openlit 1.30.2__tar.gz → 1.30.3__tar.gz

{openlit-1.30.2 → openlit-1.30.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: openlit
-Version: 1.30.2
+Version: 1.30.3
 Summary: OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications and GPUs, facilitating the integration of observability into your GenAI-driven projects
 Home-page: https://github.com/openlit/openlit/tree/main/openlit/python
 Keywords: OpenTelemetry,otel,otlp,llm,tracing,openai,anthropic,claude,cohere,llm monitoring,observability,monitoring,gpt,Generative AI,chatGPT,gpu
@@ -72,7 +72,7 @@ This project proudly follows and maintains the [Semantic Conventions](https://gi
 | [✅ Cohere](https://docs.openlit.io/latest/integrations/cohere)                      |                                          | [✅ EmbedChain](https://docs.openlit.io/latest/integrations/embedchain)    |               |                                       
 | [✅ Mistral](https://docs.openlit.io/latest/integrations/mistral)                    |                                                                          | [✅ Guardrails](https://docs.openlit.io/latest/integrations/guardrails)    |               |
 | [✅ Azure OpenAI](https://docs.openlit.io/latest/integrations/azure-openai)          |                                                                          | [✅ CrewAI](https://docs.openlit.io/latest/integrations/crewai)            |               |
-| [✅ Azure AI Inference](https://docs.openlit.io/latest/integrations/azure-ai-inference) |                                                                          |                                         
+| [✅ Azure AI Inference](https://docs.openlit.io/latest/integrations/azure-ai-inference) |                                                                          | [✅ DSPy](https://docs.openlit.io/latest/integrations/dspy)                                    |               |
 | [✅ GitHub AI Models](https://docs.openlit.io/latest/integrations/github-models)  |                                                                          |                                       |               |
 | [✅ HuggingFace Transformers](https://docs.openlit.io/latest/integrations/huggingface) |                                                                          |                                       |               |
 | [✅ Amazon Bedrock](https://docs.openlit.io/latest/integrations/bedrock)             |                                                                          |                                       |               |
@@ -84,6 +84,7 @@ This project proudly follows and maintains the [Semantic Conventions](https://gi
 | [✅ Google AI Studio](https://docs.openlit.io/latest/integrations/google-ai-studio)  |                                                                          |                                       |               |
 | [✅ NVIDIA NIM](https://docs.openlit.io/latest/integrations/nvidia-nim)              |                                                                          |                                       |               |
 
+
 ## Supported Destinations
 - [✅ OpenTelemetry Collector](https://docs.openlit.io/latest/connections/otelcol)
 - [✅ Prometheus + Tempo](https://docs.openlit.io/latest/connections/prometheus-tempo)

{openlit-1.30.2 → openlit-1.30.3}/README.md

@@ -41,7 +41,7 @@ This project proudly follows and maintains the [Semantic Conventions](https://gi
 | [✅ Cohere](https://docs.openlit.io/latest/integrations/cohere)                      |                                          | [✅ EmbedChain](https://docs.openlit.io/latest/integrations/embedchain)    |               |                                       
 | [✅ Mistral](https://docs.openlit.io/latest/integrations/mistral)                    |                                                                          | [✅ Guardrails](https://docs.openlit.io/latest/integrations/guardrails)    |               |
 | [✅ Azure OpenAI](https://docs.openlit.io/latest/integrations/azure-openai)          |                                                                          | [✅ CrewAI](https://docs.openlit.io/latest/integrations/crewai)            |               |
-| [✅ Azure AI Inference](https://docs.openlit.io/latest/integrations/azure-ai-inference) |                                                                          |                                         
+| [✅ Azure AI Inference](https://docs.openlit.io/latest/integrations/azure-ai-inference) |                                                                          | [✅ DSPy](https://docs.openlit.io/latest/integrations/dspy)                                    |               |
 | [✅ GitHub AI Models](https://docs.openlit.io/latest/integrations/github-models)  |                                                                          |                                       |               |
 | [✅ HuggingFace Transformers](https://docs.openlit.io/latest/integrations/huggingface) |                                                                          |                                       |               |
 | [✅ Amazon Bedrock](https://docs.openlit.io/latest/integrations/bedrock)             |                                                                          |                                       |               |
@@ -53,6 +53,7 @@ This project proudly follows and maintains the [Semantic Conventions](https://gi
 | [✅ Google AI Studio](https://docs.openlit.io/latest/integrations/google-ai-studio)  |                                                                          |                                       |               |
 | [✅ NVIDIA NIM](https://docs.openlit.io/latest/integrations/nvidia-nim)              |                                                                          |                                       |               |
 
+
 ## Supported Destinations
 - [✅ OpenTelemetry Collector](https://docs.openlit.io/latest/connections/otelcol)
 - [✅ Prometheus + Tempo](https://docs.openlit.io/latest/connections/prometheus-tempo)

{openlit-1.30.2 → openlit-1.30.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "openlit"
-version = "1.30.2"
+version = "1.30.3"
 description = "OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications and GPUs, facilitating the integration of observability into your GenAI-driven projects"
 authors = ["OpenLIT"]
 repository = "https://github.com/openlit/openlit/tree/main/openlit/python"

{openlit-1.30.2 → openlit-1.30.3}/src/openlit/instrumentation/litellm/__init__.py

@@ -7,10 +7,10 @@ from opentelemetry.instrumentation.instrumentor import BaseInstrumentor
 from wrapt import wrap_function_wrapper
 
 from openlit.instrumentation.litellm.litellm import (
-    completion
+    completion, embedding
 )
 from openlit.instrumentation.litellm.async_litellm import (
-   acompletion
+   acompletion, aembedding
 )
 
 _instruments = ("litellm >= 1.52.6",)
@@ -48,6 +48,20 @@ class LiteLLMInstrumentor(BaseInstrumentor):
                   tracer, pricing_info, trace_content, metrics, disable_metrics),
         )
 
+        wrap_function_wrapper(
+            "litellm",
+            "embedding",
+            embedding("litellm.embedding", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+        wrap_function_wrapper(
+            "litellm",
+            "aembedding",
+            aembedding("litellm.embedding", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
 
     def _uninstrument(self, **kwargs):
         # Proper uninstrumentation logic to revert patched methods

{openlit-1.30.2 → openlit-1.30.3}/src/openlit/instrumentation/litellm/async_litellm.py

@@ -8,6 +8,7 @@ from opentelemetry.trace import SpanKind, Status, StatusCode
 from opentelemetry.sdk.resources import TELEMETRY_SDK_NAME
 from openlit.__helpers import (
     get_chat_model_cost,
+    get_embed_model_cost,
     openai_tokens,
     handle_exception,
     response_as_dict,
@@ -404,3 +405,117 @@ def acompletion(gen_ai_endpoint, version, environment, application_name,
                     return response
 
     return wrapper
+
+def aembedding(gen_ai_endpoint, version, environment, application_name,
+                    tracer, pricing_info, trace_content, metrics, disable_metrics):
+    """
+    Generates a telemetry wrapper for embeddings to collect metrics.
+
+    Args:
+        gen_ai_endpoint: Endpoint identifier for logging and tracing.
+        version: Version of the monitoring package.
+        environment: Deployment environment (e.g., production, staging).
+        application_name: Name of the application using the OpenAI API.
+        tracer: OpenTelemetry tracer for creating spans.
+        pricing_info: Information used for calculating the cost of OpenAI usage.
+        trace_content: Flag indicating whether to trace the actual content.
+
+    Returns:
+        A function that wraps the embeddings method to add telemetry.
+    """
+
+    async def wrapper(wrapped, instance, args, kwargs):
+        """
+        Wraps the 'embeddings' API call to add telemetry.
+
+        This collects metrics such as execution time, cost, and token usage, and handles errors
+        gracefully, adding details to the trace for observability.
+
+        Args:
+            wrapped: The original 'embeddings' method to be wrapped.
+            instance: The instance of the class where the original method is defined.
+            args: Positional arguments for the 'embeddings' method.
+            kwargs: Keyword arguments for the 'embeddings' method.
+
+        Returns:
+            The response from the original 'embeddings' method.
+        """
+
+        with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
+            response = await wrapped(*args, **kwargs)
+            response_dict = response_as_dict(response)
+            try:
+                # Calculate cost of the operation
+                cost = get_embed_model_cost(kwargs.get("model", "text-embedding-ada-002"),
+                                pricing_info, response_dict.get('usage').get('prompt_tokens'))
+
+                # Set Span attributes
+                span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+                span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
+                                    SemanticConvetion.GEN_AI_SYSTEM_OPENAI)
+                span.set_attribute(SemanticConvetion.GEN_AI_TYPE,
+                                    SemanticConvetion.GEN_AI_TYPE_EMBEDDING)
+                span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
+                                    gen_ai_endpoint)
+                span.set_attribute(SemanticConvetion.GEN_AI_ENVIRONMENT,
+                                    environment)
+                span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
+                                    application_name)
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
+                                    kwargs.get("model", "text-embedding-ada-002"))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_EMBEDDING_FORMAT,
+                                    kwargs.get("encoding_format", "float"))
+                # span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_EMBEDDING_DIMENSION,
+                #                     kwargs.get("dimensions", "null"))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
+                                    kwargs.get("user", ""))
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                    response_dict.get('usage').get('prompt_tokens'))
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                    response_dict.get('usage').get('total_tokens'))
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
+                                    cost)
+                if trace_content:
+                    span.add_event(
+                        name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
+                        attributes={
+                            SemanticConvetion.GEN_AI_CONTENT_PROMPT: kwargs.get("input", ""),
+                        },
+                    )
+
+                span.set_status(Status(StatusCode.OK))
+
+                if disable_metrics is False:
+                    attributes = {
+                        TELEMETRY_SDK_NAME:
+                            "openlit",
+                        SemanticConvetion.GEN_AI_APPLICATION_NAME:
+                            application_name,
+                        SemanticConvetion.GEN_AI_SYSTEM:
+                            SemanticConvetion.GEN_AI_SYSTEM_OPENAI,
+                        SemanticConvetion.GEN_AI_ENVIRONMENT:
+                            environment,
+                        SemanticConvetion.GEN_AI_TYPE:
+                            SemanticConvetion.GEN_AI_TYPE_EMBEDDING,
+                        SemanticConvetion.GEN_AI_REQUEST_MODEL:
+                            kwargs.get("model", "text-embedding-ada-002")
+                    }
+
+                    metrics["genai_requests"].add(1, attributes)
+                    metrics["genai_total_tokens"].add(
+                        response_dict.get('usage').get('total_tokens'), attributes)
+                    metrics["genai_prompt_tokens"].add(
+                        response_dict.get('usage').get('prompt_tokens'), attributes)
+                    metrics["genai_cost"].record(cost, attributes)
+
+                # Return original response
+                return response
+
+            except Exception as e:
+                handle_exception(span, e)
+                logger.error("Error in trace creation: %s", e)
+
+                # Return original response
+                return response
+
+    return wrapper

{openlit-1.30.2 → openlit-1.30.3}/src/openlit/instrumentation/litellm/litellm.py

@@ -8,6 +8,7 @@ from opentelemetry.trace import SpanKind, Status, StatusCode
 from opentelemetry.sdk.resources import TELEMETRY_SDK_NAME
 from openlit.__helpers import (
     get_chat_model_cost,
+    get_embed_model_cost,
     openai_tokens,
     handle_exception,
     response_as_dict,
@@ -404,3 +405,117 @@ def completion(gen_ai_endpoint, version, environment, application_name,
                     return response
 
     return wrapper
+
+def embedding(gen_ai_endpoint, version, environment, application_name,
+              tracer, pricing_info, trace_content, metrics, disable_metrics):
+    """
+    Generates a telemetry wrapper for embeddings to collect metrics.
+    
+    Args:
+        gen_ai_endpoint: Endpoint identifier for logging and tracing.
+        version: Version of the monitoring package.
+        environment: Deployment environment (e.g., production, staging).
+        application_name: Name of the application using the OpenAI API.
+        tracer: OpenTelemetry tracer for creating spans.
+        pricing_info: Information used for calculating the cost of OpenAI usage.
+        trace_content: Flag indicating whether to trace the actual content.
+    
+    Returns:
+        A function that wraps the embeddings method to add telemetry.
+    """
+
+    def wrapper(wrapped, instance, args, kwargs):
+        """
+        Wraps the 'embeddings' API call to add telemetry.
+
+        This collects metrics such as execution time, cost, and token usage, and handles errors
+        gracefully, adding details to the trace for observability.
+
+        Args:
+            wrapped: The original 'embeddings' method to be wrapped.
+            instance: The instance of the class where the original method is defined.
+            args: Positional arguments for the 'embeddings' method.
+            kwargs: Keyword arguments for the 'embeddings' method.
+
+        Returns:
+            The response from the original 'embeddings' method.
+        """
+
+        with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
+            response = wrapped(*args, **kwargs)
+            response_dict = response_as_dict(response)
+            try:
+                # Calculate cost of the operation
+                cost = get_embed_model_cost(kwargs.get("model", "text-embedding-ada-002"),
+                                    pricing_info, response_dict.get('usage').get('prompt_tokens'))
+
+                # Set Span attributes
+                span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+                span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
+                                    SemanticConvetion.GEN_AI_SYSTEM_OPENAI)
+                span.set_attribute(SemanticConvetion.GEN_AI_TYPE,
+                                    SemanticConvetion.GEN_AI_TYPE_EMBEDDING)
+                span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
+                                    gen_ai_endpoint)
+                span.set_attribute(SemanticConvetion.GEN_AI_ENVIRONMENT,
+                                    environment)
+                span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
+                                    application_name)
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
+                                    kwargs.get("model", "text-embedding-ada-002"))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_EMBEDDING_FORMAT,
+                                    kwargs.get("encoding_format", "float"))
+                # span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_EMBEDDING_DIMENSION,
+                #                     kwargs.get("dimensions", "null"))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
+                                    kwargs.get("user", ""))
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                    response_dict.get('usage').get('prompt_tokens'))
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                    response_dict.get('usage').get('total_tokens'))
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
+                                    cost)
+                if trace_content:
+                    span.add_event(
+                        name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
+                        attributes={
+                            SemanticConvetion.GEN_AI_CONTENT_PROMPT: kwargs.get("input", ""),
+                        },
+                    )
+
+                span.set_status(Status(StatusCode.OK))
+
+                if disable_metrics is False:
+                    attributes = {
+                        TELEMETRY_SDK_NAME:
+                            "openlit",
+                        SemanticConvetion.GEN_AI_APPLICATION_NAME:
+                            application_name,
+                        SemanticConvetion.GEN_AI_SYSTEM:
+                            SemanticConvetion.GEN_AI_SYSTEM_OPENAI,
+                        SemanticConvetion.GEN_AI_ENVIRONMENT:
+                            environment,
+                        SemanticConvetion.GEN_AI_TYPE:
+                            SemanticConvetion.GEN_AI_TYPE_EMBEDDING,
+                        SemanticConvetion.GEN_AI_REQUEST_MODEL:
+                            kwargs.get("model", "text-embedding-ada-002")
+                    }
+
+                    metrics["genai_requests"].add(1, attributes)
+                    metrics["genai_total_tokens"].add(
+                        response_dict.get('usage').get('total_tokens'), attributes)
+                    metrics["genai_prompt_tokens"].add(
+                        response_dict.get('usage').get('prompt_tokens'), attributes)
+                    metrics["genai_cost"].record(cost, attributes)
+
+                # Return original response
+                return response
+
+            except Exception as e:
+                handle_exception(span, e)
+                logger.error("Error in trace creation: %s", e)
+
+                # Return original response
+                return response
+
+    return wrapper

{openlit-1.30.2 → openlit-1.30.3}/src/openlit/instrumentation/openai/async_openai.py

@@ -446,11 +446,11 @@ def async_embedding(gen_ai_endpoint, version, environment, application_name,
 
         with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
             response = await wrapped(*args, **kwargs)
-
+            response_dict = response_as_dict(response)
             try:
                 # Calculate cost of the operation
                 cost = get_embed_model_cost(kwargs.get("model", "text-embedding-ada-002"),
-                                            pricing_info, response.usage.prompt_tokens)
+                                    pricing_info, response_dict.get('usage').get('prompt_tokens'))
 
                 # Set Span attributes
                 span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
@@ -473,9 +473,9 @@ def async_embedding(gen_ai_endpoint, version, environment, application_name,
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
                                     kwargs.get("user", ""))
                 span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
-                                    response.usage.prompt_tokens)
+                                    response_dict.get('usage').get('prompt_tokens'))
                 span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                                    response.usage.total_tokens)
+                                    response_dict.get('usage').get('total_tokens'))
                 span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
                                     cost)
                 if trace_content:
@@ -505,8 +505,10 @@ def async_embedding(gen_ai_endpoint, version, environment, application_name,
                     }
 
                     metrics["genai_requests"].add(1, attributes)
-                    metrics["genai_total_tokens"].add(response.usage.total_tokens, attributes)
-                    metrics["genai_prompt_tokens"].add(response.usage.prompt_tokens, attributes)
+                    metrics["genai_total_tokens"].add(
+                        response_dict.get('usage').get('total_tokens'), attributes)
+                    metrics["genai_prompt_tokens"].add(
+                        response_dict.get('usage').get('prompt_tokens'), attributes)
                     metrics["genai_cost"].record(cost, attributes)
 
                 # Return original response

{openlit-1.30.2 → openlit-1.30.3}/src/openlit/instrumentation/openai/openai.py

@@ -446,11 +446,11 @@ def embedding(gen_ai_endpoint, version, environment, application_name,
 
         with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
             response = wrapped(*args, **kwargs)
-
+            response_dict = response_as_dict(response)
             try:
                 # Calculate cost of the operation
                 cost = get_embed_model_cost(kwargs.get("model", "text-embedding-ada-002"),
-                                            pricing_info, response.usage.prompt_tokens)
+                                    pricing_info, response_dict.get('usage').get('prompt_tokens'))
 
                 # Set Span attributes
                 span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
@@ -473,9 +473,9 @@ def embedding(gen_ai_endpoint, version, environment, application_name,
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
                                     kwargs.get("user", ""))
                 span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
-                                    response.usage.prompt_tokens)
+                                    response_dict.get('usage').get('prompt_tokens'))
                 span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                                    response.usage.total_tokens)
+                                    response_dict.get('usage').get('total_tokens'))
                 span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
                                     cost)
                 if trace_content:
@@ -505,8 +505,10 @@ def embedding(gen_ai_endpoint, version, environment, application_name,
                     }
 
                     metrics["genai_requests"].add(1, attributes)
-                    metrics["genai_total_tokens"].add(response.usage.total_tokens, attributes)
-                    metrics["genai_prompt_tokens"].add(response.usage.prompt_tokens, attributes)
+                    metrics["genai_total_tokens"].add(
+                        response_dict.get('usage').get('total_tokens'), attributes)
+                    metrics["genai_prompt_tokens"].add(
+                        response_dict.get('usage').get('prompt_tokens'), attributes)
                     metrics["genai_cost"].record(cost, attributes)
 
                 # Return original response