Vector Stores

Vector stores contain embedding vectors of ingested document chunks (and sometimes the document chunks as well).

Simple Vector Store

By default, LlamaIndex uses a simple in-memory vector store that’s great for quick experimentation. They can be persisted to (and loaded from) disk by calling vector_store.persist() (and SimpleVectorStore.from_persist_path(...) respectively).

Vector Store Options & Feature Support

LlamaIndex supports over 20 different vector store options. We are actively adding more integrations and improving feature coverage for each.

Vector Store	Type	Metadata Filtering	Hybrid Search	Delete	Store Documents	Async
Apache Cassandra®	self-hosted / cloud	✓		✓	✓
Astra DB	cloud	✓		✓	✓
Azure Cognitive Search	cloud		✓	✓	✓
Azure CosmosDB MongoDB	cloud			✓	✓
ChatGPT Retrieval Plugin	aggregator			✓	✓
Chroma	self-hosted	✓		✓	✓
DashVector	cloud	✓		✓	✓
Deeplake	self-hosted / cloud	✓		✓	✓
DocArray	aggregator	✓		✓	✓
DynamoDB	cloud			✓
Elasticsearch	self-hosted / cloud	✓	✓	✓	✓	✓
FAISS	in-memory
LanceDB	cloud	✓		✓	✓
Lantern	self-hosted / cloud	✓	✓	✓	✓	✓
Metal	cloud	✓		✓	✓
MongoDB Atlas	self-hosted / cloud	✓		✓	✓
MyScale	cloud	✓	✓	✓	✓
Milvus / Zilliz	self-hosted / cloud	✓		✓	✓
Neo4jVector	self-hosted / cloud			✓	✓
OpenSearch	self-hosted / cloud	✓		✓	✓
Pinecone	cloud	✓	✓	✓	✓
Postgres	self-hosted / cloud	✓	✓	✓	✓	✓
pgvecto.rs	self-hosted / cloud	✓	✓	✓	✓
Qdrant	self-hosted / cloud	✓		✓	✓	✓
Redis	self-hosted / cloud	✓		✓	✓
Simple	in-memory	✓		✓
SingleStore	self-hosted / cloud	✓		✓	✓
Supabase	self-hosted / cloud	✓		✓	✓
Tair	cloud	✓		✓	✓
TencentVectorDB	cloud	✓	✓	✓	✓
Timescale		✓		✓	✓	✓
Typesense	self-hosted / cloud	✓		✓	✓
Weaviate	self-hosted / cloud	✓	✓	✓	✓

For more details, see Vector Store Integrations.

Examples