Urgent.News

What's breaking now, across thousands of outlets.

Tech

Ofrenda: A Remembrance Builder That Never Leaves Your Laptop (clear, and states the open-source angle right away)

What I Built Every family has a few people whose stories only exist in someone’s head. A grandmother who hummed while she cooked. An uncle with one phrase he said at every dinner. Those details are the first to fade, and the hardest to write down when you’re staring at a blank page. The tempting move is to paste the little you remember into a chatbot and ask it to write something beautiful. I…

Ofrenda is an open-source tool designed to help users remember and honor the stories of loved ones who have passed away. The software allows individuals to input personal details about a person, such as their name, years of life, favorite foods and songs, and cherished memories. A Gemma model, running locally through Ollama, then uses these inputs to craft a personalized remembrance piece.

The process begins with safety measures, as the model is instructed to only use the facts provided and avoid inventing any details. It asks follow-up questions that focus on sensory experiences and personal stories, encouraging users to recall specific details about the person. The model then generates a short, first-person draft of the remembrance, which remains editable for final touches.

When complete, the entire remembrance is exported as a standalone HTML file. This file contains the user's memories, a photo, and an animated candle, all encapsulated in a design that can be printed, shared, or kept for years. The entire software runs locally, ensuring privacy and offline functionality, making it a truly unique way to preserve and share personal histories without relying on external servers or AI services.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in Tech

Fintech Ticket Triage with Node.js RAG: PDF Upload, Semantic Search, and Citations

Short answer: use Node.js for the upload workflow, pgvector for metadata-aware semantic search, and embeddings plus citations as a validated contract; choose a shared OpenAI-compatible runtime only…

  • PDF uploads divided into overlapping chunks for semantic search
  • Embedded chunks with filename, page, and section metadata
  • Generated answers include citations and provenance for verification

How to Learn React Hooks (and Stop Fighting useEffect)

The first React app I wrote with hooks had a useEffect that fetched a user profile. It worked on the first load. Then I added the user ID to the dependency array because the linter told me to, and the…

  • Start by understanding what a render is in React hooks.
  • Use the updater form of useState for dependent state values.
  • Properly use the dependency array in useEffect to avoid stale data.

Day 15 of 30: the halfway map, fourteen ideas worth keeping

Halfway through the series. Instead of a self-congratulating check-in, here's something more useful: a map of the fourteen ideas so far, each in a paragraph, so you can skim the series in five minutes…

  • Day 15 marks halfway point in 30-day series
  • Focus on fourteen ideas for safe defaults and systems
  • Next topics: Three.js, Row Level Security, test plan

More from Sunday 1 November →