Hacker News with Generative AI: Search

Knowledge Library MCP (devpost.com)
Knowledge Library MCP (KL MCP) is a multi-modal application leveraging Azure AI Agent Service to locate documents—text and images—and deliver conversational insights via bots. It enhances search with live data integration and Responsible AI principles, designed for scalable, professional-grade querying.
Show HN: Search and chat with millions of court cases using AI. (courtsearch.ai)
Improving recommendation systems and search in the age of LLMs (eugeneyan.com)
Recommendation systems and search have historically drawn inspiration from language modeling. For example, the adoption of Word2vec to learn item embeddings (for embedding-based retrieval), and using GRUs, Transformer, and BERT to predict the next best item (for ranking). The current paradigm of large language models is no different.
Show HN: I converted my notebook into a searchable database of IT keywords (techbook.digital)
Google gets 373x more searches every day than ChatGPT (sparktoro.com)
For years, two questions have dominated both marketers’ interest and the media’s coverage of Google Search:
Long Read: Lessons from Building Semantic Search for GitHub and Why I Failed (notion.site)
Optimizing for Multiple Objectives in Search and Recommendations (shaped.ai)
Building effective recommendation and search systems means going beyond simply predicting relevance. Modern users expect personalized experiences that cater to a wide range of needs and preferences, and businesses need systems that align with their overarching goals. This requires optimizing for multiple objectives simultaneously – a complex challenge that demands a nuanced approach. This post explores the concept of value modeling and multi-objective optimization (MOO), explaining how these techniques enable the development of more sophisticated and valuable recommendation and search experiences.
BM25 in PostgreSQL (vectorchord.ai)
We’re excited to share something special with you: VectorChord-BM25, a new extension designed to make PostgreSQL’s full-text search even better. Whether you’re building a small app or managing a large-scale system, this tool brings advanced BM25 scoring and ranking right into PostgreSQL, making your searches smarter and faster.
Chrome has built-in AI history search (support.google.com)
You can use everyday language to find and receive generated answers about what you’re searching for in your Chrome browsing history. This works even if you don't know an exact keyword or website address.
Show HN: PG-Capture – a better way to sync Postgres with Algolia (or Elastic) (onrender.com)
Schema-based Change-Data-Capture for Postgres
Google is making it even easier to remove your personal information on Search (engadget.com)
Google has been offering the Results About You tool since 2022 and updated it once in 2023.
VectorChord-BM25: PostgreSQL Search with BM25 – 3x Faster Than Elasticsearch (vectorchord.ai)
We’re excited to share something special with you: VectorChord-BM25, a new extension designed to make PostgreSQL’s full-text search even better. Whether you’re building a small app or managing a large-scale system, this tool brings advanced BM25 scoring and ranking right into PostgreSQL, making your searches smarter and faster.
Just Write (chasingbrains.co)
A blog post is a very long and complex search query to find fascinating people and make them route interesting stuff to your inbox.
(Ab)using general search algorithms on dynamic optimization problems (2023) (dubovik.eu)
In retrospect, my most ambitious blog yet. As it goes, I was reading “Artificial Intelligence. A Modern Approach” the other day. In one of the earlier chapters the authors discuss general search algorithms: breadth-first search, depth-first search, uniform-cost search (Dijkstra), and variations of those. A bit later they also cover Monte Carlo tree search as a way of finding approximate solutions in big state spaces.
Show HN: A GPU-accelerated binary vector index (rlafuente.com)
Solving Postgres' Search Limitations (paradedb.com)
We recently completed one of our biggest engineering bets to date: migrating pg_search, a Postgres extension for full text search and analytics, to Postgres' block storage system. In doing so, pg_search is the first-ever extension1 to port an external file format to Postgres block storage.
Open-source DeepResearch – Freeing our search agents (huggingface.co)
Yesterday, OpenAI released Deep Research, a system that browses the web to summarize content and answer questions based on the summary.
DeepSeek models are available now in Cursor (twitter.com)
Perplexity launches Sonar, an API for AI search (techcrunch.com)
Perplexity on Tuesday launched an API service called Sonar, allowing enterprises and developers to build the startup’s generative AI search tools into their own applications.
Using the most unhinged AVX-512 instruction to make fastest phrase search algo (gab-menezes.github.io)
Do you know when you go to your favorite search engine and search for something using double quotes, like a passage of a book/article or something very specific? That’s called phrase search (sometimes exact search). What we are telling the search engine is that we want these exact words in this exact order (this varies from search engine to search engine, but that’s the main idea).
Making the fastest phrase search algo with the most unhinged AVX512 instruction (gab-menezes.github.io)
For those who don’t want to read/don’t care that much, here are the results. I hope after seeing them you are compelled to read. TL;DR: I wrote a super fast phrase search algorithm using AVX-512 and achieved wins up to 1600x the performance of Meilisearch.
GitHub introduces sub-issues, issue types and advanced search (github.blog)
Following our opt-in preview last year, we are excited to release sub-issues, issue types and advanced search for issues to everyone! 🎉
Working with The Associated Press to provide fresh results for the Gemini app (google)
The AP will now deliver a feed of real-time information to help enhance the usefulness of results displayed in the Gemini app.
In a cold day of late winter a new search experience came out (lexy.uno)
What can I help you find?
Magna: Embedding similarity search tool for searching within large documents (github.com/yousef-rafat)
Magna is an AI-powered embedding similarity search tool for searching within large documents.
Show HN: Podcast API (listennotes.com)
The Best Podcast API for Search, Directory, and Insights
Hoarder: Self-hostable bookmark-everything app (github.com/hoarder-app)
A self-hostable bookmark-everything app (links, notes and images) with AI-based automatic tagging and full text search
Is ChatGPT Good at Search? (openread.academy)
Large Language Models (LLMs) have demonstrated a remarkable ability to generalize zero-shot to various language-related tasks.
Kagi Teams (kagi.com)
To satisfy the growing demand for our services in work environments, we are launching Kagi for Teams - bringing our unmatched quality, privacy-focused search and AI tools to businesses worldwide.
Cascading retrieval: Unifying dense and sparse vector embeddings with reranking (pinecone.io)
We're excited to announce new cascading retrieval capabilities, further advancing AI search applications. These enhancements make it seamless to combine dense retrieval, sparse retrieval, and reranking into a unified search pipeline, delivering unparalleled precision, performance, and ease of use. With these updates, Pinecone solidifies its position as the most comprehensive platform for modern AI retrieval.