Metadata-Version: 2.4
Name: graphrag-vectors
Version: 3.0.2
Summary: GraphRAG vector store package.
Project-URL: Source, https://github.com/microsoft/graphrag
Author: Mónica Carvajal
Author-email: Alonso Guevara Fernández <alonsog@microsoft.com>, Andrés Morales Esquivel <andresmor@microsoft.com>, Chris Trevino <chtrevin@microsoft.com>, David Tittsworth <datittsw@microsoft.com>, Dayenne de Souza <ddesouza@microsoft.com>, Derek Worthen <deworthe@microsoft.com>, Gaudy Blanco Meneses <gaudyb@microsoft.com>, Ha Trinh <trinhha@microsoft.com>, Jonathan Larson <jolarso@microsoft.com>, Josh Bradley <joshbradley@microsoft.com>, Kate Lytvynets <kalytv@microsoft.com>, Kenny Zhang <zhangken@microsoft.com>, Nathan Evans <naevans@microsoft.com>, Rodrigo Racanicci <rracanicci@microsoft.com>, Sarah Smith <smithsarah@microsoft.com>
License: MIT
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Requires-Python: <3.14,>=3.11
Requires-Dist: azure-core~=1.32
Requires-Dist: azure-cosmos~=4.9
Requires-Dist: azure-identity~=1.25
Requires-Dist: azure-search-documents~=11.6
Requires-Dist: graphrag-common==3.0.2
Requires-Dist: lancedb~=0.24.1
Requires-Dist: numpy~=2.1
Requires-Dist: pyarrow~=22.0
Requires-Dist: pydantic~=2.10
Description-Content-Type: text/markdown

# GraphRAG Vectors

This package provides vector store implementations for GraphRAG with support for multiple backends including LanceDB, Azure AI Search, and Azure Cosmos DB. It offers both a convenient configuration-driven API and direct factory access for creating and managing vector stores with flexible index schema definitions.

## Basic usage with the utility function (recommended)

This demonstrates the recommended approach to create a vector store using the create_vector_store convenience function with configuration objects that specify the store type and index schema. The example shows setting up a LanceDB vector store with a defined index configuration, then connecting to it and creating the index for vector operations.

[Open the notebook to explore the basic usage with utility function example code](example_notebooks/basic_usage_with_utility_function_example.ipynb)

## Basic usage implementing the factory directly

This example shows a different approach to create vector stores by directly using the vector_store_factory with enum types and dictionary-based initialization arguments. This method provides more direct control over the factory creation process while bypassing the convenience function layer.

[Open the notebook to explore the basic usage using factory directly example code](example_notebooks/basic_usage_factory_example.ipynb)

## Supported Vector Stores

- **LanceDB**: Local vector database
- **Azure AI Search**: Azure's managed search service with vector capabilities
- **Azure Cosmos DB**: Azure's NoSQL database with vector search support

## Custom Vector Store

You can register custom vector store implementations:

[Open the notebook to explore the custom vector example code](example_notebooks/basic_usage_factory_example.ipynb)

## Configuration

Vector stores are configured using:
- `VectorStoreConfig`: baseline parameters for the store
- `IndexSchema`: Schema configuration for the specific index to create/connect to (index name, field names, vector size)
