built to help AI systems decide what to say and simultaneously helping people to verify, refine, or challenge what the AI system produces. That is the shift - and it runs deeper than it might first appear.
Elasticsearch shipped in 2012 and the deal was simple: your data lived in Postgres or MySQL; you copied it into Lucene; you got ranked search. The duplication tax was the price of admission.
A Researcher's Perspective on Retrieval Quality in RAG Systems
A batch reranking API powered by Qwen3-Reranker that reorders product documents by semantic relevance to search queries.
Harrier is a new embedding model series designed for the demands of modern AI systems. It is our latest open-source text embedding model series, delivering state-of-the-art performance and ranking 1st on the multilingual MTEB-v2 benchmark.
Here’s a recap of our biggest AI updates from March 2026, including an expansion of Search Live, more ways to access Personal Intelligence and new tools that make it easier to switch to Gemini.
The Microsoft Rewards Total Prize Drop is officially underway, and it’s bringing the biggest rewards yet. For a limited time, Microsoft Rewards members can enter for a chance to win a $1,000,000 USD cash grand prize or one of three customizable Mercedes‑Benz cars.
Showing 54 of 55 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
