Technique

Retrieval-Augmented Generation

A technique that grounds an LLM's answers in documents retrieved at query time, reducing hallucination.

A full explainer for this concept is being written. In the meantime, here's what's in the news.

In the news

llm-system-design — A production-grade LLM System Design platform & interactive lab. Features a pure-Python LLM serving, RAG, routing, safet

GitHub · Jul 29, 2026

Beyond RAG: Task-aware knowledge compression for enterprise AI on AWS

AWS ML Blog · Jul 27, 2026

llm-engineering-platform — A production-oriented LLM engineering platform with OpenAI-compatible serving, streaming, observability, evaluation, rep

GitHub · Jul 26, 2026

data-driven-ai-guide — Teach Data Engineers How to Think AI.

GitHub · Jul 26, 2026

Product Hunt · Jul 24, 2026

Agentic retrieval for Amazon Bedrock Managed Knowledge Base

AWS ML Blog · Jul 23, 2026

The AI context gap: Enterprise AI organizations have a trust problem, not a retrieval problem — and most are still building the fix

VentureBeat AI · Jul 16, 2026

CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning

Apple ML Research · Jul 15, 2026