Metadata-Version: 2.4
Name: lightrag-memgraph
Version: 0.1.2
Summary: LightRAG integration with Memgraph
Project-URL: Homepage, https://github.com/memgraph/ai-toolkit
Project-URL: Source, https://github.com/memgraph/ai-toolkit/tree/main/integrations/lightrag-memgraph
Project-URL: Issues, https://github.com/memgraph/ai-toolkit/issues
Author-email: Memgraph Tech Team <tech@memgraph.com>
License: MIT
License-File: LICENSE
Keywords: graph,integration,lightrag,memgraph,toolkit
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Requires-Python: >=3.10
Requires-Dist: lightrag-hku[api]==1.4.8.2
Requires-Dist: memgraph-toolbox>=0.1.7
Requires-Dist: numpy>=1.21.0
Provides-Extra: dev
Requires-Dist: black>=22.0.0; extra == 'dev'
Requires-Dist: isort>=5.0.0; extra == 'dev'
Requires-Dist: mypy>=1.0.0; extra == 'dev'
Requires-Dist: pytest-asyncio>=0.21.0; extra == 'dev'
Requires-Dist: pytest>=7.0.0; extra == 'dev'
Description-Content-Type: text/markdown

# 🔗 lightrag-memgraph

lightrag-memgraph is an integration that connects
[lightrag](https://github.com/HKUDS/LightRAG) and
[memgraph](https://github.com/memgraph/memgraph). The library began as a small
wrapper designed to specifically configure Memgraph within a pipeline that
processes unstructured data (various texts) and transforms it into an
ontology/entity schema graph. In other words, it enables you to extract and
enhance entities from unstructured documents, storing them in a graph for
powerful querying and analysis. Ideal for building knowledge graphs, improving
data discovery, and leveraging advanced AI techniques on top of your domain
data.

## Notes

- Entity/relationship extraction is high-quality, but also high-cost and
relatively slow.
- The goal over time is to expose time and cost metrics (e.g., $ per your
specific document page or chunk).
