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
Elasticsearch	self-hosted / cloud	✓	✓	✓	✓	✓
Pinecone	cloud	✓	✓	✓	✓
Timescale		✓		✓	✓	✓
Weaviate	self-hosted / cloud	✓	✓	✓	✓
Postgres	self-hosted / cloud	✓	✓	✓	✓	✓
Cassandra	self-hosted / cloud	✓		✓	✓
Qdrant	self-hosted / cloud	✓		✓	✓
Chroma	self-hosted	✓		✓	✓
Milvus / Zilliz	self-hosted / cloud	✓		✓	✓
Typesense	self-hosted / cloud	✓		✓	✓
Supabase	self-hosted / cloud	✓		✓	✓
MongoDB Atlas	self-hosted / cloud	✓		✓	✓
Redis	self-hosted / cloud	✓		✓	✓
Deeplake	self-hosted / cloud	✓		✓	✓
OpenSearch	self-hosted / cloud	✓		✓	✓
Neo4jVector	self-hosted / cloud			✓	✓
Azure Cognitive Search	cloud		✓	✓	✓
DynamoDB	cloud			✓
LanceDB	cloud	✓		✓	✓
Metal	cloud	✓		✓	✓
MyScale	cloud	✓	✓		✓
Tair	cloud	✓		✓	✓
Simple	in-memory	✓		✓
FAISS	in-memory
ChatGPT Retrieval Plugin	aggregator			✓	✓
DocArray	aggregator	✓		✓	✓

For more details, see Vector Store Integrations.

Examples

• Elasticsearch Vector Store
• Simple Vector Store
• Rockset Vector Store
• Qdrant Vector Store
• Faiss Vector Store
• DeepLake Vector Store
• MyScale Vector Store
• Metal Vector Store
• Weaviate Vector Store
• Opensearch Vector Store
• Pinecone Vector Store
• Chroma
• LanceDB Vector Store
• Milvus Vector Store
• Redis Vector Store
• Query the data
• Working with Metadata
• Weaviate Vector Store - Hybrid Search
• Zep Vector Store
• Create a Zep Vector Store and Index
• Querying with Metadata filters
• Pinecone Vector Store - Hybrid Search
• Simple Vector Store - Async Index Creation
• Tair Vector Store
• Supabase Vector Store
• DocArray Hnsw Vector Store
• DocArray InMemory Vector Store
• MongoDB Atlas
• Cassandra Vector Store
• Neo4j vector store
• Azure Cognitive Search
• Basic Example
• Create Index (if it does not exist)
• Use Existing Index
• Adding a document to existing index
• Filtering
• Epsilla Vector Store
• Timescale Vector Store (PostgreSQL)