Expose only completed files as RAG evidence
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.
Posts tagged embeddings
AI/LLM topics — agents, prompts
HTML, CSS, JS, HTTP, URL basics
TypeScript, Java, Python, Rust
Data structures, Big-O, patterns
React, Next.js, Tauri, Tailwind
Spring, FastAPI, SQL
Claude Code · MCP · Context7 · Figma — overview of AI coding tools
Deployment options and decision criteria
PostgreSQL · Kafka · data strategy notes
Docker, Compose, Caddy, SSH
Windows vs Mac and other dev-environment notes
Cross-platform options compared (Tauri · Flutter · RN)
pnpm, uv, Gradle, Git, regex
KISS · DRY · YAGNI · naming — development philosophy
OAuth · JWT · security fundamentals
Testcontainers, Vitest, pytest
Searching, reading docs, debugging
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.
An embedding is the result of mapping text (or images · code) to fixed-dimensional real-valued vectors. On top of the assumption that semantically close items sit close in the vector space, search · clustering · classif…