[Vector stores](https://python.langchain.com/docs/concepts/vectorstores): LLM should read this page when: 1) Building applications that need to index and retrieve information based on semantic similarity 2) Integrating vector databases into their application 3) Exploring advanced vector search and retrieval techniques Vector stores are specialized data stores that enable indexing and retrieving information based on vector representations (embeddings) of data, allowing semantic similarity search over unstructured data like text, images, and audio. The page covers vector store integrations, the core interface, adding/deleting documents, basic and advanced similarity search techniques, and concepts like metadata filtering.

