Skip to main content


Rockset is a real-time analytics database service for serving low latency, high concurrency analytical queries at scale. It builds a Converged Index™ on structured and semi-structured data with an efficient store for vector embeddings. Its support for running SQL on schemaless data makes it a perfect choice for running vector search with metadata filters.

Installation and Setup

Make sure you have Rockset account and go to the web console to get the API key. Details can be found on the website.

pip install rockset

Vector Store

See a usage example.

from langchain_community.vectorstores import Rockset 

API Reference:

Document Loader

See a usage example.

from langchain_community.document_loaders import RocksetLoader

API Reference:

Chat Message History

See a usage example.

from langchain_community.chat_message_histories import RocksetChatMessageHistory

Help us out by providing feedback on this documentation page: