Engineering posts about Embedding
Curated summaries and key learnings for engineers working with Embedding.
Building with Gemini Embedding 2: Agentic multimodal RAG and beyond
The article introduces Gemini Embedding 2, a multimodal embedding model that integrates various data types, including text, images, video, and audio, into a unified embedding space. This model...
Learning Long-Term Motion Embeddings for Efficient Kinematics Generation
The article presents a novel method for learning long-term motion embeddings aimed at enhancing the efficiency of kinematics generation. By leveraging a highly compressed motion embedding with a...
What is pgvector?
pgvector is an open-source PostgreSQL extension designed to facilitate vector storage and similarity search directly within Postgres, eliminating the need for separate vector databases for AI...
A Theoretical Framework for Acoustic Neighbor Embeddings
This paper introduces a theoretical framework for interpreting acoustic neighbor embeddings, which represent phonetic content in a fixed-dimensional embedding space. It proposes a probabilistic...
Advancing semantic search for millions of Rovo users
The article outlines Rovo's innovative approach to semantic search, which enhances the ability of users to find relevant information across various tools like Jira and Confluence. By moving beyond...
SOTA Embedding Model for Agentic Workflows Now in Public Preview
The article introduces Qwen3-Embedding-0.6B, a state-of-the-art multilingual embedding model optimized for vector search and AI agent workloads, now available on Databricks. This model supports...
Recommending Travel Destinations to Help Users Explore
The article outlines the development of a destination recommendation model aimed at assisting users during the exploratory phase of trip planning. It highlights the unique challenges of integrating...
How Ontologies Help Nuclear Scale to Meet Global Energy Demand
The article explores how ontologies can enhance the operational efficiency of nuclear plants by capturing and structuring complex relationships between components, systems, and constraints. As the...
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...
Asynchronous Verified Semantic Caching for Tiered LLM Architectures
The article introduces 'Krites', an innovative asynchronous caching policy designed for large language models (LLMs) that enhances semantic caching efficiency without compromising critical path...
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)....
PinLanding: Turn Billions of Products into Instant Shopping Collections with Multimodal AI
The article presents PinLanding, an innovative pipeline designed to generate shopping collections from vast product catalogs using multimodal AI techniques. It emphasizes the transition from...
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...
Universal User Modeling (UUM): A Foundation Model for User Understanding at Snapchat
The article discusses Universal User Modeling (UUM) at Snapchat, a foundational model designed to enhance user understanding across various product surfaces. UUM captures user behaviors over time by...