Expose only completed files as RAG evidence
1 min
File upload and search availability are different states. Only a search copy that finished parsing, embedding, and storage—and has processed = TRUE—may become evidence for a user answer.
#pgvector
Posts tagged pgvector
Categories
AI & LLM
9AI/LLM topics — agents, prompts
Web Fundamentals
7HTML, CSS, JS, HTTP, URL basics
Languages
4TypeScript, Java, Python, Rust
Programming
4Data structures, Big-O, patterns
Frontend
18React, Next.js, Tauri, Tailwind
Backend
19Spring, FastAPI, SQL
Agent tooling
15Claude Code · MCP · Context7 · Figma — overview of AI coding tools
Cloud
22Deployment options and decision criteria
Data
20PostgreSQL · Kafka · data strategy notes
Infra
10Docker, Compose, Caddy, SSH
Environment
11Windows vs Mac and other dev-environment notes
Mobile
4Cross-platform options compared (Tauri · Flutter · RN)
Dev tools
12pnpm, uv, Gradle, Git, regex
Philosophy
10KISS · DRY · YAGNI · naming — development philosophy
Security concepts
9OAuth · JWT · security fundamentals
Quality / Tests
11Testcontainers, Vitest, pytest
Learning
6Searching, reading docs, debugging
Posts tagged pgvector
pgvector and RAG
6 minThe trend of combining large language model responses with external knowledge has settled under the name RAG (Retrieval-Augmented Generation). At its core sits vector similarity search, and PostgreSQL's pgvector extensi…
RAG and Search — Chunking · Embedding · Reranking · Hybrid
6 minRAG (Retrieval-Augmented Generation) is an approach to supplement an LLM's limited training cutoff and memory limits with external knowledge. By separating retrieval and generation, you can handle new material without r…