Tag: vector-search
Browse 4 practical software engineering resources tagged with "vector-search". Discover code recipes, design patterns, documentation templates, and in-depth guides to help you build, deploy, and maintain production-ready solutions involving vector-search. Each resource is written for engineers who ship real systems, with copy-paste examples and practical trade-offs.
Vector Search
Vector search finds items based on semantic similarity. It uses embeddings and is the basis of modern RAG and recommendation systems.
The resources below cover embeddings, vector databases, similarity metrics, and indexing. Each guide helps you implement semantic search.
Every resource includes clear explanations, copy-paste code, and practical warnings. Use them to make informed decisions, avoid production pitfalls, and speed up your delivery. If you are just getting started, read the beginner-friendly articles first; if you are experienced, jump straight to the advanced patterns and architecture guides. New resources are added regularly, so bookmark this page and check back for the latest patterns.
Build Semantic Search with Embeddings in Python, JS, Java
Build a semantic search engine with text embeddings and vector similarity. Includes Python,...
Embedding Cache Pattern
Cache LLM embeddings to reduce API calls and cost. Store embeddings with a content hash key and...
RAG Hybrid Search Pattern
Combine keyword (BM25) and semantic (vector) search to improve retrieval accuracy in RAG pipelines....
Complete Guide to RAG in Production
Build production RAG systems. Covers chunking strategies, embedding models, vector stores,...