ragstack-ai-knowledge-store
DataStax RAGStack Graph Store
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires cassio to be installed and initialized; an embeddings provider must be supplied to GraphStore.
- 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 · maintenance · safety
BUSL-1.1 (unclear) — Licensed under BUSL-1.1, a proprietary license with time-based restrictions. Review the license terms carefully before using in commercial or production contexts.
last release 2024-07-30 (745 days) · last repo commit 2026-03-12 · 193 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 96,854 downloads/mo, #13,192 on PyPI
Alternatives
Verify before relying
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)- 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.
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 on it.
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
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.
Requires cassio to be installed and initialized; an embeddings provider must be supplied to GraphStore.
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)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
| License | BUSL-1.1 unclear |
| Python support | Capped below the current Python release <3.13,>=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 1 packagecassio |
| Maintenance | Actively maintained 745 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 96,854 / month, #13,192 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: Other/Proprietary LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.9 |
Evidence: ragstack_ai_knowledge_store-0.2.1-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “hybrid graph vector store”
- ragstack-ai-knowledge-storeStores and retrieves LangChain documents using a hybrid graph…
- graph-retrieverCombines vector similarity search with graph traversal over metadata…
- pyobvectorpyobvector is a Python SDK for OceanBase Vector Store that provides…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also graph-retriever · langchain-graph-retriever · langchain-mongodb · langchain-neo4j · neo4j-graphrag · langchain-milvus · langchain-elasticsearch · langchain-pinecone · farm-haystack · langchain-postgres