Skip to main content
OpenVikingStore is a LangGraph BaseStore backed by OpenViking. Use it for long-term memory across threads in an OpenViking HTTP deployment.

Overview

OpenViking is a context database for AI agents. The langchain-openviking package includes an OpenVikingStore class for storing LangGraph values as durable OpenViking content records and indexing them for query-based search calls. This page documents the published langchain-openviking package on PyPI (v0.1.0).

Integration details

Setup

To use OpenVikingStore, you need an OpenViking HTTP deployment and an API key.

Installation

Install the integration with the langgraph extra:

Credentials

Set your OpenViking URL and API key:

Instantiation

Instantiate OpenVikingStore with your OpenViking HTTP connection settings:
The package default root_uri is viking://user/memories/langgraph_store. Newer OpenViking servers reject that uid-less form, so pass the viking://~ home alias (as above) or an explicit viking://user/<uid>/... URI.

Usage

Use put to write a JSON-serializable mapping under a namespace and key:
Use get to retrieve the stored item:
Use search with a namespace prefix. Pass query for semantic search:
Use delete to remove a key:

API reference

For detailed documentation, see the OpenViking LangChain and LangGraph integration guide and the OpenVikingStore source for v0.1.0. See also the LangGraph store integrations list.