Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: semantic-search
Semantic Search Service with a Pinecone Vector Database Behind an MCP Server
A reusable semantic search service: chunk PDFs, store embeddings in a Pinecone vector database, and let any agent query them through a FastMCP server.
7 min readA Field Map of RAG: From First Principles to Production Failures
Two pipelines, three steps and a list of named failures: how retrieval-augmented generation works, where it breaks, and which fixes address each problem.
7 min readDesigning Portable Multi-Tenant Semantic Search on Kubernetes and Qdrant
How a semantic search platform uses Kubernetes for portability and tenant-aware routing to keep its vector database replaceable and its workloads isolated.
6 min readMeaning as Coordinates: From Embeddings to Vector Databases and RAG
Embeddings, cosine similarity, vector databases and the RAG loop explained with four tiny sentences about dogs, cats and Paris, so semantic search clicks.
11 min readSemantic Search in PostgreSQL With pgvector and Node.js, No LLM Needed
Semantic search in PostgreSQL with pgvector and Node.js, no LLM: MiniLM embeddings, chunks, an IVFFlat index, distance operators and how to read the scores.
8 min readBeyond Cosine Similarity: Five RAG Retrieval Techniques Compared
Cosine, BM25, hybrid RRF, cross-encoder reranking and MMR explained with code, trade-offs and a query-first way to decide which retrieval technique your RAG needs.
10 min readHow to Debug Empty Retrieval When a RAG System Returns Nothing
A RAG system that returns nothing, debugged stage by stage: ingestion, score thresholds, filters, query rewriting, hybrid search, reranking and fallbacks.
9 min readSemantic Search in PostgreSQL With pgvector and .NET: A Practical Setup
Store embeddings next to relational data, build HNSW or IVFFlat indexes, filter and blend hybrid ranks, and judge when pgvector is enough for your app.
9 min readPractical notes: Vector Search, Semantic Search, and RAG: How AI Finds the
Operable walkthrough of Practical notes: Vector Search, Semantic Search, and RAG: How AI Finds the: contracts, checks, and drop-in code slots for teams shipping this pattern.
9 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.