Subject
25 entries
Search
Bookmarks
msgvault: personal email archive and search with DuckDB and MCP
msgvault is Wes McKinney's private email archive system — lightning-fast search over personal email with a terminal UI and MCP server, all powered by DuckDB. Local-first, no cloud, built by the creator of pandas.
ithy — Multi-LLM Research Aggregator
ithy is an AI research platform that queries multiple LLMs simultaneously and synthesizes their responses into a single interactive article. The positioning is that combining ChatGPT, Gemini, and Claude produces better answers than any one alone.
Superlinked
Superlinked is a framework for data engineers to build vector embeddings from structured data with control over how different attributes are weighted and combined. Addresses the gap between raw ML embedding models and production multi-attribute vector search.
Danswer: Natural Language Q&A Over Private Sources
Danswer (now Onyx) is an open-source enterprise Q&A system that connects to Slack, GitHub, Confluence, and other internal tools to answer natural language questions over private knowledge. Self-hosted with strong access-control enforcement — a production-ready alternative to building RAG from scratch.
Twelve Labs — Video Understanding API
Twelve Labs provides a video understanding API that lets developers search, retrieve, and understand video content semantically — as if the model could actually watch and comprehend it. Fills the gap between text search and the dense information in video.
Obsidian Omnisearch
Omnisearch is an Obsidian plugin that replaces the native search with full-text search that 'just works' — ranking results intelligently based on match quality, note size, and recency. Solves Obsidian's long-standing weak native search with BM25-style relevance scoring.
Vectors Are Over? Hashes as the Future of AI Search
Algolia's provocative post arguing that hash-based retrieval outperforms vector search for many real-world search use cases — a counterargument to the vector database hype of 2022. Grounds the comparison in production search quality metrics.
LambdaMART In Depth
An in-depth technical explainer on LambdaMART — the gradient boosted tree algorithm for learning-to-rank that underlies most production search and recommendation systems. Explains lambda values, pairwise swapping, and DCG optimization in a way that builds genuine intuition.
Indexing 1,600,000,000 Keys with Automata and Rust
Andrew Gallant's deep technical post on using finite state transducers to index 1.6 billion keys in a compact data structure — the basis for ripgrep and the fst crate. A masterclass in how the right data structure unlocks orders-of-magnitude improvements.
Internet Search Tips
Gwern Branwen's guide to effective internet search — covering advanced operators, specialized databases, tracking down primary sources, and the general epistemics of knowing when you've actually found what you're looking for. One of the most useful practical research guides online.
Powering Search and Recommendations at DoorDash
DoorDash's engineering blog post on their search and recommendation systems — covering how they rank restaurants and dishes, handle cold-start problems, and personalize results. A practical look at production recommendation systems at a major food delivery platform.
Running Elasticsearch: Fun & Profit
A free online book on running Elasticsearch in production — cluster sizing, index design, mapping, query optimization, and operational concerns like snapshots and upgrades. Practitioner-focused with real-world configuration guidance rather than API documentation.
Using Machine Learning to Rank Search Results (Part 2)
A practical tutorial on applying machine learning to re-rank search results — part 2 of a series covering feature engineering, training data construction, and evaluation for LTR in production search. Hands-on complement to the more theoretical LTR literature.
Test Driving Elasticsearch Learning to Rank with a Linear Model
OpenSource Connections' hands-on tutorial for the Elasticsearch Learning to Rank plugin with a linear model — walks through feature logging, model training, and deployment. The entry point for adding ML-powered ranking to an existing Elasticsearch stack.
Solr-LTR: From Zero to Learning to Rank in Apache Solr
A practical guide and reference implementation for setting up learning-to-rank in Apache Solr from scratch — covers the Solr LTR plugin, feature extraction, model training, and deployment. Complement to the Elasticsearch LTR tutorials for Solr shops.
LTR with Bees: Learning to Rank in Apache Solr
Christine Poerschke's tutorial using a bee-related dataset to demonstrate learning-to-rank in Apache Solr — end-to-end example from feature extraction through model training to serving. Concrete and dataset-grounded, unlike most abstract LTR tutorials.
Learning to Rank with Vespa
Thiago Martins' tutorial on learning-to-rank with Vespa for text search — covers how Vespa's native ML integration makes LTR simpler than Elasticsearch/Solr plugins, with models evaluated inside the search engine. Vespa's approach to embedding LTR natively.
Learning to Rank for Personalised Search (Yandex Kaggle Competition)
Yanir Seroussi's Kaggle competition post-mortem on Yandex Search Personalisation — applying learning-to-rank techniques to personalized search with behavioral signals. A practical case study of LTR on real search logs.
Learning to Rank 101: Linear Models
OpenSource Connections' foundational explainer on linear models for learning-to-rank — the first step before gradient boosted trees. Covers feature engineering and the intuition for why linear LTR models are both a useful starting point and a useful baseline.
Is Your Infrastructure Ready for Learning to Rank?
OpenSource Connections' guide to the infrastructure required before you can deploy learning-to-rank — covering the judgment lists, feature logging pipelines, training data management, and model versioning that most LTR tutorials skip. The operational reality of LTR in production.
Intuitive Explanation of Learning to Rank: RankNet, LambdaRank, and LambdaMART
Nikhil Dandekar's intuitive explainer on the evolution from pointwise to pairwise to listwise learning-to-rank, covering RankNet, LambdaRank, and LambdaMART. One of the best conceptual introductions to how modern search ranking algorithms actually work.
Introduction to Personalized Search
Recombee's introduction to personalized search — connecting the recommendation systems world to search, covering how behavioral signals (clicks, purchases) can be used to personalize result ranking per user. Bridges the gap between generic LTR and user-specific personalization.
How Airbnb Used Conditional Probability Models to Improve Search
How Airbnb used conditional probability models and data visualization to improve search ranking — an early public example of a major consumer company describing ML-driven search personalization. Significant for its transparency about the modeling approach.
Not Just for Search: Using ElasticSearch with Machine Learning Algorithms
An early (2013) case for using Elasticsearch beyond full-text search — specifically as a substrate for machine learning applications like nearest-neighbor lookup and feature indexing. Pre-dates the vector search era but anticipates the same pattern.
Deploying ElasticSearch with Chef Solo
An early 2012 tutorial for deploying Elasticsearch using Chef Solo — a document from when both Elasticsearch and infrastructure-as-code were early in their mainstream adoption curves. Shows the 2012 devops toolchain before Ansible and Terraform emerged.