Tag archive
A field guide to provisioning a Bedrock Knowledge Base on Aurora pgvector with Terraform, then keeping it in sync with a GitHub Actions workflow that ships docs to S3 on every push.
In the previous article, we covered the three core concepts behind RAG. Now let's build it. By the...
I built ChatScroll for the AWS H0 Hackathon — an app that lets you save AI answers as searchable...
Ollama + Open WebUI + pgvector: Sovereign RAG Stack 2026
pgvector vs Chroma vs Qdrant for Local RAG 2026
There's a moment in almost every RAG project where someone asks the question that decides your next...
At 500K embeddings for an Indian RAG MVP, Pinecone Standard costs ~₹6,200/month, self-hosted Qdrant runs ~₹1,400/month on Hetzner, and pgvector inside the Postgres you already pay for adds ₹0. Here is
This post was originally published on Rivestack. Most pgvector tutorials are written for Python....
How I would design a practical hybrid search engine for technical e-commerce catalogs using PostgreSQL, pgvector, HNSW, full-text search, and Citus.
RAG (Retrieval-Augmented Generation) — это паттерн, при котором LLM получает релевантный контекст...
Pure vector search is not always enough. If you have built a semantic search system with pgvector and...
Latency, recall, cost, and ops weight at 1M vectors. Numbers from named benchmarks, the rest labeled illustrative. A decision tree at the end.