DropboxBuilding Dash: How RAG and AI agents help us meet the needs of businesses
Read Full ArticleSummary
The article outlines the challenges faced in building Dropbox Dash, a universal search and knowledge management tool designed for knowledge workers. It highlights issues such as data diversity, fragmentation, and modalities that complicate AI processing in business environments. The solution involves leveraging retrieval-augmented generation (RAG) to enhance the accuracy and relevance of responses to user queries, while also employing AI agents for multi-step orchestration of complex tasks. The article details the design decisions made to optimize the retrieval system and the evaluation of various large language models (LLMs) to ensure effective performance.
Key Learnings
- 1Understanding data diversity, fragmentation, and modalities is crucial for developing effective AI solutions in business contexts.
- 2Retrieval-augmented generation (RAG) combines external information retrieval with generative models to provide contextually relevant answers.
- 3The choice of retrieval system significantly impacts the user experience, balancing latency, quality, and data freshness.
- 4AI agents can autonomously break down complex queries into manageable steps, enhancing the capability of AI systems in business applications.
- 5Being model agnostic allows flexibility in adapting to advancements in large language models, which is essential for maintaining competitive AI solutions.
Who Should Read This
Senior AI Engineers developing enterprise-level AI solutions that require advanced data retrieval and processing capabilities.
Test Your Knowledge
What are the trade-offs between using embedding-based semantic searches versus traditional lexical-based systems in retrieval systems?
How does data fragmentation impact the efficiency of information retrieval in AI applications?
What criteria were used to evaluate the performance of different large language models for the Dash product?
Why is it important for AI agents to have a structured planning and execution process when handling complex user queries?
What challenges arise when integrating multiple data modalities into a single AI solution, and how can they be addressed?
Topics
More articles about Retrieval Augmented Generation
Explore Retrieval Augmented Generation engineering →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...
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...
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...
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...
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)....
More from Dropbox Engineering
View Dropbox engineering blogs →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...
How low-bit inference enables efficient AI
The article discusses the advancements in large machine learning models and the challenges associated with their deployment, particularly focusing on low-bit inference techniques that enhance...
Insights from our executive roundtable on AI and engineering productivity
The article provides insights into Dropbox's approach to enhancing engineering productivity through the adoption of AI tools. It highlights the importance of aligning AI initiatives with business...
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)....
Inside the feature store powering real-time AI in Dropbox Dash
The article delves into the implementation of a feature store that powers the AI-driven Dropbox Dash, focusing on how it manages and delivers data signals for effective ranking and retrieval of...