Weaviate Knowledge Cards

Unlock the power of vector search. Our guides will help you conquer vector embeddings and build better AI applications.

Knowledge Cards / Large Language Models / Chunking

Large Language Models

Chunking

Chunking is the process of dividing large texts into smaller, manageable pieces, called 'chunks', for storage or processing in vector databases and language models. It improves search performance and the quality of language model outputs by defining the granularity of information retrieval.