Tech Blog Still Need Chunking When Long-Context Models Can Do It All? Comparing how long-context embedding models perform with different chunking strategies to find the optimal approach for your needs.
Tech Blog Featured Late Chunking in Long-Context Embedding Models Chunking long documents while preserving contextual information is challenging. We introduce the "Late Chunking" that leverages long-context embedding models to generate contextual chunk embeddings for better retrieval applications.
Events What We Learned at ICML2024 ft. PLaG, XRM, tinyBenchmark, MagicLens, Prompt Sketching etc. We had a blast at ICML 2024 in Vienna, and we want to share with you everything we said, saw, and learned.
Events A Tale of Two Worlds: EMNLP 2023 at Sentosa Just back from EMNLP2023 and my mind's still reeling! Witnessed NLP's seismic shift firsthand through daring papers and provocative posters that are challenging everything we thought we knew. Check out my take on the conference's boldest ideas.
Tech Blog Hype and Hybrids: Search is more than Keywords and Vectors Twenty years ago, “hybrid” was a term used only by botanists and chemists. Today, hybrid is booming… even in search. Many search systems are rolling out hybrid search schemes with the latest AI. But is "hybrid search" really more than a buzzword?
