Replace custom get_logger with standard Python logging

Copilot · jgbradley1 · Copilot · commit de7afafb5ee3 · 2025-05-31T06:04:25.000Z
Co-authored-by: jgbradley1 &lt;654554+jgbradley1@users.noreply.github.com&gt;
diff --git a/docs/examples_notebooks/index_migration_to_v1.ipynb b/docs/examples_notebooks/index_migration_to_v1.ipynb
@@ -202,10 +202,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from graphrag.index.flows.generate_text_embeddings import generate_text_embeddings\n",
+    "\n",
     "from graphrag.cache.factory import CacheFactory\n",
     "from graphrag.callbacks.noop_workflow_callbacks import NoopWorkflowCallbacks\n",
     "from graphrag.config.embeddings import get_embedded_fields, get_embedding_settings\n",
-    "from graphrag.index.flows.generate_text_embeddings import generate_text_embeddings\n",
     "\n",
     "# We only need to re-run the embeddings workflow, to ensure that embeddings for all required search fields are in place\n",
     "# We'll construct the context and run this function flow directly to avoid everything else\n",
diff --git a/examples_notebooks/community_contrib/yfiles-jupyter-graphs/graph-visualization.ipynb b/examples_notebooks/community_contrib/yfiles-jupyter-graphs/graph-visualization.ipynb
@@ -29,6 +29,9 @@
     "\n",
     "import pandas as pd\n",
     "import tiktoken\n",
+    "from graphrag.query.llm.oai.chat_openai import ChatOpenAI\n",
+    "from graphrag.query.llm.oai.embedding import OpenAIEmbedding\n",
+    "from graphrag.query.llm.oai.typing import OpenaiApiType\n",
     "\n",
     "from graphrag.query.context_builder.entity_extraction import EntityVectorStoreKey\n",
     "from graphrag.query.indexer_adapters import (\n",
@@ -38,9 +41,6 @@
     "    read_indexer_reports,\n",
     "    read_indexer_text_units,\n",
     ")\n",
-    "from graphrag.query.llm.oai.chat_openai import ChatOpenAI\n",
-    "from graphrag.query.llm.oai.embedding import OpenAIEmbedding\n",
-    "from graphrag.query.llm.oai.typing import OpenaiApiType\n",
     "from graphrag.query.structured_search.local_search.mixed_context import (\n",
     "    LocalSearchMixedContext,\n",
     ")\n",
diff --git a/graphrag/__init__.py b/graphrag/__init__.py
@@ -2,3 +2,12 @@
 # Licensed under the MIT License
 
 """The GraphRAG package."""
+
+import logging
+
+# Configure the graphrag root logger with a default handler
+# This ensures that the logger hierarchy is set up correctly
+_root_logger = logging.getLogger("graphrag")
+if not _root_logger.handlers:
+    # Add a NullHandler to prevent unconfigured logger warnings
+    _root_logger.addHandler(logging.NullHandler())
diff --git a/graphrag/api/index.py b/graphrag/api/index.py
@@ -19,10 +19,9 @@
 from graphrag.index.typing.pipeline_run_result import PipelineRunResult
 from graphrag.index.typing.workflow import WorkflowFunction
 from graphrag.index.workflows.factory import PipelineFactory
-from graphrag.logger.standard_logging import get_logger
 
 log = logging.getLogger(__name__)
-logger = get_logger("graphrag.indexing")
+logger = logging.getLogger("graphrag.indexing")
 
 
 async def build_index(
diff --git a/graphrag/api/query.py b/graphrag/api/query.py
@@ -17,6 +17,7 @@
 Backwards compatibility is not guaranteed at this time.
 """
 
+import logging
 from collections.abc import AsyncGenerator
 from typing import Any
 
@@ -31,7 +32,6 @@
     text_unit_text_embedding,
 )
 from graphrag.config.models.graph_rag_config import GraphRagConfig
-from graphrag.logger.standard_logging import get_logger
 from graphrag.query.factory import (
     get_basic_search_engine,
     get_drift_search_engine,
@@ -55,8 +55,8 @@
 from graphrag.utils.cli import redact
 
 # Initialize standard logger
-log = get_logger(__name__)
-logger = get_logger("graphrag.query")
+log = logging.getLogger(__name__)
+logger = logging.getLogger("graphrag.query")
 
 
 @validate_call(config={"arbitrary_types_allowed": True})
diff --git a/graphrag/cli/index.py b/graphrag/cli/index.py
@@ -14,7 +14,6 @@
 from graphrag.config.load_config import load_config
 from graphrag.config.logging import enable_logging_with_config
 from graphrag.index.validate_config import validate_config_names
-from graphrag.logger.standard_logging import get_logger
 from graphrag.logger.types import LoggerType
 from graphrag.utils.cli import redact
 
@@ -139,7 +138,7 @@ def _run_index(
 ):
     # logger parameter is kept for CLI compatibility but unused now (uses standard logging)
     _ = logger  # Suppress unused variable warning
-    progress_logger = get_logger("graphrag.cli.progress")
+    progress_logger = logging.getLogger("graphrag.cli.progress")
     info, error, success = _logger_helper(progress_logger)
 
     if not cache:
diff --git a/graphrag/cli/initialize.py b/graphrag/cli/initialize.py
@@ -3,10 +3,10 @@
 
 """CLI implementation of the initialization subcommand."""
 
+import logging
 from pathlib import Path
 
 from graphrag.config.init_content import INIT_DOTENV, INIT_YAML
-from graphrag.logger.standard_logging import get_logger
 from graphrag.prompts.index.community_report import (
     COMMUNITY_REPORT_PROMPT,
 )
@@ -48,7 +48,7 @@ def initialize_project_at(path: Path, force: bool) -> None:
     ValueError
         If the project already exists and force is False.
     """
-    progress_logger = get_logger("graphrag.cli.initialize")
+    progress_logger = logging.getLogger("graphrag.cli.initialize")
     progress_logger.info(f"Initializing project at {path}")  # noqa: G004
     root = Path(path)
     if not root.exists():
diff --git a/graphrag/cli/prompt_tune.py b/graphrag/cli/prompt_tune.py
@@ -3,13 +3,13 @@
 
 """CLI implementation of the prompt-tune subcommand."""
 
+import logging
 from pathlib import Path
 
 import graphrag.api as api
 from graphrag.cli.index import _logger_helper
 from graphrag.config.load_config import load_config
 from graphrag.config.logging import enable_logging_with_config
-from graphrag.logger.standard_logging import get_logger
 from graphrag.logger.types import LoggerType
 from graphrag.prompt_tune.generator.community_report_summarization import (
     COMMUNITY_SUMMARIZATION_FILENAME,
@@ -73,7 +73,7 @@ async def prompt_tune(
 
     # logger parameter is kept for CLI compatibility but unused now (uses standard logging)
     _ = logger  # Suppress unused variable warning
-    progress_logger = get_logger("graphrag.cli.prompt_tune")
+    progress_logger = logging.getLogger("graphrag.cli.prompt_tune")
     info, error, success = _logger_helper(progress_logger)
 
     enabled_logging, log_path = enable_logging_with_config(
diff --git a/graphrag/cli/query.py b/graphrag/cli/query.py
@@ -4,6 +4,7 @@
 """CLI implementation of the query subcommand."""
 
 import asyncio
+import logging
 import sys
 from pathlib import Path
 from typing import TYPE_CHECKING, Any
@@ -12,16 +13,15 @@
 from graphrag.callbacks.noop_query_callbacks import NoopQueryCallbacks
 from graphrag.config.load_config import load_config
 from graphrag.config.models.graph_rag_config import GraphRagConfig
-from graphrag.logger.standard_logging import get_logger
 from graphrag.utils.api import create_storage_from_config
 from graphrag.utils.storage import load_table_from_storage, storage_has_table
 
 if TYPE_CHECKING:
     import pandas as pd
 
 # Initialize standard logger
-log = get_logger(__name__)
-logger = get_logger("graphrag.cli.query")
+log = logging.getLogger(__name__)
+logger = logging.getLogger("graphrag.cli.query")
 
 
 def run_global_search(
diff --git a/graphrag/index/input/factory.py b/graphrag/index/input/factory.py
@@ -15,7 +15,6 @@
 from graphrag.index.input.csv import load_csv
 from graphrag.index.input.json import load_json
 from graphrag.index.input.text import load_text
-from graphrag.logger.standard_logging import get_logger
 from graphrag.storage.blob_pipeline_storage import BlobPipelineStorage
 from graphrag.storage.file_pipeline_storage import FilePipelineStorage
 
@@ -35,7 +34,7 @@ async def create_input(
     """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 get_logger("graphrag.input")
+    progress_reporter = progress_reporter or logging.getLogger("graphrag.input")
 
     match config.type:
         case InputType.blob:
diff --git a/graphrag/logger/standard_logging.py b/graphrag/logger/standard_logging.py
@@ -12,8 +12,8 @@
     configure_logging(log_level="INFO", log_file="/path/to/app.log")
 
     # Then throughout your code:
-    from graphrag.logger.standard_logging import get_logger
-    logger = get_logger(__name__)  # Typically pass __name__ to get module-specific logger
+    import logging
+    logger = logging.getLogger(__name__)  # Use standard logging
 
     # Use standard logging methods:
     logger.debug("Debug message")
@@ -25,9 +25,9 @@
 Notes
 -----
     The logging system is hierarchical. Loggers are organized in a tree structure,
-    with the root logger named 'graphrag'. All loggers created by get_logger() will
-    be children of this root logger. This allows for consistent configuration of all
-    graphrag-related logs throughout the application.
+    with the root logger named 'graphrag'. All loggers created with names starting
+    with 'graphrag.' will be children of this root logger. This allows for consistent
+    configuration of all graphrag-related logs throughout the application.
 
     All progress logging now uses this standard logging system for consistency.
 """
@@ -90,25 +90,3 @@ def configure_logging(
 
     # Prevent propagation to root logger to avoid duplicate logging
     logger.propagate = False
-
-
-def get_logger(name: str) -> logging.Logger:
-    """Get a logger with the given name.
-
-    This function returns a logger that is a child of the 'graphrag' logger.
-
-    Parameters
-    ----------
-    name : str
-        The name of the logger, usually __name__
-
-    Returns
-    -------
-    logging.Logger
-        A logger instance
-    """
-    # Ensure the name has 'graphrag' prefix for proper hierarchy
-    if not name.startswith("graphrag.") and name != "graphrag":
-        name = "graphrag.main" if name == "__main__" else f"graphrag.{name}"
-
-    return logging.getLogger(name)
diff --git a/tests/unit/logger/test_standard_logging.py b/tests/unit/logger/test_standard_logging.py
@@ -7,14 +7,13 @@
 import tempfile
 from pathlib import Path
 
-from graphrag.logger.standard_logging import configure_logging, get_logger
+from graphrag.logger.standard_logging import configure_logging
 
 
-def test_logger_name_formatting():
-    """Test the logger name gets formatted correctly."""
-    assert get_logger("test").name == "graphrag.test"
-    assert get_logger("graphrag.test").name == "graphrag.test"
-    assert get_logger("__main__").name == "graphrag.main"
+def test_standard_logging():
+    """Test that standard logging works."""
+    logger = logging.getLogger("graphrag.test")
+    assert logger.name == "graphrag.test"
 
 
 def test_file_logging():
@@ -26,7 +25,7 @@ def test_file_logging():
         configure_logging(log_file=log_file)
 
         # Get a logger and log some messages
-        logger = get_logger("test")
+        logger = logging.getLogger("graphrag.test")
         test_message = "Test file logging message"
         logger.info(test_message)
 
@@ -42,8 +41,8 @@ def test_logger_hierarchy():
     # Reset logging to default state
     configure_logging()
 
-    root_logger = get_logger("graphrag")
-    child_logger = get_logger("graphrag.child")
+    root_logger = logging.getLogger("graphrag")
+    child_logger = logging.getLogger("graphrag.child")
 
     # Setting level on root should affect children
     root_logger.setLevel(logging.ERROR)
