Do Not Refresh Declining Content Until You Diagnose the Loss
Do Not Refresh Declining Content Until You Diagnose the Loss A page loses clicks. The instinctive response is to update the introduction, add a few…
Architecture
⚑ Сообщить о проблемеПоследние новости Architecture от Tech News
Все темы
agents
ai
api
architecture
automation
aws
backend
beginners
career
database
devchallenge
devops
javascript
llm
machinelearning
mcp
news
opensource
performance
productivity
programming
python
react
security
showdev
softwareengineering
systemdesign
tutorial
typescript
webdev
How to Build Retrieval Architecture for a Multi-Tenant SaaS Help Center (with Pagination)
Short answer: for retrieval architecture in a multi-tenant SaaS help center, use staged retrieval with explicit collections, bounded queries, and so…
Candidate Search Architecture: Tenant-Bounded Retrieval and Source Traceability
Recruiting search has an awkward constraint: a highly relevant profile is still a security incident if it came from the wrong customer. Short answer…
pgvector, Qdrant или Milvus: как выбрать базу для RAG и не усложнить архитектуру
На демо все выглядит безобидно: загружаем документы, строим эмбеддинги, подключаем векторный поиск — и RAG уже отвечает на вопросы. А потом поиск то…
Introducing PageIndex: A Vectorless RAG Solution for dev.to
Source: https://pageindex.ai/blog/pageindex-flash Introducing PageIndex: A Vectorless RAG Solution for dev.to Short Intro Retrieval‑Augmented Genera…
From Click Logs to Search Ranking: Building an Offline Popularity Trainer with Python and Typesense
Most learning-to-rank examples end when the model has been trained. A production search system still has several harder questions to answer: Which u…
Similarity isn't relevance: the hard part of semantic search
Here's a dirty secret of search: "the closest match" and "the most useful result" are not the same thing. Return the mathematically nearest document…
[EN] Data Driven/Big Data Series #1: Apache Kafka and Elastic Stack Roles
This is the first in a series exploring the roles of Search and Streaming technologies within the Data Driven (Big Data) environment. In this post,…
I measured the RAG technique menu on 46,000 chunks. Four things mattered.
Search "advanced RAG techniques" and you'll get a list of twenty things: hybrid search, reranking, HyDE, query decomposition, contextual retrieval,…
Semantic Search Embeddings vs Keyword Search for a SaaS Help Center
Bottom line: for a beginner ask-your-docs feature in a SaaS help center, I would start with embeddings-based semantic retrieval over document chunks…
Four Vectors, One Record: How I Split Embeddings Before They Hit Search
The failure that pushed me into this design was not subtle. I had a blended embedding that kept returning candidate matches that looked reasonable a…
RocheDB: Data Locality as a First-Stage Retrieval Index
One of the ideas behind RocheDB is easy to miss if we describe it only as a NoSQL database, a document store, or a vector-aware storage engine for A…
Give Your AI Assistant a Private Memory
AI assistants are very good at explaining things, but they usually have a weak memory of your own context. They do not know which documentation page…
The Hybrid Retrieval Pattern
Pattern Defined Precise Definition: Hybrid Retrieval is an inference pattern that combines semantic vector search with traditional keyword-based BM2…
Vector Search in Elasticsearch: From Keywords to Meaning - Building Semantic Search and RAG Pipelines
You type "k8s deployment troubleshooting" into your documentation search. The top result is a page about Kubernetes architecture that never mentions…
Building Hybrid Search with PostgreSQL, pgvector, and Citus
Search looks simple from the outside. A user types something like: short-range copper module and expects the system to return the right product, may…
From Elasticsearch Bottlenecks to Weaviate: How We Built Fast Hybrid Search in Production
For years, Elasticsearch was one of those tools I would almost automatically reach for whenever a system needed search. And honestly, for many use c…
One Question, Five AI Search Engines, Five Different Answers
I asked five AI search engines the same question: "What's the best CI/CD tool for a small team?" Google AI Overviews recommended GitHub Actions. Cha…