Skip to content
masterclass Buddy
Start learning

AI Agents · Concept

Vector Store

LangChain vector stores save embedded documents and find similar content. They provide common methods for adding, deleting, and searching documents.

Last updated

Syntax

vector_store = InMemoryVectorStore(embedding_model)
vector_store.add_documents(documents=[doc1, doc2], ids=["id1", "id2"])
vector_store.delete(ids=["id1"])
vector_store.similarity_search(query, k=3, filter={"source": "tweets"})

In-depth API docs are only for subscribers: parameters, examples, common mistakes and interview practice.

Subscribe
  • Document
  • Embeddings
  • InMemoryVectorStore
  • Retriever
  • similarity_search_by_vector
  • maximum marginal relevance

Source: Vector store integrations. Checked 2026-11-03.