Aktagon Signals AI-generated & human-reviewed
tags

Rag

assets.amazon.science 3 min read

Keyword Search is All You Need: Achieving RAG-Level Performance Without Vector Databases Using Agentic Tool Use

This research demonstrates that agentic keyword search approaches can achieve over 90% of traditional RAG system performance without requiring vector databases. The study compares tool-augmented LLM agents using simple …

AI · Development Signal Editorial Team
careersatdoordash.com 4 min read

Building DoorDash’s product knowledge graph with large language models

Building DoorDash’s Product Knowledge Graph with Large Language Models DoorDash uses large language models to extract and standardize product attributes from merchant data, solving the cold-start problem that …

Artificial Intelligence/Large Language Models · Artificial Intelligence/Natural Language Processing Signal Editorial Team
careersatdoordash.com 4 min read

How DoorDash leverages LLMs for better search retrieval

How DoorDash leverages LLMs for better search retrieval DoorDash uses large language models to improve search accuracy by segmenting complex queries and linking them to structured knowledge graphs. This hybrid approach …

Artificial Intelligence/Large Language Models Signal Editorial Team
www.youtube.com 5 min read

AI Engineering Essentials: A High-Level Summary of Chip Huyen's Book

AI Engineering Essentials: A High-Level Summary of Chip Huyen’s Book AI engineering has exploded as one of the fastest-growing engineering disciplines, offering salaries of $300,000 or more. This field emerged from …

Artificial Intelligence/Large Language Models · Development/Software Engineering Signal Editorial Team