Improve internal logging functionality by using Python's standard logging module

.semversioner/next-release/patch-20250611170907043237.json

@@ -0,0 +1,4 @@
+{
+  "type": "patch",
+  "description": "cleaned up logging to follow python standards."
+}

dictionary.txt

@@ -102,6 +102,7 @@ itertuples
 isin
 nocache
 nbconvert
+levelno
 
 # HTML
 nbsp
@@ -186,6 +187,7 @@ Verdantis's
 # English
 skippable
 upvote
+unconfigured
 
 # Misc
 Arxiv

docs/config/env_vars.md

@@ -178,11 +178,11 @@ This section controls the cache mechanism used by the pipeline. This is used to
 
 ### Reporting
 
-This section controls the reporting mechanism used by the pipeline, for common events and error messages. The default is to write reports to a file in the output directory. However, you can also choose to write reports to the console or to an Azure Blob Storage container.
+This section controls the reporting mechanism used by the pipeline, for common events and error messages. The default is to write reports to a file in the output directory. However, you can also choose to write reports to an Azure Blob Storage container.
 
 | Parameter                                     | Description                                                                                                                                                        | Type  | Required or Optional | Default |
 | --------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----- | -------------------- | ------- |
-| `GRAPHRAG_REPORTING_TYPE`                     | The type of reporter to use. Options are `file`, `console`, or `blob`                                                                                              | `str` | optional             | `file`  |
+| `GRAPHRAG_REPORTING_TYPE`                     | The type of reporter to use. Options are `file` or `blob`                                                                                              | `str` | optional             | `file`  |
 | `GRAPHRAG_REPORTING_STORAGE_ACCOUNT_BLOB_URL` | The Azure Storage blob endpoint to use when in `blob` mode and using managed identity. Will have the format `https://<storage_account_name>.blob.core.windows.net` | `str` | optional             | None    |
 | `GRAPHRAG_REPORTING_CONNECTION_STRING`        | The Azure Storage connection string to use when in `blob` mode.                                                                                                    | `str` | optional             | None    |
 | `GRAPHRAG_REPORTING_CONTAINER_NAME`           | The Azure Storage container name to use when in `blob` mode.                                                                                                       | `str` | optional             | None    |

docs/config/yaml.md

@@ -149,11 +149,11 @@ This section controls the cache mechanism used by the pipeline. This is used to
 
 ### reporting
 
-This section controls the reporting mechanism used by the pipeline, for common events and error messages. The default is to write reports to a file in the output directory. However, you can also choose to write reports to the console or to an Azure Blob Storage container.
+This section controls the reporting mechanism used by the pipeline, for common events and error messages. The default is to write reports to a file in the output directory. However, you can also choose to write reports to an Azure Blob Storage container.
 
 #### Fields
 
-- `type` **file|console|blob** - The reporting type to use. Default=`file`
+- `type` **file|blob** - The reporting type to use. Default=`file`
 - `base_dir` **str** - The base directory to write reports to, relative to the root.
 - `connection_string` **str** - (blob only) The Azure Storage connection string.
 - `container_name` **str** - (blob only) The Azure Storage container name.

graphrag/__init__.py

@@ -2,3 +2,10 @@
 # Licensed under the MIT License
 
 """The GraphRAG package."""
+
+import logging
+
+from graphrag.logger.standard_logging import init_console_logger
+
+logger = logging.getLogger(__name__)
+init_console_logger()

graphrag/api/index.py

@@ -10,7 +10,7 @@
 
 import logging
 
-from graphrag.callbacks.reporting import create_pipeline_reporter
+from graphrag.callbacks.noop_workflow_callbacks import NoopWorkflowCallbacks
 from graphrag.callbacks.workflow_callbacks import WorkflowCallbacks
 from graphrag.config.enums import IndexingMethod
 from graphrag.config.models.graph_rag_config import GraphRagConfig
@@ -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.base import ProgressLogger
-from graphrag.logger.null_progress import NullProgressLogger
+from graphrag.logger.standard_logging import init_loggers
 
-log = logging.getLogger(__name__)
+logger = logging.getLogger(__name__)
 
 
 async def build_index(
@@ -31,7 +30,6 @@ async def build_index(
     is_update_run: bool = False,
     memory_profile: bool = False,
     callbacks: list[WorkflowCallbacks] | None = None,
-    progress_logger: ProgressLogger | None = None,
 ) -> list[PipelineRunResult]:
     """Run the pipeline with the given configuration.
 
@@ -45,26 +43,25 @@ async def build_index(
         Whether to enable memory profiling.
     callbacks : list[WorkflowCallbacks] | None default=None
         A list of callbacks to register.
-    progress_logger : ProgressLogger | None default=None
-        The progress logger.
 
     Returns
     -------
     list[PipelineRunResult]
         The list of pipeline run results
     """
-    logger = progress_logger or NullProgressLogger()
-    # create a pipeline reporter and add to any additional callbacks
-    callbacks = callbacks or []
-    callbacks.append(create_pipeline_reporter(config.reporting, None))
+    init_loggers(config=config)
 
-    workflow_callbacks = create_callback_chain(callbacks, logger)
+    # Create callbacks for pipeline lifecycle events if provided
+    workflow_callbacks = (
+        create_callback_chain(callbacks) if callbacks else NoopWorkflowCallbacks()
+    )
 
     outputs: list[PipelineRunResult] = []
 
     if memory_profile:
-        log.warning("New pipeline does not yet support memory profiling.")
+        logger.warning("New pipeline does not yet support memory profiling.")
 
+    logger.info("Initializing indexing pipeline...")
     # todo: this could propagate out to the cli for better clarity, but will be a breaking api change
     method = _get_method(method, is_update_run)
     pipeline = PipelineFactory.create_pipeline(config, method)
@@ -75,15 +72,14 @@ async def build_index(
         pipeline,
         config,
         callbacks=workflow_callbacks,
-        logger=logger,
         is_update_run=is_update_run,
     ):
         outputs.append(output)
         if output.errors and len(output.errors) > 0:
-            logger.error(output.workflow)
+            logger.error("Workflow %s completed with errors", output.workflow)
         else:
-            logger.success(output.workflow)
-        logger.info(str(output.result))
+            logger.info("Workflow %s completed successfully", output.workflow)
+        logger.debug(str(output.result))
 
     workflow_callbacks.pipeline_end(outputs)
     return outputs

graphrag/api/prompt_tune.py

@@ -11,6 +11,7 @@
 Backwards compatibility is not guaranteed at this time.
 """
 
+import logging
 from typing import Annotated
 
 import annotated_types
@@ -20,7 +21,7 @@
 from graphrag.config.defaults import graphrag_config_defaults
 from graphrag.config.models.graph_rag_config import GraphRagConfig
 from graphrag.language_model.manager import ModelManager
-from graphrag.logger.base import ProgressLogger
+from graphrag.logger.standard_logging import init_loggers
 from graphrag.prompt_tune.defaults import MAX_TOKEN_COUNT, PROMPT_TUNING_MODEL_ID
 from graphrag.prompt_tune.generator.community_report_rating import (
     generate_community_report_rating,
@@ -47,11 +48,12 @@
 from graphrag.prompt_tune.loader.input import load_docs_in_chunks
 from graphrag.prompt_tune.types import DocSelectionType
 
+logger = logging.getLogger(__name__)
+
 
 @validate_call(config={"arbitrary_types_allowed": True})
 async def generate_indexing_prompts(
     config: GraphRagConfig,
-    logger: ProgressLogger,
     chunk_size: PositiveInt = graphrag_config_defaults.chunks.size,
     overlap: Annotated[
         int, annotated_types.Gt(-1)
@@ -71,8 +73,6 @@ async def generate_indexing_prompts(
     Parameters
     ----------
     - config: The GraphRag configuration.
-    - logger: The logger to use for progress updates.
-    - root: The root directory.
     - output_path: The path to store the prompts.
     - chunk_size: The chunk token size to use for input text units.
     - limit: The limit of chunks to load.
@@ -89,6 +89,8 @@ async def generate_indexing_prompts(
     -------
     tuple[str, str, str]: entity extraction prompt, entity summarization prompt, community summarization prompt
     """
+    init_loggers(config=config)
+
     # Retrieve documents
     logger.info("Chunking documents...")
     doc_list = await load_docs_in_chunks(
@@ -187,9 +189,9 @@ async def generate_indexing_prompts(
         language=language,
     )
 
-    logger.info(f"\nGenerated domain: {domain}")  # noqa: G004
-    logger.info(f"\nDetected language: {language}")  # noqa: G004
-    logger.info(f"\nGenerated persona: {persona}")  # noqa: G004
+    logger.debug("Generated domain: %s", domain)
+    logger.debug("Detected language: %s", language)
+    logger.debug("Generated persona: %s", persona)
 
     return (
         extract_graph_prompt,