Engineering posts about Retrieval Augmented Generation

Curated summaries and key learnings for engineers working with Retrieval Augmented Generation.

Databricks
4m

Databricks context engineer associate: the industry’s first certification for reliable AI agent systems

The article introduces the Databricks Certified Context Engineer Associate certification, the first of its kind aimed at enhancing the reliability of AI agent systems through effective context...

Meta (Facebook)
6m

Modernizing the Facebook Groups Search to Unlock the Power of Community Knowledge

The article outlines a significant overhaul of Facebook Groups Search, transitioning from traditional keyword-based retrieval to a hybrid architecture that incorporates both lexical precision and...

DigitalOcean
18m

Building a Robust Documentation Agent with DigitalOcean Gradient AI Platform

The article outlines the development of a documentation assistant leveraging DigitalOcean's Gradient AI Platform. It emphasizes the transition from traditional documentation to an AI-driven solution...

Databricks
11m

Building a Knowledge Assistant over Code

This article explores the development of a knowledge assistant for code retrieval, specifically addressing the challenges of chunking source code for effective retrieval-augmented generation (RAG)....

Apple
2m

AMES: Approximate Multi-modal Enterprise Search via Late Interaction Retrieval

The article presents AMES (Approximate Multimodal Enterprise Search), a unified architecture for late interaction retrieval that integrates text, image, and video modalities into a shared...

Pinterest
19m

Unified Context-Intent Embeddings for Scalable Text-to-SQL

The article outlines Pinterest's evolution from basic Text-to-SQL systems to a sophisticated Analytics Agent that leverages unified context-intent embeddings for enhanced query understanding and SQL...

Apple
3m

Scaling Search Relevance: Augmenting App Store Ranking with LLM-Generated Judgments

The article presents a study on enhancing search relevance in app store rankings by integrating LLM-generated judgments. It identifies the challenge of limited expert-provided textual relevance...

Dropbox
11m

Using LLMs to amplify human labeling and improve Dash search relevance

The article outlines how Dropbox Dash utilizes a retrieval-augmented generation (RAG) approach to enhance search relevance by integrating large language models (LLMs) with human labeling. It explains...

Apple
3m

Unifying Ranking and Generation in Query Auto-Completion via Retrieval-Augmented Generation and Multi-Objective Alignment

The article discusses a novel approach to Query Auto-Completion (QAC) that integrates Retrieval-Augmented Generation (RAG) with multi-objective Direct Preference Optimization (DPO). This unified...

Dropbox
17m

Engineering VP Josh Clemm on how we use knowledge graphs, MCP, and DSPy in Dash

In this article, Josh Clemm discusses the technical architecture behind Dropbox Dash, focusing on the integration of knowledge graphs, retrieval methods, and the use of large language models (LLMs)....

Databricks
4m

Agent Bricks Knowledge Assistant Is Now Generally Available: Turning Enterprise Knowledge into Answers

The article introduces the Knowledge Assistant, a fully managed AI agent designed to transform enterprise knowledge into accurate, cited answers. It highlights the limitations of traditional...

Apple
3m

Over-Searching in Search-Augmented Large Language Models

The article explores the phenomenon of over-searching in search-augmented large language models (LLMs), where unnecessary search tool invocations can degrade response quality and lead to...

Databricks
5m

How 7‑Eleven Transformed Maintenance Technician Knowledge Access with Databricks Agent Bricks

The article details how 7-Eleven transformed its maintenance operations by implementing an AI-powered Technician's Maintenance Assistant (TMA) built on Databricks. This solution significantly reduced...

Databricks
14m

Instructed Retriever: Unlocking System-Level Reasoning in Search Agents

The article introduces the Instructed Retriever, a novel architecture designed to enhance the capabilities of retrieval-based agents by addressing the limitations of traditional Retrieval Augmented...

DigitalOcean
3m

A More Powerful, Code-First Knowledge Base Experience on the DigitalOcean Gradient™ AI Platform

The article introduces significant improvements to the DigitalOcean Gradient AI Knowledge Base platform, emphasizing a code-first approach that allows developers to manage knowledge bases directly...

Apple
3m

AgREE: Agentic Reasoning for Knowledge Graph Completion on Emerging Entities

The article introduces AgREE, an innovative agent-based framework designed to enhance Knowledge Graph Completion (KGC) for emerging entities. Traditional KGC methods often struggle with new entities...

Apple
3m

Reusing Pre-Training Data at Test Time is a Compute Multiplier

The article explores the potential of reusing pre-training data during test time to enhance the performance of large language models (LLMs). It highlights the inefficiencies in current pre-training...

Apple
2m

Semantic Mastery: Enhancing LLMs with Advanced Natural Language Understanding

The article explores the advancements in large language models (LLMs) through enhanced natural language understanding (NLU) techniques. It highlights the challenges faced in achieving deeper semantic...

AWS
5m

Introducing Amazon Nova Forge: Build your own frontier models using Nova

The article introduces Amazon Nova Forge, a service designed to help organizations build their own frontier models using generative AI. It addresses the limitations of existing customization...