Added otlp

.env.otlp.example

@@ -0,0 +1,23 @@
+
+OTEL_EXPORTER_OTLP_TRACES_ENDPOINT="http://localhost:9411/api/v2/spans"
+OTEL_EXPORTER_OTLP_METRICS_ENDPOINT="http://localhost:9411/api/v2/spans"
+USE_ZIPKIN=true
+
+# Service identification
+OTEL_SERVICE_NAME="my-graphrag-app"
+OTEL_SERVICE_VERSION="1.0.0"
+OTEL_SERVICE_NAMESPACE="my-company"
+
+# Zipkin configuration
+OTEL_EXPORTER_OTLP_TRACES_ENDPOINT="http://localhost:9411/api/v2/spans"
+
+# Tracing configuration
+OTEL_ENABLE_TRACING="true"
+OTEL_ENABLE_METRICS="true"
+OTEL_TRACE_SAMPLE_RATE="1.0"  # Sample 100% of traces
+
+# Environment
+OTEL_DEPLOYMENT_ENVIRONMENT="production"
+
+# Disable telemetry completely (if needed)
+DISABLE_TELEMETRY="false"

graphrag/__init__.py

@@ -2,3 +2,19 @@
 # Licensed under the MIT License
 
 """The GraphRAG package."""
+import logging
+
+from .telemetry import setup_telemetry, is_telemetry_disabled
+
+logger = logging.getLogger(__name__)
+
+# Initialize telemetry automatically when the package is imported
+# unless explicitly disabled
+if not is_telemetry_disabled():
+    try:
+        setup_telemetry()
+        logger.info("Telemetry initialized automatically")
+    except Exception as e:
+        logger.warning(f"Failed to initialize telemetry: {e}")
+else:
+    logger.info("Telemetry is not enabled. (Can be enabled via environment variable DISABLE_TELEMETRY)")

graphrag/api/index.py

@@ -22,10 +22,17 @@
 from graphrag.index.typing.pipeline_run_result import PipelineRunResult
 from graphrag.index.workflows.factory import PipelineFactory
 from graphrag.logger.standard_logging import init_loggers
+from graphrag.telemetry.decorators import add_trace
 
 logger = logging.getLogger(__name__)
 
-
+@add_trace(
+    operation_name="build_index",
+    attributes={
+        "component": "indexing",
+        "operation": "build_index",
+    }
+)
 async def build_index(
     config: GraphRagConfig,
     method: IndexingMethod | str = IndexingMethod.Standard,

graphrag/config/load_config.py

@@ -14,6 +14,7 @@
 
 from graphrag.config.create_graphrag_config import create_graphrag_config
 from graphrag.config.models.graph_rag_config import GraphRagConfig
+from graphrag.telemetry.decorators import add_trace
 
 _default_config_files = ["settings.yaml", "settings.yml", "settings.json"]
 
@@ -142,7 +143,9 @@ def _parse(file_extension: str, contents: str) -> dict[str, Any]:
             )
             raise ValueError(msg)
 
-
+@add_trace(
+    operation_name="graphrag.config.load_config", 
+    attributes={"component": "config"})
 def load_config(
     root_dir: Path,
     config_filepath: Path | None = None,

graphrag/index/operations/build_noun_graph/np_extractors/factory.py

@@ -22,7 +22,7 @@
 from graphrag.index.operations.build_noun_graph.np_extractors.syntactic_parsing_extractor import (
     SyntacticNounPhraseExtractor,
 )
-
+from graphrag.telemetry.decorators import add_trace
 
 class NounPhraseExtractorFactory:
     """A factory class for creating noun phrase extractor."""
@@ -74,7 +74,10 @@ def get_np_extractor(cls, config: TextAnalyzerConfig) -> BaseNounPhraseExtractor
                     word_delimiter=config.word_delimiter,
                 )
 
-
+@add_trace(
+    operation_name="np_extractor.factory.create_noun_phrase_extractor",
+    attributes={"component": "np_extractor_factory"},
+)
 def create_noun_phrase_extractor(
     analyzer_config: TextAnalyzerConfig,
 ) -> BaseNounPhraseExtractor:

graphrag/index/workflows/create_communities.py

@@ -17,11 +17,13 @@
 from graphrag.index.operations.create_graph import create_graph
 from graphrag.index.typing.context import PipelineRunContext
 from graphrag.index.typing.workflow import WorkflowFunctionOutput
+from graphrag.telemetry.decorators import trace_workflow
 from graphrag.utils.storage import load_table_from_storage, write_table_to_storage
 
 logger = logging.getLogger(__name__)
 
 
+@trace_workflow("create_communities")
 async def run_workflow(
     config: GraphRagConfig,
     context: PipelineRunContext,

graphrag/index/workflows/load_input_documents.py

@@ -13,11 +13,13 @@
 from graphrag.index.typing.context import PipelineRunContext
 from graphrag.index.typing.workflow import WorkflowFunctionOutput
 from graphrag.storage.pipeline_storage import PipelineStorage
+from graphrag.telemetry.decorators import trace_workflow
 from graphrag.utils.storage import write_table_to_storage
 
 logger = logging.getLogger(__name__)
 
 
+@trace_workflow("load_input_documents")
 async def run_workflow(
     config: GraphRagConfig,
     context: PipelineRunContext,

graphrag/query/structured_search/global_search/search.py

@@ -31,6 +31,7 @@
 )
 from graphrag.query.llm.text_utils import try_parse_json_object
 from graphrag.query.structured_search.base import BaseSearch, SearchResult
+from graphrag.telemetry.decorators import trace_search_operation
 from graphrag.tokenizer.tokenizer import Tokenizer
 
 logger = logging.getLogger(__name__)
@@ -132,6 +133,7 @@ async def stream_search(
         ):
             yield response
 
+    @trace_search_operation("global_search")
     async def search(
         self,
         query: str,

graphrag/query/structured_search/local_search/search.py

@@ -18,6 +18,7 @@
     ConversationHistory,
 )
 from graphrag.query.structured_search.base import BaseSearch, SearchResult
+from graphrag.telemetry.decorators import trace_search_operation
 from graphrag.tokenizer.tokenizer import Tokenizer
 
 logger = logging.getLogger(__name__)
@@ -48,6 +49,7 @@ def __init__(
         self.callbacks = callbacks or []
         self.response_type = response_type
 
+    @trace_search_operation("local_search")
     async def search(
         self,
         query: str,