rename storage to output

Author: dworthen

graphrag/api/index.py

@@ -52,7 +52,7 @@ async def build_index(
     list[PipelineRunResult]
         The list of pipeline run results
     """
-    is_update_run = bool(config.update_index_storage)
+    is_update_run = bool(config.update_index_output)
 
     if is_resume_run and is_update_run:
         msg = "Cannot resume and update a run at the same time."

graphrag/cli/index.py

@@ -77,7 +77,7 @@ def index_cli(
     """Run the pipeline with the given config."""
     cli_overrides = {}
     if output_dir:
-        cli_overrides["storage.base_dir"] = str(output_dir)
+        cli_overrides["output.base_dir"] = str(output_dir)
         cli_overrides["reporting.base_dir"] = str(output_dir)
     config = load_config(root_dir, config_filepath, cli_overrides)
 
@@ -106,18 +106,18 @@ def update_cli(
     """Run the pipeline with the given config."""
     cli_overrides = {}
     if output_dir:
-        cli_overrides["storage.base_dir"] = str(output_dir)
+        cli_overrides["output.base_dir"] = str(output_dir)
         cli_overrides["reporting.base_dir"] = str(output_dir)
     config = load_config(root_dir, config_filepath, cli_overrides)
 
-    # Check if update storage exist, if not configure it with default values
-    if not config.update_index_storage:
-        from graphrag.config.defaults import STORAGE_TYPE, UPDATE_STORAGE_BASE_DIR
-        from graphrag.config.models.storage_config import StorageConfig
+    # Check if update output exist, if not configure it with default values
+    if not config.update_index_output:
+        from graphrag.config.defaults import OUTPUT_TYPE, UPDATE_OUTPUT_BASE_DIR
+        from graphrag.config.models.output_config import OutputConfig
 
-        config.update_index_storage = StorageConfig(
-            type=STORAGE_TYPE,
-            base_dir=UPDATE_STORAGE_BASE_DIR,
+        config.update_index_output = OutputConfig(
+            type=OUTPUT_TYPE,
+            base_dir=UPDATE_OUTPUT_BASE_DIR,
         )
 
     _run_index(

graphrag/cli/main.py

@@ -165,7 +165,7 @@ def _index_cli(
     output: Annotated[
         Path | None,
         typer.Option(
-            help="Indexing pipeline output directory. Overrides storage.base_dir in the configuration file.",
+            help="Indexing pipeline output directory. Overrides output.base_dir in the configuration file.",
             dir_okay=True,
             writable=True,
             resolve_path=True,
@@ -226,7 +226,7 @@ def _update_cli(
     output: Annotated[
         Path | None,
         typer.Option(
-            help="Indexing pipeline output directory. Overrides storage.base_dir in the configuration file.",
+            help="Indexing pipeline output directory. Overrides output.base_dir in the configuration file.",
             dir_okay=True,
             writable=True,
             resolve_path=True,
@@ -236,7 +236,7 @@ def _update_cli(
     """
     Update an existing knowledge graph index.
 
-    Applies a default storage configuration (if not provided by config), saving the new index to the local file system in the `update_output` folder.
+    Applies a default output configuration (if not provided by config), saving the new index to the local file system in the `update_output` folder.
     """
     from graphrag.cli.index import update_cli
 

graphrag/cli/query.py

@@ -36,7 +36,7 @@ def run_global_search(
     root = root_dir.resolve()
     cli_overrides = {}
     if data_dir:
-        cli_overrides["storage.base_dir"] = str(data_dir)
+        cli_overrides["output.base_dir"] = str(data_dir)
     config = load_config(root, config_filepath, cli_overrides)
 
     dataframe_dict = _resolve_output_files(
@@ -121,7 +121,7 @@ def run_local_search(
     root = root_dir.resolve()
     cli_overrides = {}
     if data_dir:
-        cli_overrides["storage.base_dir"] = str(data_dir)
+        cli_overrides["output.base_dir"] = str(data_dir)
     config = load_config(root, config_filepath, cli_overrides)
 
     dataframe_dict = _resolve_output_files(
@@ -213,7 +213,7 @@ def run_drift_search(
     root = root_dir.resolve()
     cli_overrides = {}
     if data_dir:
-        cli_overrides["storage.base_dir"] = str(data_dir)
+        cli_overrides["output.base_dir"] = str(data_dir)
     config = load_config(root, config_filepath, cli_overrides)
 
     dataframe_dict = _resolve_output_files(
@@ -299,7 +299,7 @@ def run_basic_search(
     root = root_dir.resolve()
     cli_overrides = {}
     if data_dir:
-        cli_overrides["storage.base_dir"] = str(data_dir)
+        cli_overrides["output.base_dir"] = str(data_dir)
     config = load_config(root, config_filepath, cli_overrides)
 
     dataframe_dict = _resolve_output_files(
@@ -354,9 +354,9 @@ def _resolve_output_files(
 ) -> dict[str, pd.DataFrame]:
     """Read indexing output files to a dataframe dict."""
     dataframe_dict = {}
-    storage_config = config.storage.model_dump()  # type: ignore
+    output_config = config.output.model_dump()  # type: ignore
     storage_obj = StorageFactory().create_storage(
-        storage_type=storage_config["type"], kwargs=storage_config
+        storage_type=output_config["type"], kwargs=output_config
     )
     for name in output_list:
         df_value = asyncio.run(load_table_from_storage(name=name, storage=storage_obj))

graphrag/config/defaults.py

@@ -12,8 +12,8 @@
     InputFileType,
     InputType,
     LLMType,
+    OutputType,
     ReportingType,
-    StorageType,
     TextEmbeddingTarget,
 )
 from graphrag.vector_stores.factory import VectorStoreType
@@ -94,16 +94,16 @@
 SNAPSHOTS_GRAPHML = False
 SNAPSHOTS_EMBEDDINGS = False
 SNAPSHOTS_TRANSIENT = False
-STORAGE_BASE_DIR = "output"
-STORAGE_TYPE = StorageType.file
+OUTPUT_BASE_DIR = "output"
+OUTPUT_TYPE = OutputType.file
 SUMMARIZE_DESCRIPTIONS_MAX_LENGTH = 500
 SUMMARIZE_MODEL_ID = DEFAULT_CHAT_MODEL_ID
 UMAP_ENABLED = False
-UPDATE_STORAGE_BASE_DIR = "update_output"
+UPDATE_OUTPUT_BASE_DIR = "update_output"
 
 
 VECTOR_STORE_TYPE = VectorStoreType.LanceDB.value
-VECTOR_STORE_DB_URI = str(Path(STORAGE_BASE_DIR) / "lancedb")
+VECTOR_STORE_DB_URI = str(Path(OUTPUT_BASE_DIR) / "lancedb")
 VECTOR_STORE_CONTAINER_NAME = "default"
 VECTOR_STORE_OVERWRITE = True
 

graphrag/config/enums.py

@@ -53,17 +53,17 @@ def __repr__(self):
         return f'"{self.value}"'
 
 
-class StorageType(str, Enum):
-    """The storage type for the pipeline."""
+class OutputType(str, Enum):
+    """The output type for the pipeline."""
 
     file = "file"
-    """The file storage type."""
+    """The file output type."""
     memory = "memory"
-    """The memory storage type."""
+    """The memory output type."""
     blob = "blob"
-    """The blob storage type."""
+    """The blob output type."""
     cosmosdb = "cosmosdb"
-    """The cosmosdb storage type"""
+    """The cosmosdb output type"""
 
     def __repr__(self):
         """Get a string representation."""

graphrag/config/init_content.py

@@ -62,7 +62,7 @@
   overlap: {defs.CHUNK_OVERLAP}
   group_by_columns: [{",".join(defs.CHUNK_GROUP_BY_COLUMNS)}]
 
-### Storage settings ###
+### Output settings ###
 ## If blob storage is specified in the following four sections,
 ## connection_string and container_name must be provided
 
@@ -74,15 +74,15 @@
   type: {defs.REPORTING_TYPE.value} # or console, blob
   base_dir: "{defs.REPORTING_BASE_DIR}"
 
-storage:
-  type: {defs.STORAGE_TYPE.value} # one of [blob, cosmosdb, file]
-  base_dir: "{defs.STORAGE_BASE_DIR}"
+output:
+  type: {defs.OUTPUT_TYPE.value} # one of [blob, cosmosdb, file]
+  base_dir: "{defs.OUTPUT_BASE_DIR}"
 
 ## only turn this on if running `graphrag index` with custom settings
 ## we normally use `graphrag update` with the defaults
-update_index_storage:
-  # type: {defs.STORAGE_TYPE.value} # or blob
-  # base_dir: "{defs.UPDATE_STORAGE_BASE_DIR}"
+update_index_output:
+  # type: {defs.OUTPUT_TYPE.value} # or blob
+  # base_dir: "{defs.UPDATE_OUTPUT_BASE_DIR}"
 
 ### Workflow settings ###
 

graphrag/config/load_config.py

@@ -159,7 +159,7 @@ def load_config(
         If None, searches for config file in root.
     cli_overrides : dict[str, Any] | None
         A flat dictionary of cli overrides.
-        Example: {'storage.base_dir': 'override_value'}
+        Example: {'output.base_dir': 'override_value'}
 
     Returns
     -------

graphrag/config/models/graph_rag_config.py

@@ -23,9 +23,9 @@
 from graphrag.config.models.input_config import InputConfig
 from graphrag.config.models.language_model_config import LanguageModelConfig
 from graphrag.config.models.local_search_config import LocalSearchConfig
+from graphrag.config.models.output_config import OutputConfig
 from graphrag.config.models.reporting_config import ReportingConfig
 from graphrag.config.models.snapshots_config import SnapshotsConfig
-from graphrag.config.models.storage_config import StorageConfig
 from graphrag.config.models.summarize_descriptions_config import (
     SummarizeDescriptionsConfig,
 )
@@ -99,38 +99,38 @@ def _validate_reporting_base_dir(self) -> None:
                 (Path(self.root_dir) / self.reporting.base_dir).resolve()
             )
 
-    storage: StorageConfig = Field(
-        description="The storage configuration.", default=StorageConfig()
+    output: OutputConfig = Field(
+        description="The output configuration.", default=OutputConfig()
     )
-    """The storage configuration."""
+    """The output configuration."""
 
-    def _validate_storage_base_dir(self) -> None:
-        """Validate the storage base directory."""
-        if self.storage.type == defs.StorageType.file:
-            if self.storage.base_dir.strip() == "":
-                msg = "Storage base directory is required for file storage. Please rerun `graphrag init` and set the storage configuration."
+    def _validate_output_base_dir(self) -> None:
+        """Validate the output base directory."""
+        if self.output.type == defs.OutputType.file:
+            if self.output.base_dir.strip() == "":
+                msg = "output base directory is required for file output. Please rerun `graphrag init` and set the output configuration."
                 raise ValueError(msg)
-            self.storage.base_dir = str(
-                (Path(self.root_dir) / self.storage.base_dir).resolve()
+            self.output.base_dir = str(
+                (Path(self.root_dir) / self.output.base_dir).resolve()
             )
 
-    update_index_storage: StorageConfig | None = Field(
-        description="The storage configuration for the updated index.",
+    update_index_output: OutputConfig | None = Field(
+        description="The output configuration for the updated index.",
         default=None,
     )
-    """The storage configuration for the updated index."""
+    """The output configuration for the updated index."""
 
-    def _validate_update_index_storage_base_dir(self) -> None:
-        """Validate the update index storage base directory."""
+    def _validate_update_index_output_base_dir(self) -> None:
+        """Validate the update index output base directory."""
         if (
-            self.update_index_storage
-            and self.update_index_storage.type == defs.StorageType.file
+            self.update_index_output
+            and self.update_index_output.type == defs.OutputType.file
         ):
-            if self.update_index_storage.base_dir.strip() == "":
-                msg = "Update index storage base directory is required for file storage. Please rerun `graphrag init` and set the update index storage configuration."
+            if self.update_index_output.base_dir.strip() == "":
+                msg = "Update index output base directory is required for file output. Please rerun `graphrag init` and set the update index output configuration."
                 raise ValueError(msg)
-            self.update_index_storage.base_dir = str(
-                (Path(self.root_dir) / self.update_index_storage.base_dir).resolve()
+            self.update_index_output.base_dir = str(
+                (Path(self.root_dir) / self.update_index_output.base_dir).resolve()
             )
 
     cache: CacheConfig = Field(
@@ -269,7 +269,7 @@ def _validate_model(self):
         self._validate_root_dir()
         self._validate_models()
         self._validate_reporting_base_dir()
-        self._validate_storage_base_dir()
-        self._validate_update_index_storage_base_dir()
+        self._validate_output_base_dir()
+        self._validate_update_index_output_base_dir()
         self._validate_vector_store_db_uri()
         return self

graphrag/config/models/storage_config.py graphrag/config/models/output_config.pygraphrag/config/models/storage_config.py renamed to graphrag/config/models/output_config.py

@@ -6,18 +6,18 @@
 from pydantic import BaseModel, Field
 
 import graphrag.config.defaults as defs
-from graphrag.config.enums import StorageType
+from graphrag.config.enums import OutputType
 
 
-class StorageConfig(BaseModel):
-    """The default configuration section for Storage."""
+class OutputConfig(BaseModel):
+    """The default configuration section for Output."""
 
-    type: StorageType = Field(
-        description="The storage type to use.", default=defs.STORAGE_TYPE
+    type: OutputType = Field(
+        description="The output type to use.", default=defs.OUTPUT_TYPE
     )
     base_dir: str = Field(
-        description="The base directory for the storage.",
-        default=defs.STORAGE_BASE_DIR,
+        description="The base directory for the output.",
+        default=defs.OUTPUT_BASE_DIR,
     )
     connection_string: str | None = Field(
         description="The storage connection string to use.", default=None