Skip to content

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 ✓ ✓
BaiduVectorDB cloud ✓ ✓ ✓
ChatGPT Retrieval Plugin aggregator ✓ ✓
Chroma self-hosted ✓ ✓ ✓
DashVector cloud ✓ ✓ ✓ ✓
Databricks cloud ✓ ✓ ✓
Deeplake self-hosted / cloud ✓ ✓ ✓
DocArray aggregator ✓ ✓ ✓
DuckDB in-memory / self-hosted ✓ ✓ ✓
DynamoDB cloud ✓
Elasticsearch self-hosted / cloud ✓ ✓ ✓ ✓ ✓
FAISS in-memory
txtai in-memory
Jaguar self-hosted / cloud ✓ ✓ ✓ ✓
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 ✓ ✓ ✓
Upstash cloud ✓
Weaviate self-hosted / cloud ✓ ✓ ✓ ✓

For more details, see Vector Store Integrations.

Example Notebooks#