1,742
1,740
1,7371,7371,7361,7361,736495495
435431314314
188Apr 17 · 14 min read · Large language models can write code quickly, but they still misremember APIs, miss version-specific details, and forget what they learned at the end of a session. That is the problem Context Hub is t
Join discussion
Apr 15 · 11 min read · Why I Learned About RAG I came across a technique called RAG (Retrieval-Augmented Generation) and was intrigued by how search systems could use this kind of approach. It made me want to build a search
Join discussion
Apr 13 · 11 min read · You've chunked your documents well. You've embedded them with a frontier model. You've stored them in pgvector with a clean HNSW index. Your eval set passes. And then a user searches for ERR_BILL_4042 — your company's specific billing error code — an...
Join discussion
Mar 27 · 7 min read · Here's a surprising fact: iOS apps with AI-powered search see 73% higher user engagement than traditional keyword-based search systems. Yet most iOS developers are still relying on basic Core Data queries and UISearchController when they could be del...
Join discussionMar 25 · 2 min read · At a glance: 4,100+ stars, 300+ forks, TypeScript, MIT license, 9 tools spanning semantic search, code search, company research, and deep research. Free tier: 150 calls/day (hosted) or 1,000/month (API key). Sub-200ms fast search latency. Rating: 4/5...
Join discussionMar 25 · 3 min read · At a glance: nickclyde/duckduckgo-mcp-server — 913 stars, Python, MIT, v0.1.2. 2 tools: search (up to 10 results, regional filtering) and fetch_content (webpage text extraction). No API key, no signup, no cost. Rating: 3.5/5. What It Does ToolDes...
Join discussionMar 20 · 5 min read · Full-text search breaks when users don't know the exact terms. A user searching "how to handle payment failures" won't find your article titled "Dunning Strategy for Involuntary Churn" even though it's exactly what they need. Semantic search fixes th...
Join discussionMar 19 · 11 min read · I noticed it the first time a "simple" search request turned into an argument between three databases. A sales rep asked for "forklifts in Texas with 10,000+ lb capacity under active warranty," and I realized I could answer that question three differ...
Join discussion
Mar 16 · 10 min read · Beyond Embeddings: The Agent-Based Architecture Revolution In Part 1, I explored how embedding-driven search can understand user intent far better than traditional keyword matching. But understanding
Join discussion
