VectorStore
A low-level interface abstraction in LangChain responsible for vector storage and similarity retrieval, providing methods such as similarity_search.
Core Facts
Timeline (last 90 days)
`VectorStore` is responsible for vector storage and similarity retrieval (such as `similarity_search`) and is a relatively low-level storage interface; `Retriever` is a more general retrieval interface that only exposes `get_relevant_documents` (or `invoke` in newer versions), and any object that can return documents based on a query can be a Retriever, not necessarily a vector store.
`asRetriever()` merely adapts a VectorStore into a Retriever, and strategies such as MMR, similarity thresholds and multi-query rewriting can also be inserted in between.
Through Retriever, Document Loader, and VectorStore integration, LangChain carries the retrieval-splicing-generation process of injecting external private data into the context in the form of prompts.
Knowledge graphs built by Semantica are stored in a VectorStore, combining graph structure with vector retrieval so that Agents can perform structured traversal via graph edge relationships as well as fuzzy semantic retrieval via vector similarity.
All Facts (5)
Spring AI provides a unified VectorStore interface abstraction, allowing developers to switch between different vector databases without modifying business logic code.
70%Unverified`VectorStore` is responsible for vector storage and similarity retrieval (such as `similarity_search`) and is a relatively low-level storage interface; `Retriever` is a more general retrieval interface that only exposes `get_relevant_documents` (or `invoke` in newer versions), and any object that can return documents based on a query can be a Retriever, not necessarily a vector store.
50%Unverified`asRetriever()` merely adapts a VectorStore into a Retriever, and strategies such as MMR, similarity thresholds and multi-query rewriting can also be inserted in between.
50%UnverifiedThrough Retriever, Document Loader, and VectorStore integration, LangChain carries the retrieval-splicing-generation process of injecting external private data into the context in the form of prompts.
50%UnverifiedKnowledge graphs built by Semantica are stored in a VectorStore, combining graph structure with vector retrieval so that Agents can perform structured traversal via graph edge relationships as well as fuzzy semantic retrieval via vector similarity.
50%