Metadata-Version: 2.1
Name: ragstack-ai-knowledge-graph
Version: 0.0.2
Summary: DataStax RAGStack Knowledge Graph
Home-page: https://github.com/datastax/ragstack-ai
License: BUSL-1.1
Author: DataStax
Requires-Python: >=3.11,<4.0
Classifier: License :: Other/Proprietary License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Dist: cassio (>=0.1.5,<0.2.0)
Requires-Dist: graphviz (>=0.20.3,<0.21.0)
Requires-Dist: langchain (>=0.1.14,<0.2.0)
Requires-Dist: langchain-community (>=0.0.31,<0.0.32)
Requires-Dist: langchain-experimental (>=0.0.56,<0.0.57)
Requires-Dist: langchain-openai (>=0.1.1,<0.2.0)
Requires-Dist: pydantic-yaml (>=1.3.0,<2.0.0)
Requires-Dist: pyyaml (>=6.0.1,<7.0.0)
Project-URL: Documentation, https://docs.datastax.com/en/ragstack
Project-URL: Repository, https://github.com/datastax/ragstack-ai
Description-Content-Type: text/markdown

# RAGStack Knowledge Store

> [!WARNING]
> This is a proof-of-concept showing how knowledge graphs can be stored in Astra
> / Cassandra and retrieved via traversal. There are a variety of planned improvements
> including benchmarking, evaluation, and possible schema changes.

This includes some code (`CassandraGraphStore`) which could be added to
LangChain or RAGStack to write LangChain's `GraphDocuments` to Cassandra tables.
It also includes code to create a runnable for retrieving knowledge triples from
Cassandra.

The file `notebook.ipynb` shows this working on an example snippet from
LangChain's docs.

To run, copy `env.template` to `.env`.
