1. Docs
  2. Cloaked AI
  3. Database Integrations
  1. Docs
  2. Cloaked AI
  3. Database Integrations

Database Integrations

Cloaked AI was designed to easily interoperate with a wide range of vector databases. This is possible because the encrypted embeddings are simple drop-in replacements for their unencrypted counterparts.

We have several examples of integrating with common vector databases below. They each demonstrate how you can encrypt the embedding vectors to protect the sensitive data and still use the vector database to perform nearest neighbor queries. In many cases, these examples start with the database’s own Getting Started guide and simply add the necessary encryption steps when inserting vectors and querying for nearest neighbors.

Several examples also demonstrate how metadata can be encrypted and stored securely with each vector, then decrypted when results are returned by search. They use standard encryption for the text fields associated with the embeddings and deterministic encryption for additional fields that can be used to filter the nearest neighbor queries.

Elasticsearch

We provide a Python example of integrating both Cloaked AI and Cloaked Search with Elasticsearch. This hybrid search use case allows a single query to rank based on both keywords and similar embeddings while protecting the sensitive data in both keyword and vector indices.

Marqo

We provide a GitHub repository showing how to integrate Cloaked AI with Marqo and query encrypted embeddings.

Milvus

We provide a Python example of integrating Cloaked AI with Milvus. This example demonstrates encryption of the vectors, associated metadata, and filter fields.

OpenSearch

We provide a Python example of integrating both Cloaked AI and Cloaked Search with OpenSearch. This is a hybrid search example similar to the Elasticsearch one and provides the same security benefits while retaining full search capabilities.

pgvector

We provide a Python example of integrating Cloaked AI with pgvector. This example also includes vectors, metadata, and filter fields.

Pinecone

We provide a Jupyter notebook and Python example showing how to conduct a search on encrypted data in Pinecone as well as a walkthrough video providing additional details about the notebook. This example encrypts vectors and metdadata fields.

Qdrant

We provide a Rust example showing how to use Cloaked AI with Qdrant to encrypt and query embeddings.

Weaviate

We provide a Python example of integrating Cloaked AI with Weaviate. This example also encrypts vectors, metadata, and filter fields.

Note: this example builds off of Weaviate’s “Bring your own vectors” example, as we do not currently support their vectorizer model of inserting data.