monocle-apptrace 0.1.1__py3-none-any.whl → 0.2.0__py3-none-any.whl

monocle_apptrace/metamodel/entities/README.md

@@ -1,33 +1,44 @@
 # 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.
 
-## Entity Types
+## Entities
 Following attributes are supported for all entities
 | Name | Description | Required |
 | - | - | - |
 | name | Entity name generated by Monocle | Required |
-| type | Monocle Entity type | True |
+| type | entity.category.type | True |
 
 ### MonocleEntity.Workflow
-Workflow ie the core application code. Supported types are -
+Workflow ie the core application code. 
+#### Workflow types
 - generic
 - langchain
-- llama_index
+- llamaindex
 - haystack
 
 ### MonocleEntity.Model
-GenAI models. Supported types are -
+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 |
 | - | - | - |
-| model_name | Name of model | True |
-
+| parameters | model parameters | false |
+| algorithm | model algorithm | false |
 
 ### MonocleEntity.AppHosting
-Application host services where the workflow code is run. Supported types are -
+Application host services where the workflow code is run.
+#### AppHosting types
 - generic
 - aws_lambda
 - aws_sagemaker
@@ -36,7 +47,12 @@ Application host services where the workflow code is run. Supported types are -
 - azure_mlw
 
 ### MonocleEntity.Inference
-The model hosting infrastructure services. Supported types are -
+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
@@ -45,8 +61,15 @@ The model hosting infrastructure services. Supported types are -
 - 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. Supported types are -
+Vector search data stores.
+#### VectorStore types
 - generic
 - chroma
 - aws_es

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"
+      }
+    ]
+  ]
+}

monocle_apptrace/metamodel/maps/{lang_chain_methods.json → langchain_methods.json}

@@ -1,4 +1,4 @@
-{ 
+{
 "wrapper_methods" : [
     {
         "package": "langchain.prompts.base",
@@ -19,42 +19,65 @@
         "object": "BaseChatModel",
         "method": "invoke",
         "wrapper_package": "wrap_common",
-        "wrapper_method": "llm_wrapper"
+        "wrapper_method": "llm_wrapper",
+        "output_processor": ["metamodel/maps/attributes/inference/langchain_entities.json"]
     },
     {
         "package": "langchain.chat_models.base",
         "object": "BaseChatModel",
         "method": "ainvoke",
         "wrapper_package": "wrap_common",
-        "wrapper_method": "allm_wrapper"
+        "wrapper_method": "allm_wrapper",
+        "output_processor": ["metamodel/maps/attributes/inference/langchain_entities.json"]
     },
     {
         "package": "langchain_core.language_models.llms",
         "object": "LLM",
         "method": "_generate",
         "wrapper_package": "wrap_common",
-        "wrapper_method": "llm_wrapper"
+        "wrapper_method": "llm_wrapper",
+        "output_processor": ["metamodel/maps/attributes/inference/langchain_entities.json"]
     },
     {
         "package": "langchain_core.language_models.llms",
         "object": "LLM",
         "method": "_agenerate",
         "wrapper_package": "wrap_common",
-        "wrapper_method": "llm_wrapper"
+        "wrapper_method": "allm_wrapper",
+        "output_processor": ["metamodel/maps/attributes/inference/langchain_entities.json"]
+    },
+    {
+        "package": "langchain_core.language_models.llms",
+        "object": "BaseLLM",
+        "method": "invoke",
+        "wrapper_package": "wrap_common",
+        "wrapper_method": "llm_wrapper",
+        "output_processor": ["metamodel/maps/attributes/inference/langchain_entities.json"]
+    },
+    {
+        "package": "langchain_core.language_models.llms",
+        "object": "BaseLLM",
+        "method": "ainvoke",
+        "wrapper_package": "wrap_common",
+        "wrapper_method": "allm_wrapper",
+        "output_processor": ["metamodel/maps/attributes/inference/langchain_entities.json"]
     },
     {
         "package": "langchain_core.retrievers",
         "object": "BaseRetriever",
         "method": "invoke",
         "wrapper_package": "wrap_common",
-        "wrapper_method": "task_wrapper"
+        "wrapper_method": "task_wrapper",
+        "output_processor": ["metamodel/maps/attributes/retrieval/langchain_entities.json"]
+
     },
     {
         "package": "langchain_core.retrievers",
         "object": "BaseRetriever",
         "method": "ainvoke",
         "wrapper_package": "wrap_common",
-        "wrapper_method": "atask_wrapper"
+        "wrapper_method": "atask_wrapper",
+        "output_processor": ["metamodel/maps/attributes/retrieval/langchain_entities.json"]
     },
     {
         "package": "langchain.schema",
@@ -103,4 +126,4 @@
         "wrapper_method": "atask_wrapper"
     }
 ]
-}
+}

monocle_apptrace/metamodel/maps/{llama_index_methods.json → llamaindex_methods.json}

@@ -6,7 +6,8 @@
         "method": "retrieve",
         "span_name": "llamaindex.retrieve",
         "wrapper_package": "wrap_common",
-        "wrapper_method": "task_wrapper"
+        "wrapper_method": "task_wrapper",
+        "output_processor": ["metamodel/maps/attributes/retrieval/llamaindex_entities.json"]
     },
     {
         "package": "llama_index.core.indices.base_retriever",
@@ -14,7 +15,8 @@
         "method": "aretrieve",
         "span_name": "llamaindex.retrieve",
         "wrapper_package": "wrap_common",
-        "wrapper_method": "atask_wrapper"
+        "wrapper_method": "atask_wrapper",
+        "output_processor": ["metamodel/maps/attributes/retrieval/llamaindex_entities.json"]
     },
     {
         "package": "llama_index.core.base.base_query_engine",
@@ -38,7 +40,8 @@
         "method": "chat",
         "span_name": "llamaindex.llmchat",
         "wrapper_package": "wrap_common",
-        "wrapper_method": "task_wrapper"
+        "wrapper_method": "task_wrapper",
+        "output_processor": ["metamodel/maps/attributes/inference/llamaindex_entities.json"]
     },
     {
         "package": "llama_index.core.llms.custom",
@@ -46,7 +49,8 @@
         "method": "achat",
         "span_name": "llamaindex.llmchat",
         "wrapper_package": "wrap_common",
-        "wrapper_method": "atask_wrapper"
+        "wrapper_method": "atask_wrapper",
+        "output_processor": ["metamodel/maps/attributes/inference/llamaindex_entities.json"]
     },
     {
         "package": "llama_index.llms.openai.base",
@@ -55,8 +59,7 @@
         "span_name": "llamaindex.openai",
         "wrapper_package": "wrap_common",
         "wrapper_method": "llm_wrapper",
-        "span_name_getter_package" : "llamaindex",
-        "span_name_getter_mothod" : "get_llm_span_name_for_openai"
+        "output_processor": ["metamodel/maps/attributes/inference/llamaindex_entities.json"]
     },
     {
         "package": "llama_index.llms.openai.base",
@@ -64,7 +67,8 @@
         "method": "achat",
         "span_name": "llamaindex.openai",
         "wrapper_package": "wrap_common",
-        "wrapper_method": "allm_wrapper"
+        "wrapper_method": "allm_wrapper",
+        "output_processor": ["metamodel/maps/attributes/inference/llamaindex_entities.json"]
     }
 ]
-}
+}

monocle_apptrace/metamodel/spans/span_example.json

@@ -13,7 +13,7 @@
         "status_code": "OK"
     },
     "attributes": {
-        "span.type": "Retrieval", 
+        "span.type": "retrieval", 
         "entity.count": 2,
         "entity.1.name": "ChromaVectorStore",
         "entity.1.type": "vectorstore.chroma",

monocle_apptrace/metamodel/spans/span_types.json

@@ -0,0 +1,16 @@
+{
+    "span_types" : [
+        {
+            "type": "inference",
+            "description": "Model inference span"
+        },
+        {
+            "type": "retrieval",
+            "description": "vector embedding retrieval"
+        },
+        {
+            "type": "workflow",
+            "description": "workflow orchetraction at top level"
+        }
+    ]
+}