Hybrid Search and Reranking: What Each One Actually Buys You
Enterprise RAG Engineering — Part 2 of 3 Where Part 1 Left Off Part 1 argued that most enterprise RAG systems fail at the ingestion layer, before a…
DevOps
⚑ Сообщить о проблемеПоследние новости DevOps от Tech News
Все темы
agents
ai
api
architecture
automation
aws
backend
beginners
cloud
database
devchallenge
devops
docker
javascript
kubernetes
llm
machinelearning
mcp
node
opensource
performance
productivity
programming
python
security
showdev
testing
tutorial
typescript
webdev
How Does a Vector Database Work?
Most explanations of vector databases turn into a wall of math. Here's the one-minute version instead. The idea, in one sentence A vector database d…
Semantic Search Without an LLM. Build Blazing-Fast Semantic Search for \$0
We live in an era where "AI search" usually means routing simple queries through heavy, expensive, slow generative Large Language Models (LLMs). But…
Why we built recall-first search on PostgreSQL
Our careers page search often felt broken. Searching for “Java” could return JavaScript roles. A misspelling could produce no results at all. Search…
Designing Low-Power IoT Devices with Integrated Wi-Fi and Bluetooth LE SoCs
Modern IoT devices are expected to do more while using less power and occupying less physical space. A single connected device may need to communica…
Infino: fastest VectorDB at a million, still cheaper at a billion
Disclosure: I work on Infino, the engine benchmarked here. This post first appeared on the Infino blog . Every team that adopts vector search eventu…
OpenViking’s Filesystem View of Agent Context Is a Welcome Escape from RAG Glue Code
A repository gaining 7,710 stars in a month deserves a performance-minded look, not just a screenshot of the README. OpenViking positions itself as…
Talk to Your Medical History: Building a Personal EHR RAG with Milvus and Unstructured.io 🩺
We’ve all been there: digging through a mountain of crumpled hospital printouts, blurry scans, and nested PDFs just to find out what that specific b…
One MCP Server, Two AI Clients: Wiring Actian VectorAI DB Into Claude and Cursor
MCP promises one server, any AI client. I put that to the test by wiring Actian VectorAI DB up to Claude and Cursor with a single ~230-line Python f…
VectorAI DB Doesn't Embed Your Text, and That's the Point
Building a small local knowledge base on top of Actian VectorAI DB, the actual challenge wasn't the database. It was easy to accidentally fake seman…
Using SynapCores as a LlamaIndex Vector Store + Property Graph Store
Most LlamaIndex setups end up with two separate backends once you go beyond plain vector search: a vector store for VectorStoreIndex , and a separat…
jina-embeddings-v4 as an OpenAI-Compatible Embeddings Server
jina-embeddings-v4 is a self-hosted server for the jina-embeddings-v4 embedding model with an OpenAI-compatible /v1/embeddings endpoint. It runs on…
Scaling RAG Systems: Production Architecture, Performance, and Cost Optimization
The first three parts of this series covered why production RAG systems fail and how the quality of the data foundation directly affects everything…
My Favorite Constant in Retrieval Is 60. Nobody Tunes It. That's the Point.
Reciprocal rank fusion merges two ranked lists — say, BM25 results and vector-search results over your chargeback cases — into one. It has exactly o…
Why AI Agents Lose Their Memory And How MemoFS Solves It
Whether you are using off-the-shelf AI coding tools like Claude Code and Cursor or building custom autonomous AI agents with TypeScript and LLM APIs…
Kdrant: an idiomatic, coroutine-first Kotlin client for Qdrant
If you build on the JVM and want to use Qdrant , the official client is io.qdrant:client — and it's built for Java. Every call returns a ListenableF…
Can ClickHouse Replace a Vector Database?
Vector databases like Pinecone, Weaviate, and Milvus exist for one job: store embeddings and find the nearest ones to a query vector, fast. ClickHou…
Vector Databases, Deep Indexing & Token Economics: The Complete Story (phase 3)
From "we have vectors" to "this actually scales, and doesn't bankrupt us." The Story Starts: Two Questions in One 👦 Nephew: Uncle, Phase 2 is done.…
Quantified Self 2.0: Stop Guessing Your Health History—Build a Personal Medical Vector Database
Let's be real: our personal medical history is a mess. It’s a chaotic mix of PDF lab results, grainy scans of prescriptions, and cryptic Electronic…
The Markdown File That Beat a $50M Vector Database: Separating Storage and Search in Agent Memory
In the rush to build AI agents, we defaulted to complex vector databases. But high-traffic platforms are converging on a simpler, more robust founda…
Building a cross-user review graph with pgvector on Amazon Aurora
Every review app is a silo. Yelp reviews places, Amazon reviews its own catalog, Letterboxd reviews film. I wanted to build the opposite: one place…
Pinecone vs Weaviate vs Milvus vs Qdrant: Which Vector DB in 2026?
I have helped a number of teams pick a vector database in the last year. The conversation always starts the same way: four logos, one Slack message,…
Embeddings Magic
Transforming language into geometry. Introduction Embeddings are one of the most important building blocks of modern AI applications, yet they're of…
# Vector Search and RAG: A Primer
A short learning path from a weekend project: I indexed my personal markdown notes (~800 chunks), tried a few local embedding models, stored the sam…
Vector Databases Are Not Magic, Here's What's Actually Happening Under the Hood
You've seen the tutorials. Spin up Pinecone, call .upsert() , do a similarity search, ship it. Everyone claps. The demo works. Then you take it to p…
I Built a Python Agent That Uses a Vector DB as Memory, Not Retrieval
Vector databases are almost always talked about in the context of RAG. Store your documents, embed them, retrieve the relevant chunks at inference t…
Your vector memory database remembers everything. That’s exactly the issue.
There is a design assumption baked into almost every vector database and AI memory implementation that sounds reasonable until you watch it grow nod…
Why Your Vector Database Is Overpriced: Lucene's 32x Compression and Serverless Economics
Why Your Vector Database Is Overpriced: Lucene's 32x Compression and Serverless Economics In 2026, the boundary between "search engine" and "AI infr…
The challenges of creating a semantic memory layer on Cloudflare Workers, D1, and Vectorize.
The main concept is straightforward: embed text, store the vector, and query it later. The time-consuming part was everything else. I created a memo…
Enterprises Are Quietly Moving Their AI Back On-Premises. Here Is Why.
42% of companies are considering moving workloads off the cloud. For AI infrastructure specifically, the reasons are more urgent than cost. The Tren…