PinnedAngelina YangHow to Find a “Good Boss” and the Battle of TrafalgarWhen I first graduated and was looking for a job, I never thought about what I want from a manager. I probably selected the highest paid…·5 min read·Mar 6, 2023----
Angelina YangFaster, Cheaper Retrieval with Embedding QuantizationEmbeddings are a fundamental component of most modern AI stack. When working with large document repositories, the computational costs of…·3 min read·3 hours ago----
Angelina YangGriffin: New LLM Architecture Conquer Long ContextsRecurrent neural networks (RNNs) have fast inference and scale efficiently on long sequences, but they are difficult to train and hard to…·5 min read·3 days ago----
Angelina YangSTORM: AI Agents for Long-Form WritingWriting a well-structured and organized piece of content is crucial for effectively conveying information to readers. One of the key…·3 min read·May 6, 2024--1--1
Angelina YangPrivate, No-Code Alternatives to ChatGPT on Your DesktopAre you concerned with privacy when using AI chatbots like ChatGPT?·2 min read·May 3, 2024----
Angelina YangBoost Your RAG Systems with Semantic CachingFor retrieval-augmented generation (RAG) AI applications, semantic caching offers a powerful optimization to handle repetitive user queries…·2 min read·May 1, 2024----
Angelina Yang4 Patterns of Agentic Reasoning DesignToday, the way most of us interact with Language Models (LMs) is akin to a non-agentic workflow. We prompt them, they generate an answer…·3 min read·Apr 29, 2024----
Angelina YangHow to Generate Structured Output with LLM?Do your products or use cases need structured output?·2 min read·Apr 29, 2024----
Angelina Yang🦖RAPTOR🦖 Implementation Code Walk-throughLast week we talked about RAPTOR — an advanced RAG technique that features recursive hierarchical clustering. If you would like to revisit:·2 min read·Apr 22, 2024----
Angelina Yang🦖RAPTOR🦖 for Advanced RAG“Retrieval-augmented language models can better adapt to changes in world state and incorporate long-tail knowledge.”·3 min read·Apr 17, 2024--1--1