Merge branch 'v3/main' into graphrag-config

dworthen · dworthen · commit 72484f148dae · 2025-11-04T13:10:33.000-08:00
diff --git a/docs/examples_notebooks/api_overview.ipynb b/docs/examples_notebooks/api_overview.ipynb
@@ -28,10 +28,11 @@
     "from pathlib import Path\n",
     "from pprint import pprint\n",
     "\n",
-    "import graphrag.api as api\n",
     "import pandas as pd\n",
     "from graphrag.config.load_config import load_config\n",
-    "from graphrag.index.typing.pipeline_run_result import PipelineRunResult"
+    "from graphrag.index.typing.pipeline_run_result import PipelineRunResult\n",
+    "\n",
+    "import graphrag.api as api"
    ]
   },
   {
diff --git a/docs/examples_notebooks/input_documents.ipynb b/docs/examples_notebooks/input_documents.ipynb
@@ -30,10 +30,11 @@
     "from pathlib import Path\n",
     "from pprint import pprint\n",
     "\n",
-    "import graphrag.api as api\n",
     "import pandas as pd\n",
     "from graphrag.config.load_config import load_config\n",
-    "from graphrag.index.typing.pipeline_run_result import PipelineRunResult"
+    "from graphrag.index.typing.pipeline_run_result import PipelineRunResult\n",
+    "\n",
+    "import graphrag.api as api"
    ]
   },
   {
diff --git a/packages/graphrag-common/README.md b/packages/graphrag-common/README.md
@@ -1,9 +1,11 @@
-# GraphRAG Factory
+# GraphRAG Common
+
+## Factory module
 
 ```python
 from abc import ABC, abstractmethod
 
-from graphrag_factory import Factory
+from graphrag_common.factory import Factory
 
 class SampleABC(ABC):
 
diff --git a/packages/graphrag-common/graphrag_common/__init__.py b/packages/graphrag-common/graphrag_common/__init__.py
@@ -0,0 +1,4 @@
+# Copyright (c) 2024 Microsoft Corporation.
+# Licensed under the MIT License
+
+"""GraphRAG Common package."""
diff --git a/packages/graphrag-common/graphrag_common/factory/__init__.py b/packages/graphrag-common/graphrag_common/factory/__init__.py
@@ -1,8 +1,8 @@
 # Copyright (c) 2024 Microsoft Corporation.
 # Licensed under the MIT License
 
-"""The GraphRAG Factory package."""
+"""The GraphRAG factory module."""
 
-from graphrag_factory.factory import Factory
+from graphrag_common.factory.factory import Factory
 
 __all__ = ["Factory"]
diff --git a/packages/graphrag-common/graphrag_common/factory/factory.py b/packages/graphrag-common/graphrag_common/factory/factory.py
@@ -5,12 +5,27 @@
 
 from abc import ABC
 from collections.abc import Callable
+<<<<<<<< HEAD:packages/graphrag-factory/graphrag_factory/factory.py
+========
+from dataclasses import dataclass
+>>>>>>>> v3/main:packages/graphrag-common/graphrag_common/factory/factory.py
 from typing import Any, ClassVar, Generic, Literal, TypeVar
 
 T = TypeVar("T", covariant=True)
 
 ServiceScope = Literal["singleton", "transient"]
 
+<<<<<<<< HEAD:packages/graphrag-factory/graphrag_factory/factory.py
+========
+
+@dataclass
+class _ServiceDescriptor(Generic[T]):
+    """Descriptor for a service."""
+
+    scope: ServiceScope
+    initializer: Callable[..., T]
+
+>>>>>>>> v3/main:packages/graphrag-common/graphrag_common/factory/factory.py
 
 class Factory(ABC, Generic[T]):
     """Abstract base class for factories."""
@@ -25,9 +40,13 @@ def __new__(cls, *args: Any, **kwargs: Any) -> "Factory":
 
     def __init__(self):
         if not hasattr(self, "_initialized"):
+<<<<<<<< HEAD:packages/graphrag-factory/graphrag_factory/factory.py
             self._service_initializers: dict[
                 str, tuple[ServiceScope, Callable[..., T]]
             ] = {}
+========
+            self._service_initializers: dict[str, _ServiceDescriptor[T]] = {}
+>>>>>>>> v3/main:packages/graphrag-common/graphrag_common/factory/factory.py
             self._initialized_services: dict[str, T] = {}
             self._initialized = True
 
@@ -54,7 +73,11 @@ def register(
             initializer: A callable that creates an instance of T.
             scope: The service scope, either 'singleton' or 'transient'.
         """
+<<<<<<<< HEAD:packages/graphrag-factory/graphrag_factory/factory.py
         self._service_initializers[strategy] = (scope, initializer)
+========
+        self._service_initializers[strategy] = _ServiceDescriptor(scope, initializer)
+>>>>>>>> v3/main:packages/graphrag-common/graphrag_common/factory/factory.py
 
     def create(self, strategy: str, init_args: dict[str, Any] | None = None) -> T:
         """
@@ -77,12 +100,23 @@ def create(self, strategy: str, init_args: dict[str, Any] | None = None) -> T:
             msg = f"Strategy '{strategy}' is not registered. Registered strategies are: {', '.join(list(self._service_initializers.keys()))}"
             raise ValueError(msg)
 
+<<<<<<<< HEAD:packages/graphrag-factory/graphrag_factory/factory.py
         scope, service_initializer = self._service_initializers[strategy]
         if scope == "singleton":
             if strategy not in self._initialized_services:
                 self._initialized_services[strategy] = service_initializer(
+========
+        service_descriptor = self._service_initializers[strategy]
+        if service_descriptor.scope == "singleton":
+            if strategy not in self._initialized_services:
+                self._initialized_services[strategy] = service_descriptor.initializer(
+>>>>>>>> v3/main:packages/graphrag-common/graphrag_common/factory/factory.py
                     **(init_args or {})
                 )
             return self._initialized_services[strategy]
 
+<<<<<<<< HEAD:packages/graphrag-factory/graphrag_factory/factory.py
         return service_initializer(**(init_args or {}))
+========
+        return service_descriptor.initializer(**(init_args or {}))
+>>>>>>>> v3/main:packages/graphrag-common/graphrag_common/factory/factory.py
diff --git a/packages/graphrag-common/graphrag_common/py.typed b/packages/graphrag-common/graphrag_common/py.typed
diff --git a/packages/graphrag-common/pyproject.toml b/packages/graphrag-common/pyproject.toml
@@ -1,7 +1,7 @@
 [project]
-name = "graphrag-factory"
+name = "graphrag-common"
 version = "2.7.0"
-description = "GraphRAG: A graph-based retrieval-augmented generation (RAG) system."
+description = "Common utilities and types for GraphRAG"
 authors = [
     {name = "Alonso Guevara Fernández", email = "alonsog@microsoft.com"},
     {name = "Andrés Morales Esquivel", email = "andresmor@microsoft.com"},
diff --git a/packages/graphrag/graphrag/cache/factory.py b/packages/graphrag/graphrag/cache/factory.py
@@ -5,7 +5,7 @@
 
 from __future__ import annotations
 
-from graphrag_factory import Factory
+from graphrag_common.factory import Factory
 
 from graphrag.cache.json_pipeline_cache import JsonPipelineCache
 from graphrag.cache.memory_pipeline_cache import InMemoryCache
diff --git a/packages/graphrag/graphrag/index/input/factory.py b/packages/graphrag/graphrag/index/input/factory.py
@@ -5,7 +5,7 @@
 
 import logging
 
-from graphrag_factory import Factory
+from graphrag_common.factory import Factory
 
 from graphrag.config.enums import InputFileType
 from graphrag.index.input.csv import CSVFileReader
diff --git a/packages/graphrag/graphrag/language_model/factory.py b/packages/graphrag/graphrag/language_model/factory.py
@@ -3,7 +3,7 @@
 
 """A package containing a factory for supported llm types."""
 
-from graphrag_factory import Factory
+from graphrag_common.factory import Factory
 
 from graphrag.config.enums import ModelType
 from graphrag.language_model.protocol.base import ChatModel, EmbeddingModel
diff --git a/packages/graphrag/graphrag/language_model/providers/litellm/services/rate_limiter/rate_limiter_factory.py b/packages/graphrag/graphrag/language_model/providers/litellm/services/rate_limiter/rate_limiter_factory.py
@@ -3,7 +3,7 @@
 
 """LiteLLM Rate Limiter Factory."""
 
-from graphrag_factory import Factory
+from graphrag_common.factory import Factory
 
 from graphrag.language_model.providers.litellm.services.rate_limiter.rate_limiter import (
     RateLimiter,
diff --git a/packages/graphrag/graphrag/language_model/providers/litellm/services/retry/retry_factory.py b/packages/graphrag/graphrag/language_model/providers/litellm/services/retry/retry_factory.py
@@ -3,7 +3,7 @@
 
 """LiteLLM Retry Factory."""
 
-from graphrag_factory import Factory
+from graphrag_common.factory import Factory
 
 from graphrag.language_model.providers.litellm.services.retry.exponential_retry import (
     ExponentialRetry,
diff --git a/packages/graphrag/graphrag/logger/factory.py b/packages/graphrag/graphrag/logger/factory.py
@@ -8,7 +8,7 @@
 import logging
 from pathlib import Path
 
-from graphrag_factory import Factory
+from graphrag_common.factory import Factory
 
 from graphrag.config.enums import ReportingType
 
diff --git a/packages/graphrag/graphrag/storage/factory.py b/packages/graphrag/graphrag/storage/factory.py
@@ -5,7 +5,7 @@
 
 from __future__ import annotations
 
-from graphrag_factory import Factory
+from graphrag_common.factory import Factory
 
 from graphrag.config.enums import StorageType
 from graphrag.storage.blob_pipeline_storage import BlobPipelineStorage
diff --git a/packages/graphrag/graphrag/vector_stores/factory.py b/packages/graphrag/graphrag/vector_stores/factory.py
@@ -5,7 +5,7 @@
 
 from __future__ import annotations
 
-from graphrag_factory import Factory
+from graphrag_common.factory import Factory
 
 from graphrag.config.enums import VectorStoreType
 from graphrag.vector_stores.azure_ai_search import AzureAISearchVectorStore
diff --git a/packages/graphrag/pyproject.toml b/packages/graphrag/pyproject.toml
@@ -41,7 +41,7 @@ dependencies = [
     "devtools>=0.12.2",
     "environs>=11.0.0",
     "graphrag-config==2.7.0",
-    "graphrag-factory==2.7.0",
+    "graphrag-common==2.7.0",
     "graspologic-native>=1.2.5",
     "json-repair>=0.30.3",
     "lancedb>=0.17.0",
diff --git a/pyproject.toml b/pyproject.toml
@@ -53,7 +53,7 @@ package = false
 members = ["packages/*"]
 
 [tool.uv.sources]
-graphrag-factory = { workspace = true }
+graphrag-common = { workspace = true }
 graphrag-config = { workspace = true }
 
 # Keep poethepoet for task management to minimize changes
@@ -69,7 +69,7 @@ _semversioner_release = "semversioner release"
 _semversioner_changelog = "semversioner changelog > CHANGELOG.md"
 # Add more update toml tasks as packages are added
 _semversioner_update_graphrag_toml_version = "update-toml update --file packages/graphrag/pyproject.toml --path project.version --value $(uv run semversioner current-version)"
-_semversioner_update_graphrag_factory_toml_version = "update-toml update --file packages/graphrag-factory/pyproject.toml --path project.version --value $(uv run semversioner current-version)"
+_semversioner_update_graphrag_common_toml_version = "update-toml update --file packages/graphrag-common/pyproject.toml --path project.version --value $(uv run semversioner current-version)"
 _semversioner_update_graphrag_config_toml_version = "update-toml update --file packages/graphrag-config/pyproject.toml --path project.version --value $(uv run semversioner current-version)"
 _semversioner_update_workspace_dependency_versions = "python -m scripts.update_workspace_dependency_versions"
 semversioner_add = "semversioner add-change"
@@ -104,7 +104,7 @@ sequence = [
     '_semversioner_changelog',
     # Add more update toml tasks as packages are added
     '_semversioner_update_graphrag_toml_version',
-    '_semversioner_update_graphrag_factory_toml_version',
+    '_semversioner_update_graphrag_common_toml_version',
     '_semversioner_update_graphrag_config_toml_version',
     '_semversioner_update_workspace_dependency_versions',
     '_sync',
@@ -220,7 +220,12 @@ convention = "numpy"
 
 # https://github.com/microsoft/pyright/blob/9f81564a4685ff5c55edd3959f9b39030f590b2f/docs/configuration.md#sample-pyprojecttoml-file
 [tool.pyright]
-include = ["packages/graphrag/graphrag", "packages/graphrag-factory/graphrag_factory", "packages/graphrag-config/graphrag_config", "tests"]
+include = [
+    "packages/graphrag/graphrag", 
+    "packages/graphrag-common/graphrag_common", 
+    "packages/graphrag-config/graphrag_config", 
+    "tests"
+]
 exclude = ["**/node_modules", "**/__pycache__"]
 
 [tool.pytest.ini_options]
diff --git a/tests/unit/graphrag_factory/test_factory.py b/tests/unit/graphrag_factory/test_factory.py
@@ -5,7 +5,7 @@
 
 from abc import ABC, abstractmethod
 
-from graphrag_factory import Factory
+from graphrag_common.factory import Factory
 
 
 class TestABC(ABC):
diff --git a/uv.lock b/uv.lock

Original file line number	Diff line number	Diff line change
`@@ -28,10 +28,11 @@`
`28`	`28`	`"from pathlib import Path\n",`
`29`	`29`	`"from pprint import pprint\n",`
`30`	`30`	`"\n",`
`31`		`- "import graphrag.api as api\n",`
`32`	`31`	`"import pandas as pd\n",`
`33`	`32`	`"from graphrag.config.load_config import load_config\n",`
`34`		`- "from graphrag.index.typing.pipeline_run_result import PipelineRunResult"`
	`33`	`+ "from graphrag.index.typing.pipeline_run_result import PipelineRunResult\n",`
	`34`	`+ "\n",`
	`35`	`+ "import graphrag.api as api"`
`35`	`36`	`]`
`36`	`37`	`},`
`37`	`38`	`{`
Original file line number	Diff line number	Diff line change
`@@ -30,10 +30,11 @@`
`30`	`30`	`"from pathlib import Path\n",`
`31`	`31`	`"from pprint import pprint\n",`
`32`	`32`	`"\n",`
`33`		`- "import graphrag.api as api\n",`
`34`	`33`	`"import pandas as pd\n",`
`35`	`34`	`"from graphrag.config.load_config import load_config\n",`
`36`		`- "from graphrag.index.typing.pipeline_run_result import PipelineRunResult"`
	`35`	`+ "from graphrag.index.typing.pipeline_run_result import PipelineRunResult\n",`
	`36`	`+ "\n",`
	`37`	`+ "import graphrag.api as api"`
`37`	`38`	`]`
`38`	`39`	`},`
`39`	`40`	`{`