ragstack-ai-knowledge-store

What it is and what it does

RAGStack Graph Store is a LangChain-compatible document store that layers graph structure on top of vector search. Instead of retrieving documents by similarity alone, it lets you define edges between chunks—via hyperlinks, semantic relationships, or custom metadata—and then traverse those edges during retrieval to surface related context. You populate documents with metadata fields like `content_id` and `links`, add them to the store, and retrieve them with a configurable depth parameter that controls how many levels of edges to follow.

The package is built on top of cassio and designed to work with Cassandra as the underlying storage backend. It integrates with LangChain's embedding and retrieval ecosystems. The main use case is building retrieval systems where document relationships matter—e.g., a knowledge base where pages link to each other, or chunks that should pull in related context when retrieved.

Use it for:

• Build a documentation system where hyperlinks between pages are traversed to surface related docs alongside vector matches.
• Create a knowledge graph retriever that follows semantic edges between chunks to enrich context for generation.
• Store and retrieve hierarchical or interconnected documents where edge depth controls retrieval scope.
• Implement a hybrid search that combines vector similarity with relationship-based ranking for multi-hop context.
• Populate and query a document store where metadata-driven links define how chunks should be connected.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Stores and retrieves LangChain documents using a hybrid graph approach that combines vector similarity search with edge-based traversal between document chunks.

Yes, if you need hybrid graph-based retrieval for LangChain and are comfortable with the BUSL-1.1 license terms. The package has low install friction, active maintenance, no known vulnerabilities, and clear integration with cassio. Verify the license is compatible with your use case before committing to production.

Install

ragstack-ai-knowledge-store on PyPI

pip install ragstack-ai-knowledge-store

uv add ragstack-ai-knowledge-store

poetry add ragstack-ai-knowledge-store

Installing ragstack-ai-knowledge-store

Before you install

Low friction install with a single runtime dependency (cassio). The package is actively maintained with recent commits and no known vulnerabilities, though it has not been updated since July 2024.

License in practice

Licensed under BUSL-1.1, a proprietary license with time-based restrictions. Review the license terms carefully before using in commercial or production contexts.

Quickstart

pip install ragstack-ai-knowledge-store

import cassio
from ragstack_ai_knowledge_store import GraphStore

cassio.init(auto=True)
graph_store = GraphStore(embeddings=embeddings_provider)
graph_store.add_documents(documents)
retriever = graph_store.as_retriever(k=4, depth=1)

Requires cassio to be installed and initialized; an embeddings provider must be supplied to GraphStore.

Verify before relying

• Performance characteristics when traversing edges at depth > 1 or with large document collections.
• Whether the BUSL-1.1 license permits all intended use cases (commercial, SaaS, etc.).
• Specific LangChain version compatibility requirements.

Package facts

Evidence: ragstack_ai_knowledge_store-0.2.1-py3-none-any.whl

Tags

More Artificial Intelligence packages

Further reading