cleanup logging factory

graphrag/api/index.py

@@ -19,7 +19,7 @@ from graphrag.config.models.graph_rag_config import GraphRagConfig
 from graphrag.index.create_pipeline_config import create_pipeline_config
 from graphrag.index.run import run_pipeline_with_config
 from graphrag.index.typing import PipelineRunResult
-from graphrag.logging.base import ProgressReporter
+from graphrag.logger.base import ProgressLogger
 from graphrag.vector_stores.factory import VectorStoreType
 
 
@@ -29,7 +29,7 @@ async def build_index(
     is_resume_run: bool = False,
     memory_profile: bool = False,
     callbacks: list[WorkflowCallbacks] | None = None,
-    progress_reporter: ProgressReporter | None = None,
+    progress_reporter: ProgressLogger | None = None,
 ) -> list[PipelineRunResult]:
     """Run the pipeline with the given configuration.
 
@@ -45,7 +45,7 @@ async def build_index(
         Whether to enable memory profiling.
     callbacks : list[WorkflowCallbacks] | None default=None
         A list of callbacks to register.
-    progress_reporter : ProgressReporter | None default=None
+    progress_reporter : ProgressLogger | None default=None
         The progress reporter.
 
     Returns

graphrag/api/prompt_tune.py

@@ -16,7 +16,7 @@ from pydantic import PositiveInt, validate_call
 
 from graphrag.config.models.graph_rag_config import GraphRagConfig
 from graphrag.index.llm.load_llm import load_llm
-from graphrag.logging.print_progress import PrintProgressReporter
+from graphrag.logger.print_progress import PrintProgressLogger
 from graphrag.prompt_tune.defaults import MAX_TOKEN_COUNT
 from graphrag.prompt_tune.generator.community_report_rating import (
     generate_community_report_rating,
@@ -80,7 +80,7 @@ async def generate_indexing_prompts(
     -------
     tuple[str, str, str]: entity extraction prompt, entity summarization prompt, community summarization prompt
     """
-    reporter = PrintProgressReporter("")
+    reporter = PrintProgressLogger("")
 
     # Retrieve documents
     doc_list = await load_docs_in_chunks(

graphrag/api/query.py

@@ -29,7 +29,7 @@ from graphrag.index.config.embeddings import (
     community_full_content_embedding,
     entity_description_embedding,
 )
-from graphrag.logging.print_progress import PrintProgressReporter
+from graphrag.logger.print_progress import PrintProgressLogger
 from graphrag.query.factory import (
     get_drift_search_engine,
     get_global_search_engine,
@@ -52,7 +52,7 @@ from graphrag.vector_stores.factory import VectorStoreFactory, VectorStoreType
 if TYPE_CHECKING:
     from graphrag.query.structured_search.base import SearchResult
 
-reporter = PrintProgressReporter("")
+reporter = PrintProgressLogger("")
 
 
 @validate_call(config={"arbitrary_types_allowed": True})

graphrag/callbacks/progress_workflow_callbacks.py

@@ -7,16 +7,16 @@ from typing import Any
 
 from datashaper import ExecutionNode, NoopWorkflowCallbacks, Progress, TableContainer
 
-from graphrag.logging.base import ProgressReporter
+from graphrag.logger.base import ProgressLogger
 
 
 class ProgressWorkflowCallbacks(NoopWorkflowCallbacks):
-    """A callbackmanager that delegates to a ProgressReporter."""
+    """A callbackmanager that delegates to a ProgressLogger."""
 
-    _root_progress: ProgressReporter
-    _progress_stack: list[ProgressReporter]
+    _root_progress: ProgressLogger
+    _progress_stack: list[ProgressLogger]
 
-    def __init__(self, progress: ProgressReporter) -> None:
+    def __init__(self, progress: ProgressLogger) -> None:
         """Create a new ProgressWorkflowCallbacks."""
         self._progress = progress
         self._progress_stack = [progress]
@@ -28,7 +28,7 @@ class ProgressWorkflowCallbacks(NoopWorkflowCallbacks):
         self._progress_stack.append(self._latest.child(name))
 
     @property
-    def _latest(self) -> ProgressReporter:
+    def _latest(self) -> ProgressLogger:
         return self._progress_stack[-1]
 
     def on_workflow_start(self, name: str, instance: object) -> None:

graphrag/cli/index.py

@@ -16,9 +16,8 @@ from graphrag.config.load_config import load_config
 from graphrag.config.logging import enable_logging_with_config
 from graphrag.config.resolve_path import resolve_paths
 from graphrag.index.validate_config import validate_config_names
-from graphrag.logging.base import ProgressReporter
-from graphrag.logging.factory import create_progress_reporter
-from graphrag.logging.types import ReporterType
+from graphrag.logger.base import ProgressLogger
+from graphrag.logger.factory import LoggerFactory, LoggerType
 from graphrag.utils.cli import redact
 
 # Ignore warnings from numba
@@ -27,7 +26,7 @@ warnings.filterwarnings("ignore", message=".*NumbaDeprecationWarning.*")
 log = logging.getLogger(__name__)
 
 
-def _logger(reporter: ProgressReporter):
+def _logger(reporter: ProgressLogger):
     def info(msg: str, verbose: bool = False):
         log.info(msg)
         if verbose:
@@ -46,7 +45,7 @@ def _logger(reporter: ProgressReporter):
     return info, error, success
 
 
-def _register_signal_handlers(reporter: ProgressReporter):
+def _register_signal_handlers(reporter: ProgressLogger):
     import signal
 
     def handle_signal(signum, _):
@@ -70,7 +69,7 @@ def index_cli(
     resume: str | None,
     memprofile: bool,
     cache: bool,
-    reporter: ReporterType,
+    reporter: LoggerType,
     config_filepath: Path | None,
     dry_run: bool,
     skip_validation: bool,
@@ -97,7 +96,7 @@ def update_cli(
     verbose: bool,
     memprofile: bool,
     cache: bool,
-    reporter: ReporterType,
+    reporter: LoggerType,
     config_filepath: Path | None,
     skip_validation: bool,
     output_dir: Path | None,
@@ -139,7 +138,7 @@ def _run_index(
     skip_validation,
     output_dir,
 ):
-    progress_reporter = create_progress_reporter(reporter)
+    progress_reporter = LoggerFactory.create_logger(reporter)
     info, error, success = _logger(progress_reporter)
     run_id = resume or time.strftime("%Y%m%d-%H%M%S")
 

graphrag/cli/initialize.py

@@ -6,8 +6,7 @@
 from pathlib import Path
 
 from graphrag.config.init_content import INIT_DOTENV, INIT_YAML
-from graphrag.logging.factory import create_progress_reporter
-from graphrag.logging.types import ReporterType
+from graphrag.logger.factory import LoggerFactory, LoggerType
 from graphrag.prompts.index.claim_extraction import CLAIM_EXTRACTION_PROMPT
 from graphrag.prompts.index.community_report import (
     COMMUNITY_REPORT_PROMPT,
@@ -28,7 +27,7 @@ from graphrag.prompts.query.question_gen_system_prompt import QUESTION_SYSTEM_PR
 
 def initialize_project_at(path: Path) -> None:
     """Initialize the project at the given path."""
-    progress_reporter = create_progress_reporter(ReporterType.RICH)
+    progress_reporter = LoggerFactory.create_logger(LoggerType.RICH)
     progress_reporter.info(f"Initializing project at {path}")
     root = Path(path)
     if not root.exists():

graphrag/cli/main.py

@@ -12,7 +12,7 @@ from typing import Annotated
 
 import typer
 
-from graphrag.logging.types import ReporterType
+from graphrag.logger.types import LoggerType
 from graphrag.prompt_tune.defaults import (
     MAX_TOKEN_COUNT,
     MIN_CHUNK_SIZE,
@@ -146,8 +146,8 @@ def _index_cli(
         str | None, typer.Option(help="Resume a given indexing run")
     ] = None,
     reporter: Annotated[
-        ReporterType, typer.Option(help="The progress reporter to use.")
-    ] = ReporterType.RICH,
+        LoggerType, typer.Option(help="The progress reporter to use.")
+    ] = LoggerType.RICH,
     dry_run: Annotated[
         bool,
         typer.Option(
@@ -180,7 +180,7 @@ def _index_cli(
         resume=resume,
         memprofile=memprofile,
         cache=cache,
-        reporter=ReporterType(reporter),
+        reporter=LoggerType(reporter),
         config_filepath=config,
         dry_run=dry_run,
         skip_validation=skip_validation,
@@ -213,8 +213,8 @@ def _update_cli(
         bool, typer.Option(help="Run the indexing pipeline with memory profiling")
     ] = False,
     reporter: Annotated[
-        ReporterType, typer.Option(help="The progress reporter to use.")
-    ] = ReporterType.RICH,
+        LoggerType, typer.Option(help="The progress reporter to use.")
+    ] = LoggerType.RICH,
     cache: Annotated[bool, typer.Option(help="Use LLM cache.")] = True,
     skip_validation: Annotated[
         bool,
@@ -244,7 +244,7 @@ def _update_cli(
         verbose=verbose,
         memprofile=memprofile,
         cache=cache,
-        reporter=ReporterType(reporter),
+        reporter=LoggerType(reporter),
         config_filepath=config,
         skip_validation=skip_validation,
         output_dir=output,

graphrag/cli/prompt_tune.py

@@ -7,7 +7,7 @@ from pathlib import Path
 
 import graphrag.api as api
 from graphrag.config.load_config import load_config
-from graphrag.logging.print_progress import PrintProgressReporter
+from graphrag.logger.print_progress import PrintProgressLogger
 from graphrag.prompt_tune.generator.community_report_summarization import (
     COMMUNITY_SUMMARIZATION_FILENAME,
 )
@@ -52,7 +52,7 @@ async def prompt_tune(
     - k: The number of documents to select when using auto selection method.
     - min_examples_required: The minimum number of examples required for entity extraction prompts.
     """
-    reporter = PrintProgressReporter("")
+    reporter = PrintProgressLogger("")
     root_path = Path(root).resolve()
     graph_config = load_config(root_path, config)
 

graphrag/cli/query.py

@@ -14,11 +14,11 @@ from graphrag.config.load_config import load_config
 from graphrag.config.models.graph_rag_config import GraphRagConfig
 from graphrag.config.resolve_path import resolve_paths
 from graphrag.index.create_pipeline_config import create_pipeline_config
-from graphrag.logging.print_progress import PrintProgressReporter
+from graphrag.logger.print_progress import PrintProgressLogger
 from graphrag.storage.factory import StorageFactory
 from graphrag.utils.storage import _load_table_from_storage
 
-reporter = PrintProgressReporter("")
+reporter = PrintProgressLogger("")
 
 
 def run_global_search(

graphrag/index/input/csv.py

@@ -12,7 +12,7 @@ import pandas as pd
 
 from graphrag.index.config.input import PipelineCSVInputConfig, PipelineInputConfig
 from graphrag.index.utils.hashing import gen_sha512_hash
-from graphrag.logging.base import ProgressReporter
+from graphrag.logger.base import ProgressLogger
 from graphrag.storage.pipeline_storage import PipelineStorage
 
 log = logging.getLogger(__name__)
@@ -24,7 +24,7 @@ input_type = "csv"
 
 async def load(
     config: PipelineInputConfig,
-    progress: ProgressReporter | None,
+    progress: ProgressLogger | None,
     storage: PipelineStorage,
 ) -> pd.DataFrame:
     """Load csv inputs from a directory."""

graphrag/index/input/factory.py

@@ -17,8 +17,8 @@ from graphrag.index.input.csv import input_type as csv
 from graphrag.index.input.csv import load as load_csv
 from graphrag.index.input.text import input_type as text
 from graphrag.index.input.text import load as load_text
-from graphrag.logging.base import ProgressReporter
-from graphrag.logging.null_progress import NullProgressReporter
+from graphrag.logger.base import ProgressLogger
+from graphrag.logger.null_progress import NullProgressLogger
 from graphrag.storage.blob_pipeline_storage import BlobPipelineStorage
 from graphrag.storage.file_pipeline_storage import FilePipelineStorage
 
@@ -31,13 +31,13 @@ loaders: dict[str, Callable[..., Awaitable[pd.DataFrame]]] = {
 
 async def create_input(
     config: PipelineInputConfig | InputConfig,
-    progress_reporter: ProgressReporter | None = None,
+    progress_reporter: ProgressLogger | None = None,
     root_dir: str | None = None,
 ) -> pd.DataFrame:
     """Instantiate input data for a pipeline."""
     root_dir = root_dir or ""
     log.info("loading input from root_dir=%s", config.base_dir)
-    progress_reporter = progress_reporter or NullProgressReporter()
+    progress_reporter = progress_reporter or NullProgressLogger()
 
     if config is None:
         msg = "No input specified!"

graphrag/index/input/text.py

@@ -12,7 +12,7 @@ import pandas as pd
 
 from graphrag.index.config.input import PipelineInputConfig
 from graphrag.index.utils.hashing import gen_sha512_hash
-from graphrag.logging.base import ProgressReporter
+from graphrag.logger.base import ProgressLogger
 from graphrag.storage.pipeline_storage import PipelineStorage
 
 DEFAULT_FILE_PATTERN = re.compile(
@@ -24,7 +24,7 @@ log = logging.getLogger(__name__)
 
 async def load(
     config: PipelineInputConfig,
-    progress: ProgressReporter | None,
+    progress: ProgressLogger | None,
     storage: PipelineStorage,
 ) -> pd.DataFrame:
     """Load text inputs from a directory."""

graphrag/index/run/run.py

@@ -48,8 +48,8 @@ from graphrag.index.workflows import (
     WorkflowDefinitions,
     load_workflows,
 )
-from graphrag.logging.base import ProgressReporter
-from graphrag.logging.null_progress import NullProgressReporter
+from graphrag.logger.base import ProgressLogger
+from graphrag.logger.null_progress import NullProgressLogger
 from graphrag.storage.factory import StorageFactory
 from graphrag.storage.pipeline_storage import PipelineStorage
 
@@ -64,7 +64,7 @@ async def run_pipeline_with_config(
     update_index_storage: PipelineStorage | None = None,
     cache: PipelineCache | None = None,
     callbacks: list[WorkflowCallbacks] | None = None,
-    progress_reporter: ProgressReporter | None = None,
+    progress_reporter: ProgressLogger | None = None,
     input_post_process_steps: list[PipelineWorkflowStep] | None = None,
     additional_verbs: VerbDefinitions | None = None,
     additional_workflows: WorkflowDefinitions | None = None,
@@ -99,7 +99,7 @@ async def run_pipeline_with_config(
     config = _apply_substitutions(config, run_id)
     root_dir = config.root_dir or ""
 
-    progress_reporter = progress_reporter or NullProgressReporter()
+    progress_reporter = progress_reporter or NullProgressLogger()
     storage_config = config.storage.model_dump()  # type: ignore
     storage = storage or StorageFactory.create_storage(
         storage_type=storage_config["type"],  # type: ignore
@@ -197,7 +197,7 @@ async def run_pipeline(
     storage: PipelineStorage | None = None,
     cache: PipelineCache | None = None,
     callbacks: list[WorkflowCallbacks] | None = None,
-    progress_reporter: ProgressReporter | None = None,
+    progress_reporter: ProgressLogger | None = None,
     input_post_process_steps: list[PipelineWorkflowStep] | None = None,
     additional_verbs: VerbDefinitions | None = None,
     additional_workflows: WorkflowDefinitions | None = None,
@@ -226,7 +226,7 @@ async def run_pipeline(
     """
     start_time = time.time()
 
-    progress_reporter = progress_reporter or NullProgressReporter()
+    progress_reporter = progress_reporter or NullProgressLogger()
     callbacks = callbacks or [ConsoleWorkflowCallbacks()]
     callback_chain = _create_callback_chain(callbacks, progress_reporter)
     context = create_run_context(storage=storage, cache=cache, stats=None)

graphrag/index/run/workflow.py

@@ -21,7 +21,7 @@ from graphrag.index.context import PipelineRunContext
 from graphrag.index.exporter import ParquetExporter
 from graphrag.index.run.profiling import _write_workflow_stats
 from graphrag.index.typing import PipelineRunResult
-from graphrag.logging.base import ProgressReporter
+from graphrag.logger.base import ProgressLogger
 from graphrag.storage.pipeline_storage import PipelineStorage
 from graphrag.utils.storage import _load_table_from_storage
 
@@ -68,7 +68,7 @@ async def _export_workflow_output(
 
 
 def _create_callback_chain(
-    callbacks: list[WorkflowCallbacks] | None, progress: ProgressReporter | None
+    callbacks: list[WorkflowCallbacks] | None, progress: ProgressLogger | None
 ) -> WorkflowCallbacks:
     """Create a callback manager that encompasses multiple callbacks."""
     manager = WorkflowCallbacksManager()

graphrag/index/update/incremental_index.py

@@ -23,7 +23,7 @@ from graphrag.index.update.entities import (
     _run_entity_summarization,
 )
 from graphrag.index.update.relationships import _update_and_merge_relationships
-from graphrag.logging.print_progress import ProgressReporter
+from graphrag.logger.print_progress import ProgressLogger
 from graphrag.storage.pipeline_storage import PipelineStorage
 from graphrag.utils.storage import _load_table_from_storage
 
@@ -85,7 +85,7 @@ async def update_dataframe_outputs(
     config: PipelineConfig,
     cache: PipelineCache,
     callbacks: VerbCallbacks,
-    progress_reporter: ProgressReporter,
+    progress_reporter: ProgressLogger,
 ) -> None:
     """Update the mergeable outputs.
 

graphrag/index/validate_config.py

@@ -10,12 +10,10 @@ from datashaper import NoopVerbCallbacks
 
 from graphrag.config.models.graph_rag_config import GraphRagConfig
 from graphrag.index.llm.load_llm import load_llm, load_llm_embeddings
-from graphrag.logging.print_progress import ProgressReporter
+from graphrag.logger.print_progress import ProgressLogger
 
 
-def validate_config_names(
-    reporter: ProgressReporter, parameters: GraphRagConfig
-) -> None:
+def validate_config_names(reporter: ProgressLogger, parameters: GraphRagConfig) -> None:
     """Validate config file for LLM deployment name typos."""
     # Validate Chat LLM configs
     llm = load_llm(

graphrag/logger/__init__.py

@@ -1,4 +1,4 @@
 # Copyright (c) 2024 Microsoft Corporation.
 # Licensed under the MIT License
 
-"""Logging utilities and implementations."""
+"""Logger utilities and implementations."""

graphrag/logger/base.py

@@ -10,24 +10,24 @@ from datashaper.progress.types import Progress
 
 
 class StatusLogger(ABC):
-    """Provides a way to report status updates from the pipeline."""
+    """Provides a way to log status updates from the pipeline."""
 
     @abstractmethod
     def error(self, message: str, details: dict[str, Any] | None = None):
-        """Report an error."""
+        """Log an error."""
 
     @abstractmethod
     def warning(self, message: str, details: dict[str, Any] | None = None):
-        """Report a warning."""
+        """Log a warning."""
 
     @abstractmethod
     def log(self, message: str, details: dict[str, Any] | None = None):
         """Report a log."""
 
 
-class ProgressReporter(ABC):
+class ProgressLogger(ABC):
     """
-    Abstract base class for progress reporters.
+    Abstract base class for progress loggers.
 
     This is used to report workflow processing progress via mechanisms like progress-bars.
     """
@@ -38,10 +38,10 @@ class ProgressReporter(ABC):
 
     @abstractmethod
     def dispose(self):
-        """Dispose of the progress reporter."""
+        """Dispose of the progress logger."""
 
     @abstractmethod
-    def child(self, prefix: str, transient=True) -> "ProgressReporter":
+    def child(self, prefix: str, transient=True) -> "ProgressLogger":
         """Create a child progress bar."""
 
     @abstractmethod
@@ -50,20 +50,20 @@ class ProgressReporter(ABC):
 
     @abstractmethod
     def stop(self) -> None:
-        """Stop the progress reporter."""
+        """Stop the progress logger."""
 
     @abstractmethod
     def error(self, message: str) -> None:
-        """Report an error."""
+        """Log an error."""
 
     @abstractmethod
     def warning(self, message: str) -> None:
-        """Report a warning."""
+        """Log a warning."""
 
     @abstractmethod
     def info(self, message: str) -> None:
-        """Report information."""
+        """Log information."""
 
     @abstractmethod
     def success(self, message: str) -> None:
-        """Report success."""
+        """Log success."""

graphrag/logger/console.py

@@ -5,7 +5,7 @@
 
 from typing import Any
 
-from graphrag.logging.base import StatusLogger
+from graphrag.logger.base import StatusLogger
 
 
 class ConsoleReporter(StatusLogger):

graphrag/logger/factory.py

@@ -0,0 +1,43 @@
+# Copyright (c) 2024 Microsoft Corporation.
+# Licensed under the MIT License
+
+"""Factory functions for creating loggers."""
+
+from typing import ClassVar
+
+from graphrag.logger.base import ProgressLogger
+from graphrag.logger.null_progress import NullProgressLogger
+from graphrag.logger.print_progress import PrintProgressLogger
+from graphrag.logger.rich_progress import RichProgressLogger
+from graphrag.logger.types import LoggerType
+
+
+class LoggerFactory:
+    """A factory class for loggers."""
+
+    logger_types: ClassVar[dict[str, type]] = {}
+
+    @classmethod
+    def register(cls, logger_type: str, logger: type):
+        """Register a vector store type."""
+        cls.logger_types[logger_type] = logger
+
+    @classmethod
+    def create_logger(
+        cls, logger_type: LoggerType | str, kwargs: dict | None = None
+    ) -> ProgressLogger:
+        """Create a logger based on the provided type."""
+        if kwargs is None:
+            kwargs = {}
+        match logger_type:
+            case LoggerType.RICH:
+                return RichProgressLogger("GraphRAG Indexer ")
+            case LoggerType.PRINT:
+                return PrintProgressLogger("GraphRAG Indexer ")
+            case LoggerType.NONE:
+                return NullProgressLogger()
+            case _:
+                if logger_type in cls.logger_types:
+                    return cls.logger_types[logger_type](**kwargs)
+                # default to null logger if no other logger is found
+                return NullProgressLogger()

graphrag/logger/null_progress.py

@@ -3,19 +3,19 @@
 
 """Null Progress Reporter."""
 
-from graphrag.logging.base import Progress, ProgressReporter
+from graphrag.logger.base import Progress, ProgressLogger
 
 
-class NullProgressReporter(ProgressReporter):
-    """A progress reporter that does nothing."""
+class NullProgressLogger(ProgressLogger):
+    """A progress logger that does nothing."""
 
     def __call__(self, update: Progress) -> None:
         """Update progress."""
 
     def dispose(self) -> None:
-        """Dispose of the progress reporter."""
+        """Dispose of the progress logger."""
 
-    def child(self, prefix: str, transient: bool = True) -> ProgressReporter:
+    def child(self, prefix: str, transient: bool = True) -> ProgressLogger:
         """Create a child progress bar."""
         return self
 
@@ -23,16 +23,16 @@ class NullProgressReporter(ProgressReporter):
         """Force a refresh."""
 
     def stop(self) -> None:
-        """Stop the progress reporter."""
+        """Stop the progress logger."""
 
     def error(self, message: str) -> None:
-        """Report an error."""
+        """Log an error."""
 
     def warning(self, message: str) -> None:
-        """Report a warning."""
+        """Log a warning."""
 
     def info(self, message: str) -> None:
-        """Report information."""
+        """Log information."""
 
     def success(self, message: str) -> None:
-        """Report success."""
+        """Log success."""

graphrag/logger/print_progress.py

@@ -1,18 +1,18 @@
 # Copyright (c) 2024 Microsoft Corporation.
 # Licensed under the MIT License
 
-"""Print Progress Reporter."""
+"""Print Progress Logger."""
 
-from graphrag.logging.base import Progress, ProgressReporter
+from graphrag.logger.base import Progress, ProgressLogger
 
 
-class PrintProgressReporter(ProgressReporter):
-    """A progress reporter that does nothing."""
+class PrintProgressLogger(ProgressLogger):
+    """A progress logger that prints progress to stdout."""
 
     prefix: str
 
     def __init__(self, prefix: str):
-        """Create a new progress reporter."""
+        """Create a new progress logger."""
         self.prefix = prefix
         print(f"\n{self.prefix}", end="")  # noqa T201
 
@@ -21,30 +21,30 @@ class PrintProgressReporter(ProgressReporter):
         print(".", end="")  # noqa T201
 
     def dispose(self) -> None:
-        """Dispose of the progress reporter."""
+        """Dispose of the progress logger."""
 
-    def child(self, prefix: str, transient: bool = True) -> "ProgressReporter":
+    def child(self, prefix: str, transient: bool = True) -> ProgressLogger:
         """Create a child progress bar."""
-        return PrintProgressReporter(prefix)
+        return PrintProgressLogger(prefix)
 
     def stop(self) -> None:
-        """Stop the progress reporter."""
+        """Stop the progress logger."""
 
     def force_refresh(self) -> None:
         """Force a refresh."""
 
     def error(self, message: str) -> None:
-        """Report an error."""
+        """Log an error."""
         print(f"\n{self.prefix}ERROR: {message}")  # noqa T201
 
     def warning(self, message: str) -> None:
-        """Report a warning."""
+        """Log a warning."""
         print(f"\n{self.prefix}WARNING: {message}")  # noqa T201
 
     def info(self, message: str) -> None:
-        """Report information."""
+        """Log information."""
         print(f"\n{self.prefix}INFO: {message}")  # noqa T201
 
     def success(self, message: str) -> None:
-        """Report success."""
+        """Log success."""
         print(f"\n{self.prefix}SUCCESS: {message}")  # noqa T201

graphrag/logger/rich_progress.py

@@ -13,12 +13,12 @@ from rich.progress import Progress, TaskID, TimeElapsedColumn
 from rich.spinner import Spinner
 from rich.tree import Tree
 
-from graphrag.logging.base import ProgressReporter
+from graphrag.logger.base import ProgressLogger
 
 
 # https://stackoverflow.com/a/34325723
-class RichProgressReporter(ProgressReporter):
-    """A rich-based progress reporter for CLI use."""
+class RichProgressLogger(ProgressLogger):
+    """A rich-based progress logger for CLI use."""
 
     _console: Console
     _group: Group
@@ -32,7 +32,7 @@ class RichProgressReporter(ProgressReporter):
     _last_refresh: float = 0
 
     def dispose(self) -> None:
-        """Dispose of the progress reporter."""
+        """Dispose of the progress logger."""
         self._disposing = True
         self._live.stop()
 
@@ -59,10 +59,10 @@ class RichProgressReporter(ProgressReporter):
     def __init__(
         self,
         prefix: str,
-        parent: "RichProgressReporter | None" = None,
+        parent: "RichProgressLogger | None" = None,
         transient: bool = True,
     ) -> None:
-        """Create a new rich-based progress reporter."""
+        """Create a new rich-based progress logger."""
         self._prefix = prefix
 
         if parent is None:
@@ -115,27 +115,27 @@ class RichProgressReporter(ProgressReporter):
         self.live.refresh()
 
     def stop(self) -> None:
-        """Stop the progress reporter."""
+        """Stop the progress logger."""
         self._live.stop()
 
-    def child(self, prefix: str, transient: bool = True) -> ProgressReporter:
+    def child(self, prefix: str, transient: bool = True) -> ProgressLogger:
         """Create a child progress bar."""
-        return RichProgressReporter(parent=self, prefix=prefix, transient=transient)
+        return RichProgressLogger(parent=self, prefix=prefix, transient=transient)
 
     def error(self, message: str) -> None:
-        """Report an error."""
+        """Log an error."""
         self._console.print(f"❌ [red]{message}[/red]")
 
     def warning(self, message: str) -> None:
-        """Report a warning."""
+        """Log a warning."""
         self._console.print(f"⚠️ [yellow]{message}[/yellow]")
 
     def success(self, message: str) -> None:
-        """Report success."""
+        """Log success."""
         self._console.print(f"🚀 [green]{message}[/green]")
 
     def info(self, message: str) -> None:
-        """Report information."""
+        """Log information."""
         self._console.print(message)
 
     def __call__(self, progress_update: DSProgress) -> None:

graphrag/logger/types.py

@@ -1,18 +1,18 @@
 # Copyright (c) 2024 Microsoft Corporation.
 # Licensed under the MIT License
 
-"""Types for status reporting."""
+"""Logging types."""
 
 from enum import Enum
 
 
-class ReporterType(str, Enum):
-    """The type of reporter to use."""
+class LoggerType(str, Enum):
+    """The type of logger to use."""
 
     RICH = "rich"
     PRINT = "print"
     NONE = "none"
 
     def __str__(self):
-        """Return the string representation of the enum value."""
+        """Return a string representation of the enum value."""
         return self.value

graphrag/logging/factory.py

@@ -1,36 +0,0 @@
-# Copyright (c) 2024 Microsoft Corporation.
-# Licensed under the MIT License
-
-"""Factory functions for creating loggers."""
-
-from graphrag.logging.base import ProgressReporter
-from graphrag.logging.null_progress import NullProgressReporter
-from graphrag.logging.print_progress import PrintProgressReporter
-from graphrag.logging.rich_progress import RichProgressReporter
-from graphrag.logging.types import ReporterType
-
-
-def create_progress_reporter(
-    reporter_type: ReporterType = ReporterType.NONE,
-) -> ProgressReporter:
-    """Load a progress reporter.
-
-    Parameters
-    ----------
-    reporter_type : {"rich", "print", "none"}, default=rich
-        The type of progress reporter to load.
-
-    Returns
-    -------
-    ProgressReporter
-    """
-    match reporter_type:
-        case ReporterType.RICH:
-            return RichProgressReporter("GraphRAG Indexer ")
-        case ReporterType.PRINT:
-            return PrintProgressReporter("GraphRAG Indexer ")
-        case ReporterType.NONE:
-            return NullProgressReporter()
-        case _:
-            msg = f"Invalid progress reporter type: {reporter_type}"
-            raise ValueError(msg)

graphrag/model/__init__.py

@@ -1,4 +1,4 @@
 # Copyright (c) 2024 Microsoft Corporation.
 # Licensed under the MIT License
 
-"""GraphRAG knowledge model package root."""
+"""Knowledge model package."""

graphrag/prompt_tune/loader/input.py

@@ -15,7 +15,7 @@ from graphrag.config.models.llm_parameters import LLMParameters
 from graphrag.index.input.factory import create_input
 from graphrag.index.llm.load_llm import load_llm_embeddings
 from graphrag.index.operations.chunk_text import chunk_text
-from graphrag.logging.base import ProgressReporter
+from graphrag.logger.base import ProgressLogger
 from graphrag.prompt_tune.defaults import (
     MIN_CHUNK_OVERLAP,
     MIN_CHUNK_SIZE,
@@ -54,7 +54,7 @@ async def load_docs_in_chunks(
     config: GraphRagConfig,
     select_method: DocSelectionType,
     limit: int,
-    reporter: ProgressReporter,
+    reporter: ProgressLogger,
     chunk_size: int = MIN_CHUNK_SIZE,
     n_subset_max: int = N_SUBSET_MAX,
     k: int = K,

graphrag/prompts/index/__init__.py

@@ -1,4 +1,4 @@
 # Copyright (c) 2024 Microsoft Corporation.
 # Licensed under the MIT License
 
-"""All prompts for indexing."""
+"""All prompts for the indexing engine."""

graphrag/prompts/query/__init__.py

@@ -1,4 +1,4 @@
 # Copyright (c) 2024 Microsoft Corporation.
 # Licensed under the MIT License
 
-"""All prompts for query."""
+"""All prompts for the query engine."""

graphrag/query/llm/oai/base.py

@@ -8,8 +8,8 @@ from collections.abc import Callable
 
 from openai import AsyncAzureOpenAI, AsyncOpenAI, AzureOpenAI, OpenAI
 
-from graphrag.logging.base import StatusLogger
-from graphrag.logging.console import ConsoleReporter
+from graphrag.logger.base import StatusLogger
+from graphrag.logger.console import ConsoleReporter
 from graphrag.query.llm.base import BaseTextEmbedding
 from graphrag.query.llm.oai.typing import OpenaiApiType
 

graphrag/query/llm/oai/chat_openai.py

@@ -15,7 +15,7 @@ from tenacity import (
     wait_exponential_jitter,
 )
 
-from graphrag.logging.base import StatusLogger
+from graphrag.logger.base import StatusLogger
 from graphrag.query.llm.base import BaseLLM, BaseLLMCallback
 from graphrag.query.llm.oai.base import OpenAILLMImpl
 from graphrag.query.llm.oai.typing import (

graphrag/query/llm/oai/embedding.py

@@ -18,7 +18,7 @@ from tenacity import (
     wait_exponential_jitter,
 )
 
-from graphrag.logging.base import StatusLogger
+from graphrag.logger.base import StatusLogger
 from graphrag.query.llm.base import BaseTextEmbedding
 from graphrag.query.llm.oai.base import OpenAILLMImpl
 from graphrag.query.llm.oai.typing import (

graphrag/storage/blob_pipeline_storage.py

@@ -13,7 +13,7 @@ from azure.identity import DefaultAzureCredential
 from azure.storage.blob import BlobServiceClient
 from datashaper import Progress
 
-from graphrag.logging.base import ProgressReporter
+from graphrag.logger.base import ProgressLogger
 from graphrag.storage.pipeline_storage import PipelineStorage
 
 log = logging.getLogger(__name__)
@@ -95,7 +95,7 @@ class BlobPipelineStorage(PipelineStorage):
         self,
         file_pattern: re.Pattern[str],
         base_dir: str | None = None,
-        progress: ProgressReporter | None = None,
+        progress: ProgressLogger | None = None,
         file_filter: dict[str, Any] | None = None,
         max_count=-1,
     ) -> Iterator[tuple[str, dict[str, Any]]]:

graphrag/storage/file_pipeline_storage.py

@@ -16,7 +16,7 @@ from aiofiles.os import remove
 from aiofiles.ospath import exists
 from datashaper import Progress
 
-from graphrag.logging.base import ProgressReporter
+from graphrag.logger.base import ProgressLogger
 from graphrag.storage.pipeline_storage import PipelineStorage
 
 log = logging.getLogger(__name__)
@@ -38,7 +38,7 @@ class FilePipelineStorage(PipelineStorage):
         self,
         file_pattern: re.Pattern[str],
         base_dir: str | None = None,
-        progress: ProgressReporter | None = None,
+        progress: ProgressLogger | None = None,
         file_filter: dict[str, Any] | None = None,
         max_count=-1,
     ) -> Iterator[tuple[str, dict[str, Any]]]:

graphrag/storage/pipeline_storage.py

@@ -8,7 +8,7 @@ from abc import ABCMeta, abstractmethod
 from collections.abc import Iterator
 from typing import Any
 
-from graphrag.logging.base import ProgressReporter
+from graphrag.logger.base import ProgressLogger
 
 
 class PipelineStorage(metaclass=ABCMeta):
@@ -19,7 +19,7 @@ class PipelineStorage(metaclass=ABCMeta):
         self,
         file_pattern: re.Pattern[str],
         base_dir: str | None = None,
-        progress: ProgressReporter | None = None,
+        progress: ProgressLogger | None = None,
         file_filter: dict[str, Any] | None = None,
         max_count=-1,
     ) -> Iterator[tuple[str, dict[str, Any]]]:

pyproject.toml

@@ -132,7 +132,6 @@ coverage_report = 'coverage report --omit "**/tests/**" --show-missing'
 check_format = 'ruff format . --check'
 fix = "ruff check --fix ."
 fix_unsafe = "ruff check --fix --unsafe-fixes ."
-
 _test_all = "coverage run -m pytest ./tests"
 test_unit = "pytest ./tests/unit"
 test_integration = "pytest ./tests/integration"
@@ -146,7 +145,6 @@ query = "python -m graphrag query"
 prompt_tune = "python -m graphrag prompt-tune"
 # Pass in a test pattern
 test_only = "pytest -s -k"
-
 serve_docs = "mkdocs serve"
 build_docs = "mkdocs build"