📄️ Comparison table of all supported Embedding Stores
| Embedding Store | Storing Metadata | Filtering by Metadata | Removing Embeddings |
📄️ In-memory
LangChain4j provides a simple in-memory implementation of an EmbeddingStore interface:
📄️ Astra DB
Astra DB
📄️ Azure AI Search
https://azure.microsoft.com/en-us/products/ai-services/ai-search/
📄️ Azure CosmosDB Mongo vCore
https://azure.microsoft.com/en-us/products/cosmos-db/
📄️ Azure CosmosDB NoSQL
https://azure.microsoft.com/en-us/products/cosmos-db/
📄️ Cassandra
Cassandra
📄️ Chroma
https://www.trychroma.com/
📄️ ClickHouse
ClickHouse is the fastest and most resource efficient open-source
📄️ Oracle Coherence
https://coherence.community/
📄️ Couchbase
https://www.couchbase.com/
📄️ DuckDB
https://duckdb.org/
📄️ Elasticsearch
https://www.elastic.co/
📄️ Infinispan
https://infinispan.org/
📄️ Milvus
https://milvus.io/
📄️ MongoDB Atlas and Vector Search
MongoDB Atlas is a fully-managed cloud database available in AWS, Azure, and GCP. It supports native Vector Search and full text search (BM25) on your MongoDB document data.
📄️ Neo4j
https://neo4j.com/
📄️ OpenSearch
https://opensearch.org/
📄️ Oracle
The Oracle Embedding Store integrates with
📄️ PGVector
LangChain4j integrates seamlessly with PGVector, allowing developers to store
📄️ Pinecone
https://www.pinecone.io/
📄️ Qdrant
https://qdrant.tech/
📄️ Redis
https://redis.io/
📄️ Tablestore
https://www.aliyun.com/product/ots
📄️ Vearch
https://github.com/vearch/vearch
📄️ Vespa
https://vespa.ai/
📄️ Weaviate
https://weaviate.io/