monocle-apptrace 0.1.0__py3-none-any.whl → 0.2.0__py3-none-any.whl

monocle_apptrace/instrumentor.py

@@ -1,7 +1,5 @@
-
-
-import logging
-from typing import Collection,List
+import logging, os
+from typing import Collection, List
 from wrapt import wrap_function_wrapper
 from opentelemetry.trace import get_tracer
 from opentelemetry.instrumentation.instrumentor import BaseInstrumentor
@@ -11,17 +9,16 @@ from opentelemetry.sdk.trace.export import BatchSpanProcessor, SpanProcessor
 from opentelemetry.sdk.resources import SERVICE_NAME, Resource
 from opentelemetry import trace
 from opentelemetry.context import get_value, attach, set_value
-from monocle_apptrace.wrap_common import CONTEXT_PROPERTIES_KEY
+from monocle_apptrace.utils import process_wrapper_method_config
+from monocle_apptrace.wrap_common import SESSION_PROPERTIES_KEY
 from monocle_apptrace.wrapper import INBUILT_METHODS_LIST, WrapperMethod
-from monocle_apptrace.exporters.file_exporter import FileSpanExporter
-
+from monocle_apptrace.exporters.monocle_exporters import get_monocle_exporter
 
 logger = logging.getLogger(__name__)
 
 _instruments = ()
 
 class MonocleInstrumentor(BaseInstrumentor):
-
     workflow_name: str = ""
     user_wrapper_methods: list[WrapperMethod] = []
     instrumented_method_list: list[object] = []
@@ -37,7 +34,7 @@ class MonocleInstrumentor(BaseInstrumentor):
 
     def _instrument(self, **kwargs):
         tracer_provider = kwargs.get("tracer_provider")
-        tracer = get_tracer(instrumenting_module_name= __name__, tracer_provider= tracer_provider)
+        tracer = get_tracer(instrumenting_module_name=__name__, tracer_provider=tracer_provider)
 
         user_method_list = [
             {
@@ -46,8 +43,9 @@ class MonocleInstrumentor(BaseInstrumentor):
                 "method": method.method,
                 "span_name": method.span_name,
                 "wrapper": method.wrapper,
+                "output_processor": method.output_processor
             } for method in self.user_wrapper_methods]
-
+        process_wrapper_method_config(user_method_list)
         final_method_list = user_method_list + INBUILT_METHODS_LIST
 
         for wrapped_method in final_method_list:
@@ -69,7 +67,6 @@ class MonocleInstrumentor(BaseInstrumentor):
                                 object:{wrap_object},
                                 method:{wrap_method}""")
 
-
     def _uninstrument(self, **kwargs):
         for wrapped_method in self.instrumented_method_list:
             try:
@@ -93,8 +90,9 @@ def setup_monocle_telemetry(
     resource = Resource(attributes={
         SERVICE_NAME: workflow_name
     })
-    span_processors = span_processors or [BatchSpanProcessor(FileSpanExporter())]
+    span_processors = span_processors or [BatchSpanProcessor(get_monocle_exporter())]
     trace_provider = TracerProvider(resource=resource)
+    attach(set_value("workflow_name", workflow_name))
     tracer_provider_default = trace.get_tracer_provider()
     provider_type = type(tracer_provider_default).__name__
     is_proxy_provider = "Proxy" in provider_type
@@ -102,23 +100,22 @@ def setup_monocle_telemetry(
         processor.on_start = on_processor_start
         if not is_proxy_provider:
             tracer_provider_default.add_span_processor(processor)
-        else :
+        else:
             trace_provider.add_span_processor(processor)
-    if is_proxy_provider :
+    if is_proxy_provider:
         trace.set_tracer_provider(trace_provider)
     instrumentor = MonocleInstrumentor(user_wrapper_methods=wrapper_methods or [])
     # instrumentor.app_name = workflow_name
     if not instrumentor.is_instrumented_by_opentelemetry:
         instrumentor.instrument()
 
-
 def on_processor_start(span: Span, parent_context):
-    context_properties = get_value(CONTEXT_PROPERTIES_KEY)
+    context_properties = get_value(SESSION_PROPERTIES_KEY)
     if context_properties is not None:
         for key, value in context_properties.items():
             span.set_attribute(
-                f"{CONTEXT_PROPERTIES_KEY}.{key}", value
+                f"{SESSION_PROPERTIES_KEY}.{key}", value
             )
 
 def set_context_properties(properties: dict) -> None:
-    attach(set_value(CONTEXT_PROPERTIES_KEY, properties))
+    attach(set_value(SESSION_PROPERTIES_KEY, properties))

monocle_apptrace/langchain/__init__.py

@@ -1,6 +1,9 @@
 import os
-from monocle_apptrace.utils import load_wrapper_from_config
+from monocle_apptrace.utils import get_wrapper_methods_config
 
 parent_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))
-LANGCHAIN_METHODS = load_wrapper_from_config(
-    os.path.join(parent_dir, 'wrapper_config', 'lang_chain_methods.json'))
+LANGCHAIN_METHODS = get_wrapper_methods_config(
+    wrapper_methods_config_path=os.path.join(parent_dir, 'metamodel', 'maps', 'langchain_methods.json'),
+    attributes_config_base_path=os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+
+

monocle_apptrace/llamaindex/__init__.py

@@ -1,15 +1,16 @@
-
-#pylint: disable=protected-access
+# pylint: disable=protected-access
 import os
-from monocle_apptrace.utils import load_wrapper_from_config
+from monocle_apptrace.utils import get_wrapper_methods_config
+
 
 def get_llm_span_name_for_openai(instance):
     if (hasattr(instance, "_is_azure_client")
-        and callable(getattr(instance, "_is_azure_client"))
-        and instance._is_azure_client()):
+            and callable(getattr(instance, "_is_azure_client"))
+            and instance._is_azure_client()):
         return "llamaindex.azure_openai"
     return "llamaindex.openai"
 
 parent_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))
-LLAMAINDEX_METHODS = load_wrapper_from_config(
-    os.path.join(parent_dir, 'wrapper_config', 'llama_index_methods.json'))
+LLAMAINDEX_METHODS = get_wrapper_methods_config(
+    wrapper_methods_config_path=os.path.join(parent_dir, 'metamodel', 'maps', 'llamaindex_methods.json'),
+    attributes_config_base_path=os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))

monocle_apptrace/metamodel/README.md

@@ -0,0 +1,47 @@
+# Monocle metamodel
+
+## Overview 
+Monocle metamodel is the way to manage standardization across all supported GenAI component stack. It includes the list of components that Monocle can identify and extract metadata. This help understanding and analyzing the traces from applications that include multiple components and can evolve over time. This is one of core value that Monocle provides to it's user community.
+
+## Meta model
+The Monocle metamodel comprises of three things, 
+- Entity types, definitions of technology types and supported vendor implementations.
+- A JSON format that overlays on top of Open Telemetry tracing format that includes the common attributes for each entity type.
+- Map of component menthods to trace with instrumentation methods provided by Monocle.
+
+### Entity type
+The entity type defines the type of GenAI component that Monocle understand. The monocle instrumentation can extract the relevenat information for this entity. There are a fixed set of [entity types](./entity_types.py) that are defined by Monocle out of the box, eg workflow, model etc. As the GenAI landscape evolves, the Monocle community will introduce a new entity type if the current entities won't represent a new technology component.
+Each entity types has number of supported technology components that Monocle handles out of the box, eg. LlamaIndex is a supported workflow. Monocle community will continue to expand the breadth of the project by adding more components.
+
+### Span types
+The GenAI application have specific [types of spans](./spans/README.md#span-types-and-events) where diffrent entities integrate. Monocle metamodel defines these types and specifies format for tracing data and metadata generated in such spans. 
+
+### Consistent trace format
+Monocle generates [traces](../../../Monocle_User_Guide.md#traces) which comprises of [spans](../../../Monocle_User_Guide.md#spans). Note that Monocle trace is [OpenTelemetry format](https://opentelemetry.io/docs/concepts/signals/traces/) compatible. Each span is essentially a step in the execution that interacts with one of more GenAI technology components. The please refer to the [full spec of the json format](./span_format.json) and a detailed [example](./span_example.json). 
+The ```attribute``` section of the span includes a list of such entities that are used in that span.
+The runtime data and metadata collected during the execution of that span are included in the ```events``` section of the trace (as per the Otel spec). Each entry in the event corrosponds to the entity involved in that trace execution if it has produced any runtime outputs. 
+Please see the [span format](./spans/README.md) for details.
+
+### Instrumentation method map
+The map dectates what Monocle tracing method is relevant for the a given GenAI tech component method/API. It also specifies the name for that span to set in the trace output.
+```python
+    {
+        "package": "llama_index.core.base.base_query_engine",
+        "object": "BaseQueryEngine",
+        "method": "query",
+        "span_name": "llamaindex.query",
+        "wrapper_package": "wrap_common",
+        "wrapper_method": "task_wrapper"
+    }
+```
+
+## Extending the meta model
+Monocle is highly extensible. This section describe when one would need to extend the meta model. Please refer to Monocle [User guide](../../../Monocle_User_Guide.md) and [Contributor guide](../../../Monocle_contributor_guide.md) for detailed steps.
+### Trace a new method/API
+If you have overloaded an existing functionality in one of the supported components by creating a new function. Monocle doesn't know that this function should be traced, say because it's calling an LLM. You could define a new mapping so Monocle instrumentation can trace this function the say way it handles other LLM invocation functions.
+
+### Adding a new component provider
+Let's say there's a new database that supports vector search capability which is not supported by the Monocle. In this case, first you'll need to add that database under the ``MonocleEntity.VectorDB`` list. Then you'll need to extend the method map and test if the existing Monocle tracing functions has logic to effectively trace the new component. If not, then you might need to implement new method to cover the gap and update the mapping table according.
+
+### Support new type of entity
+If there's new component that can't be mapped to any of the existing entity types, then it'll require extending the metamodel and implement new instrumetation to support it. We recommend you initiate a discussion with Monocle community to add the support.

monocle_apptrace/metamodel/entities/README.md

@@ -0,0 +1,77 @@
+# Monocle Entities
+The entity type defines the type of GenAI component that Monocle understand. The monocle instrumentation can extract the relevenat information for this entity. There are a fixed set of [entity types](./entity_types.py) that are defined by Monocle out of the box, eg workflow, model etc. As the GenAI landscape evolves, the Monocle community will introduce a new entity type if the current entities won't represent a new technology component.
+
+## Entities
+Following attributes are supported for all entities
+| Name | Description | Required |
+| - | - | - |
+| name | Entity name generated by Monocle | Required |
+| type | entity.category.type | True |
+
+### MonocleEntity.Workflow
+Workflow ie the core application code. 
+#### Workflow types
+- generic
+- langchain
+- llamaindex
+- haystack
+
+### MonocleEntity.Model
+GenAI models. It has following sub categories
+- generic
+- llm
+- embedding
+#### Model types
+- gpt3
+- gpt-3.5
+- gpt-3.5-turbo
+- gpt4
+- gpt4o
+- gpt4o-mini
+- ollama
+
+Following attributes are supported for all model type entities
+| Name | Description | Required |
+| - | - | - |
+| parameters | model parameters | false |
+| algorithm | model algorithm | false |
+
+### MonocleEntity.AppHosting
+Application host services where the workflow code is run.
+#### AppHosting types
+- generic
+- aws_lambda
+- aws_sagemaker
+- azure_func
+- github_codespace
+- azure_mlw
+
+### MonocleEntity.Inference
+The model hosting infrastructure services.
+Following attributes are supported for inference type entities
+| Name | Description | Required |
+| - | - | - |
+| inference_endpoint | connection endpoint for inference service | false |
+#### Inference types
+- generic
+- nvidia_triton
+- openai
+- azure_oai
+- aws_sagemaker
+- aws_bedrock
+- hugging_face
+
+Following attributes are supported for inference type entities
+| Name | Description | Inference type | Required |
+| - | - | - | - |
+| deployment | model deployment name | azure_oai | false |
+
+
+### MonocleEntity.VectorStore
+Vector search data stores.
+#### VectorStore types
+- generic
+- chroma
+- aws_es
+- milvus
+- pinecone

monocle_apptrace/metamodel/entities/app_hosting_types.json

@@ -0,0 +1,29 @@
+{
+    "entity" : "app_hosting",
+    "types": [
+        {
+            "name": "aws_lambda",
+            "attributes" : []
+        },
+        {
+            "name": "aws_sagemaker",
+            "attributes" : []
+        },
+        {
+            "name": "azure_func",
+            "attributes" : []
+        },
+        {
+            "name": "azure_mlw",
+            "attributes" : []
+        },
+        {
+            "name": "github_codespace",
+            "attributes" : []
+        },
+        {
+            "name": "generic",
+            "attributes" : []
+        }
+    ]
+}

monocle_apptrace/metamodel/entities/entities.json

@@ -0,0 +1,49 @@
+{
+    "description": "Monocle entities represents kinds GenAI technology components and their implementations supported by Monocle",
+    "monocle_entities": [
+        {
+            "name": "workflow",
+            "attributes" : [],
+            "categories": []
+        },
+        {
+            "name": "model",
+            "attributes" : [
+                {
+                    "attribute_name": "model_name",
+                    "attribute_description": "Model name",
+                    "required": true
+                }
+            ],
+            "categories": [
+                {
+                    "name": "llm",
+                    "attributes" : []
+                },
+                {
+                    "name": "embedding",
+                    "attributes" : []
+                },
+                {
+                    "name": "generic",
+                    "attributes" : []
+                }
+            ]
+        },
+        {
+            "name": "vector_store",
+            "attributes" : [],
+            "categories": []
+        },
+        {
+            "name": "app_hosting",
+            "attributes" : [],
+            "categories": []
+        },
+        {
+            "name": "inference",
+            "attributes" : [],
+            "categories": []
+        }
+    ]
+}

monocle_apptrace/metamodel/entities/inference_types.json

@@ -0,0 +1,33 @@
+{
+    "entity" : "vector_store",
+    "types": [
+        {
+            "name": "aws_sagemaker",
+            "attributes" : []
+        },
+        {
+            "name": "aws_bedrock",
+            "attributes" : []
+        },
+        {
+            "name": "azure_oai",
+            "attributes" : []
+        },
+        {
+            "name": "openai",
+            "attributes" : []
+        },
+        {
+            "name": "nvidia_triton",
+            "attributes" : []
+        },
+        {
+            "name": "hugging_face",
+            "attributes" : []
+        },
+        {
+            "name": "generic",
+            "attributes" : []
+        }
+    ]
+}

monocle_apptrace/metamodel/entities/model_types.json

@@ -0,0 +1,41 @@
+{
+    "entity" : "model",
+    "types": [
+        {
+            "name": "gpt3",
+            "attributes" : []
+        },
+        {
+            "name": "gpt-3.5",
+            "attributes" : []
+        },
+        {
+            "name": "gpt-3.5-turbo",
+            "attributes" : []
+        },
+        {
+            "name": "gpt-3.5",
+            "attributes" : []
+        },
+        {
+            "name": "gpt4",
+            "attributes" : []
+        },
+        {
+            "name": "gpt4o",
+            "attributes" : []
+        },
+        {
+            "name": "gpt4o-mini",
+            "attributes" : []
+        },
+        {
+            "name": "ollama",
+            "attributes" : []
+        },
+        {
+            "name": "generic",
+            "attributes" : []
+        }
+    ]
+}

monocle_apptrace/metamodel/entities/vector_store_types.json

@@ -0,0 +1,25 @@
+{
+    "entity" : "vector_store",
+    "types": [
+        {
+            "name": "chroma",
+            "attributes" : []
+        },
+        {
+            "name": "aws_es",
+            "attributes" : []
+        },
+        {
+            "name": "milvus",
+            "attributes" : []
+        },
+        {
+            "name": "pinecone",
+            "attributes" : []
+        },
+        {
+            "name": "generic",
+            "attributes" : []
+        }
+    ]
+}

monocle_apptrace/metamodel/entities/workflow_types.json

@@ -0,0 +1,22 @@
+{
+    "entity" : "workflow",
+    "types": [
+        {
+            "name": "llama_index",
+            "attributes" : []
+        },
+        {
+            "name": "langchain",
+            "attributes" : []
+        },
+        {
+            "name": "haystack",
+            "attributes" : []
+        },
+        {
+            "name": "generic",
+            "attributes" : []
+        }
+
+    ]
+}

monocle_apptrace/metamodel/maps/attributes/inference/langchain_entities.json

@@ -0,0 +1,35 @@
+{
+  "type": "inference",
+  "attributes": [
+    [
+      {
+        "_comment": "provider type ,name , deployment , inference_endpoint",
+        "attribute": "type",
+        "accessor": "lambda instance,args:'inference.azure_oai'"
+      },
+      {
+        "attribute": "provider_name",
+        "accessor": "lambda instance,args:args['provider_name']"
+      },
+      {
+        "attribute": "deployment",
+        "accessor": "lambda instance,args: resolve_from_alias(instance.__dict__, ['engine', 'azure_deployment', 'deployment_name', 'deployment_id', 'deployment'])"
+      },
+      {
+        "attribute": "inference_endpoint",
+        "accessor": "lambda instance,args: resolve_from_alias(instance.__dict__, ['azure_endpoint', 'api_base']) or args['inference_endpoint']"
+      }
+    ],
+    [
+      {
+        "_comment": "LLM Model",
+        "attribute": "name",
+        "accessor": "lambda instance,args: resolve_from_alias(instance.__dict__, ['model', 'model_name'])"
+      },
+      {
+        "attribute": "type",
+        "accessor": "lambda instance,args: 'model.llm.'+resolve_from_alias(instance.__dict__, ['model', 'model_name'])"
+      }
+    ]
+  ]
+}

monocle_apptrace/metamodel/maps/attributes/inference/llamaindex_entities.json

@@ -0,0 +1,35 @@
+{
+  "type": "inference",
+  "attributes": [
+    [
+      {
+        "_comment": "provider type ,name , deployment , inference_endpoint",
+        "attribute": "type",
+        "accessor": "lambda instance,args:'inference.azure_oai'"
+      },
+      {
+        "attribute": "provider_name",
+        "accessor": "lambda instance,args:args['provider_name']"
+      },
+      {
+        "attribute": "deployment",
+        "accessor": "lambda instance,args: resolve_from_alias(instance.__dict__, ['engine', 'azure_deployment', 'deployment_name', 'deployment_id', 'deployment'])"
+      },
+      {
+        "attribute": "inference_endpoint",
+        "accessor": "lambda instance,args: resolve_from_alias(instance.__dict__, ['azure_endpoint', 'api_base'])"
+      }
+    ],
+    [
+      {
+        "_comment": "LLM Model",
+        "attribute": "name",
+        "accessor": "lambda instance,args: resolve_from_alias(instance.__dict__, ['model', 'model_name'])"
+      },
+      {
+        "attribute": "type",
+        "accessor": "lambda instance,args: 'model.llm.'+resolve_from_alias(instance.__dict__, ['model', 'model_name'])"
+      }
+    ]
+  ]
+}

monocle_apptrace/metamodel/maps/attributes/retrieval/langchain_entities.json

@@ -0,0 +1,27 @@
+{
+  "type": "retrieval",
+  "attributes": [
+    [
+      {
+        "_comment": "vector store name and type",
+        "attribute": "name",
+        "accessor": "lambda instance,args: type(instance.vectorstore).__name__"
+      },
+      {
+        "attribute": "type",
+        "accessor": "lambda instance,args: 'vectorstore.'+type(instance.vectorstore).__name__"
+      }
+    ],
+    [
+      {
+        "_comment": "embedding model name and type",
+        "attribute": "name",
+        "accessor": "lambda instance,args: instance.vectorstore.embeddings.model"
+      },
+      {
+        "attribute": "type",
+        "accessor": "lambda instance ,args: 'model.embedding.'+instance.vectorstore.embeddings.model"
+      }
+    ]
+  ]
+}

monocle_apptrace/metamodel/maps/attributes/retrieval/llamaindex_entities.json

@@ -0,0 +1,27 @@
+{
+  "type": "retrieval",
+  "attributes": [
+    [
+      {
+        "_comment": "vector store name and type",
+        "attribute": "name",
+        "accessor": "lambda instance,args: type(instance._vector_store).__name__"
+      },
+      {
+        "attribute": "type",
+        "accessor": "lambda instance,args: 'vectorstore.'+type(instance._vector_store).__name__"
+      }
+    ],
+    [
+      {
+        "_comment": "embedding model name and type",
+        "attribute": "name",
+        "accessor": "lambda instance,args: instance._embed_model.model_name"
+      },
+      {
+        "attribute": "type",
+        "accessor": "lambda instance ,args: 'model.embedding.'+instance._embed_model.model_name"
+      }
+    ]
+  ]
+}