AI-powered semantic documentation search? 🔥 It feels like chatting... with the website, rather than searching through it. A combination of keyword-based search and semantic search is definitely going to be the future!show more

I’ve been building an AI-powered document reader. First feature... is fast semantic search over any PDF (even entire books!) You can ask an abstract question and get direct quotes that answer it.show more

iMessage search is still broken in 2025. So I... fixed it myself. It doesn't even work most of the time. When it does, it's slow, misses messages constantly, and only matches exact words. Search "dinner" and you won't find "let's grab food." iMessage Intelligence fixes all of this while also being insanely fast. Here's how it works: → Full text search index on your messages for keyword matching → On-device ML (MiniLM via CoreML) generates semantic embeddings. Your Mac generates these embeddings in under a minute, then syncs to your phone → sqlite-vec stores vectors locally for similarity search → Hybrid results: keyword hits appear in <10ms, semantic matches merge in <60ms It also has advanced filters iMessage doesn't have: sort options, date ranges, conversation filters, sent vs received, groups vs 1-on-1. Search runs 100% on-device. No cloud processing. Sign up for the waitlist:show more

i built an app to search old travel photos... on my computer with natural language queries using free local AI models: - smolVLM to describe the scene and colours - roboflow RF-DETR to detect objects - chromaDB to store metadata labels and run semantic search - python + streamlit for the interface fast and free search has been achieved internallyshow more

You can now generate public endpoints, UI snippets, and... a MCP server with AI Search: making it easy to add search to your website or connect AI agents.show more

owning that new lewk is as easy as circling... it with AI-powered Circle to Search.show more

owning that new lewk is as easy as circling... it with AI-powered Circle to Search.show more

The AI Watching Series Episode 4: Finance Wall Street,... Simplified. Rocket watches finance videos. To save you time. Looking for the latest market insights? Don't spend hours searching through earnings calls, macro analysis, interviews, and investment videos trying to find the one answer you're looking for. Let Rocket do the research first. Ask questions like: → Why is Bitcoin moving today? → What are analysts saying about NVIDIA? → Find every mention of rate cuts. → Bull vs. bear case for Tesla. → Best long-term investing strategies. Instead of searching through thousands of finance videos… Search the moments that matter. Powered by UpRock Video Semantic Search (VSS). What should Rocket research next? 👇show more

The AI Watching Series Episode 3: Food Yes, Chef!... AI watches cooking videos. So you don't have to. Looking for your next favorite meal? Don't spend hours skipping through recipe videos searching for that one technique or ingredient. Let AI do the research for you. Ask questions like: → Best smash burger recipe → Authentic carbonara without cream → Crispiest air fryer chicken wings → Perfect medium-rare steak every time Instead of watching hundreds of cooking videos... Search the moments that matter. Powered by UpRock Video Semantic Search (VSS). What should Rocket cook next? 👇show more

With SGE, our new generative AI experience in Search,... you’ll get even more from a single search. With this Search Labs experiment, you’ll be able to quickly get a lay of the land on a topic, with an AI-powered overview and conversational ways to ask follow-up questions. Available in ➡️ English & Hindi Learn more:show more

Google Scholar, Semantic Scholar, PubMed, and Scite — four... different databases. Research Kick Chat combines them all to give you an AI-powered super search engine for research. Here's how to fast-track your literature discovery with Research Kick Chat:show more

AI agents can already read the web. Now we're... giving them eyes. Introducing Semantic Video Search, powered by the UpRock Network. Not transcript search. Not keyword matching. Real multimodal intelligence across: → video → audio → frames → timestamps → context Ask questions. Get answers from video. Powered by a global swarm of 3M+ real devices across 190+ countries, UpRock gives AI agents access to the internet as real users experience it. No datacenter blocks. No proxy games. No synthetic traffic. Just ground-truth intelligence from the real web. Over the next few posts, we'll show what this unlocks. 👇show more

Launching today: the Search Generative Experience (SGE) - available... as an experiment in Search Labs. Supercharge your search by getting: 📖 a gist of a topic with AI-powered overviews 🔎 pointers to explore more and natural ways to ask follow ups Try the experiment here:show more

Big moment for Postgres! Search has always been Postgres'... weak spot, and everyone just accepted it. If you needed a real relevance-ranked keyword search, the default answer was to spin up Elasticsearch or add Algolia and deal with the data sync headaches forever. The problem isn't that Postgres can't do text search. It can. But the built-in `ts_rank` function uses a basic term frequency algorithm that doesn't come close to what modern search engines deliver. So teams end up: - Running a separate Elasticsearch cluster just for search - Building sync pipelines that inevitably drift out of consistency - Paying for managed search services that charge per query - Accepting mediocre search relevance because "good enough" ships faster But this is actually a solvable problem. You can realistically bring industry-standard search ranking directly into Postgres, which eliminates the need for external infra entirely. This exact solution is now available with the newly open-sourced pg_textsearch by Tiger Data - Creators of TimescaleDB, a Postgres extension that brings true BM25 relevance ranking into the database. BM25 is the algorithm behind Elasticsearch, Lucene, and most modern search engines. Now it runs natively in Postgres. Here's what pg_textsearch enables: - True BM25 ranking with configurable parameters (the same algorithm powering production search systems) - Simple SQL syntax: `ORDER BY content 'search terms'` - Works with Postgres text search configurations for multiple languages - Pairs naturally with pgvector for hybrid keyword + semantic search That last point matters a lot for RAG apps. The video below shows this in action, and I worked with the team to put this together. You can now do hybrid retrieval (combining keyword matching with vector similarity) in a single database, without stitching together multiple systems. The syntax is clean enough that you can add relevance-ranked search to existing queries in minutes. pg_textsearch is fully open-source under the PostgreSQL license. You can find a link to their GitHub repo in the next tweet.show more

Speaking of truly independent alternatives to Google Search, Brave... Search is an excellent privacy-focused, no tracking search engine with its own independent index, community driven ranking options, AI-powered answers, and integrated chatbot ✨show more

We've made it easier to search specific sites through... Brave Search! Brave Search now includes search bangs in its suggestions so you can quickly find these shortcuts. You can also browse the full list of 12,000+ bangs supported on Brave Search here:show more

Finding places to explore is easier than ever with... the new search feature. 🔎🗺️ Search for a place or event, and jump in!show more