TLDRocket
Sign in

Retrieval-Augmented Generation

45 summarised stories about Retrieval-Augmented Generation, each linking back to the original source. Browse all topics →

+ Follow this topic

Key players

The New Stack Amazon Bedrock Amazon Web Services MarkTechPost OpenAI GPT-4.1

Sunday, 11 June 2023

Obsidian-Copilot: An Assistant for Writing & Reflecting

Eugene Yan 3 years ago 37

A developer built Obsidian-Copilot, a plugin that uses retrieval-augmented generation to help draft writing and reflect on journal entries by retrieving relevant notes and feeding them to language models. The system combines BM25 classical search with semantic search using the e5-small-v2 embedding model (ranked 7th on the Massive Text Embedding Benchmark) and chunks documents by top-level bullets rather than fixed token lengths. The tool enables users to generate drafts from section headers and weekly reflections from daily journal entries by integrating retrieval services with OpenSearch and FastAPI into Obsidian via a TypeScript plugin.

Read the full story
Retrieval-Augmented Generation Embedding Models

The daily briefing

Every AI story that matters, in your inbox by 8am.

TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the day in two minutes. Follow companies and topics for alerts, or get the briefing in Slack. Free, no spam, unsubscribe anytime.