openlit 1.18.1__py3-none-any.whl → 1.19.0__py3-none-any.whl

openlit/instrumentation/langchain/__init__.py

@@ -5,7 +5,14 @@ import importlib.metadata
 from opentelemetry.instrumentation.instrumentor import BaseInstrumentor
 from wrapt import wrap_function_wrapper
 
-from openlit.instrumentation.langchain.langchain import general_wrap, hub, llm, allm
+from openlit.instrumentation.langchain.langchain import (
+    general_wrap,
+    hub,
+    llm,
+    allm,
+    chat,
+    achat
+)
 
 _instruments = ("langchain >= 0.1.20",)
 
@@ -52,6 +59,18 @@ WRAPPED_METHODS = [
         "endpoint": "langchain.llm",
         "wrapper": allm,
     },
+    {
+        "package": "langchain_core.language_models.chat_models",
+        "object": "BaseChatModel.invoke",
+        "endpoint": "langchain.chat_models",
+        "wrapper": chat,
+    },
+    {
+        "package": "langchain_core.language_models.chat_models",
+        "object": "BaseChatModel.ainvoke",
+        "endpoint": "langchain.chat_models",
+        "wrapper": achat,
+    },
 ]
 
 class LangChainInstrumentor(BaseInstrumentor):
@@ -66,6 +85,8 @@ class LangChainInstrumentor(BaseInstrumentor):
         tracer = kwargs.get("tracer")
         pricing_info = kwargs.get("pricing_info")
         trace_content = kwargs.get("trace_content")
+        metrics = kwargs.get("metrics_dict")
+        disable_metrics = kwargs.get("disable_metrics")
         version = importlib.metadata.version("langchain")
 
         for wrapped_method in WRAPPED_METHODS:
@@ -77,7 +98,7 @@ class LangChainInstrumentor(BaseInstrumentor):
                 wrap_package,
                 wrap_object,
                 wrapper(gen_ai_endpoint, version, environment, application_name,
-                 tracer, pricing_info, trace_content),
+                 tracer, pricing_info, trace_content, metrics, disable_metrics),
             )
 
     @staticmethod

openlit/instrumentation/langchain/langchain.py

@@ -1,4 +1,4 @@
-# pylint: disable=duplicate-code, broad-exception-caught, too-many-statements, unused-argument
+# pylint: disable=duplicate-code, broad-exception-caught, too-many-statements, unused-argument, unused-import
 """
 Module for monitoring Langchain applications.
 """
@@ -6,14 +6,14 @@ Module for monitoring Langchain applications.
 import logging
 from opentelemetry.trace import SpanKind, Status, StatusCode
 from opentelemetry.sdk.resources import TELEMETRY_SDK_NAME
-from openlit.__helpers import handle_exception
+from openlit.__helpers import handle_exception, get_chat_model_cost, general_tokens
 from openlit.semcov import SemanticConvetion
 
 # Initialize logger for logging potential issues and operations
 logger = logging.getLogger(__name__)
 
 def general_wrap(gen_ai_endpoint, version, environment, application_name,
-                 tracer, pricing_info, trace_content):
+                 tracer, pricing_info, trace_content, metrics, disable_metrics):
     """
     Creates a wrapper around a function call to trace and log its execution metrics.
 
@@ -86,7 +86,7 @@ def general_wrap(gen_ai_endpoint, version, environment, application_name,
     return wrapper
 
 def hub(gen_ai_endpoint, version, environment, application_name, tracer,
-        pricing_info, trace_content):
+        pricing_info, trace_content, metrics, disable_metrics):
     """
     Creates a wrapper around Langchain hub operations for tracing and logging.
 
@@ -162,7 +162,7 @@ def hub(gen_ai_endpoint, version, environment, application_name, tracer,
 
 
 def allm(gen_ai_endpoint, version, environment, application_name,
-                 tracer, pricing_info, trace_content):
+                 tracer, pricing_info, trace_content, metrics, disable_metrics):
     """
     Creates a wrapper around a function call to trace and log its execution metrics.
 
@@ -207,6 +207,16 @@ def allm(gen_ai_endpoint, version, environment, application_name,
             response = await wrapped(*args, **kwargs)
 
             try:
+                prompt = args[0] or ""
+                # input_tokens = general_tokens(prompt)
+                # output_tokens = general_tokens(response)
+
+                # # Calculate cost of the operation
+                # cost = get_chat_model_cost(
+                #     str(getattr(instance, 'model')),
+                #     pricing_info, input_tokens, output_tokens
+                # )
+
                 span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
                 span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
                                     SemanticConvetion.GEN_AI_SYSTEM_LANGCHAIN)
@@ -226,13 +236,56 @@ def allm(gen_ai_endpoint, version, environment, application_name,
                                     str(getattr(instance, 'top_k')))
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
                                     str(getattr(instance, 'top_p')))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
+                                    False)
+                # span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                #                     input_tokens)
+                # span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                #                     output_tokens)
+                # span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                #                     input_tokens + output_tokens)
+                # span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
+                #                     cost)
                 if trace_content:
-                    span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
-                                        args[0])
-                    span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_COMPLETION,
-                                        response)
+                    span.add_event(
+                        name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
+                        attributes={
+                            SemanticConvetion.GEN_AI_CONTENT_PROMPT: prompt,
+                        },
+                    )
+                    span.add_event(
+                        name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
+                        attributes={
+                            SemanticConvetion.GEN_AI_CONTENT_COMPLETION: response,
+                        },
+                    )
+
                 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_LANGCHAIN,
+                #         SemanticConvetion.GEN_AI_ENVIRONMENT:
+                #             environment,
+                #         SemanticConvetion.GEN_AI_TYPE:
+                #             SemanticConvetion.GEN_AI_TYPE_CHAT,
+                #         SemanticConvetion.GEN_AI_REQUEST_MODEL:
+                #             str(getattr(instance, 'model'))
+                #     }
+
+                #     metrics["genai_requests"].add(1, attributes)
+                #     metrics["genai_total_tokens"].add(
+                #         input_tokens + output_tokens, attributes
+                #     )
+                #     metrics["genai_completion_tokens"].add(output_tokens, attributes)
+                #     metrics["genai_prompt_tokens"].add(input_tokens, attributes)
+                #     metrics["genai_cost"].record(cost, attributes)
+
                 # Return original response
                 return response
 
@@ -246,7 +299,7 @@ def allm(gen_ai_endpoint, version, environment, application_name,
     return wrapper
 
 def llm(gen_ai_endpoint, version, environment, application_name,
-                 tracer, pricing_info, trace_content):
+                 tracer, pricing_info, trace_content, metrics, disable_metrics):
     """
     Creates a wrapper around a function call to trace and log its execution metrics.
 
@@ -291,6 +344,16 @@ def llm(gen_ai_endpoint, version, environment, application_name,
             response = wrapped(*args, **kwargs)
 
             try:
+                prompt = args[0] or ""
+                # input_tokens = general_tokens(prompt)
+                # output_tokens = general_tokens(response)
+
+                # # Calculate cost of the operation
+                # cost = get_chat_model_cost(
+                #     str(getattr(instance, 'model')),
+                #     pricing_info, input_tokens, output_tokens
+                # )
+
                 span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
                 span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
                                     SemanticConvetion.GEN_AI_SYSTEM_LANGCHAIN)
@@ -310,13 +373,332 @@ def llm(gen_ai_endpoint, version, environment, application_name,
                                     str(getattr(instance, 'top_k')))
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
                                     str(getattr(instance, 'top_p')))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
+                                    False)
+                # span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                #                     input_tokens)
+                # span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                #                     output_tokens)
+                # span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                #                     input_tokens + output_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: prompt,
+                        },
+                    )
+                    span.add_event(
+                        name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
+                        attributes={
+                            SemanticConvetion.GEN_AI_CONTENT_COMPLETION: response,
+                        },
+                    )
+
+                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_LANGCHAIN,
+                #         SemanticConvetion.GEN_AI_ENVIRONMENT:
+                #             environment,
+                #         SemanticConvetion.GEN_AI_TYPE:
+                #             SemanticConvetion.GEN_AI_TYPE_CHAT,
+                #         SemanticConvetion.GEN_AI_REQUEST_MODEL:
+                #             str(getattr(instance, 'model'))
+                #     }
+
+                #     metrics["genai_requests"].add(1, attributes)
+                #     metrics["genai_total_tokens"].add(
+                #         input_tokens + output_tokens, attributes
+                #     )
+                #     metrics["genai_completion_tokens"].add(output_tokens, attributes)
+                #     metrics["genai_prompt_tokens"].add(input_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
+
+def chat(gen_ai_endpoint, version, environment, application_name,
+                 tracer, pricing_info, trace_content, metrics, disable_metrics):
+    """
+    Creates a wrapper around a function call to trace and log its execution metrics.
+
+    This function wraps any given function to measure its execution time,
+    log its operation, and trace its execution using OpenTelemetry.
+    
+    Parameters:
+    - gen_ai_endpoint (str): A descriptor or name for the endpoint being traced.
+    - version (str): The version of the Langchain application.
+    - environment (str): The deployment environment (e.g., 'production', 'development').
+    - application_name (str): Name of the Langchain application.
+    - tracer (opentelemetry.trace.Tracer): The tracer object used for OpenTelemetry tracing.
+    - pricing_info (dict): Information about the pricing for internal metrics (currently not used).
+    - trace_content (bool): Flag indicating whether to trace the content of the response.
+
+    Returns:
+    - function: A higher-order function that takes a function 'wrapped' and returns
+                a new function that wraps 'wrapped' with additional tracing and logging.
+    """
+
+    def wrapper(wrapped, instance, args, kwargs):
+        """
+        An inner wrapper function that executes the wrapped function, measures execution
+        time, and records trace data using OpenTelemetry.
+
+        Parameters:
+        - wrapped (Callable): The original function that this wrapper will execute.
+        - instance (object): The instance to which the wrapped function belongs. This
+                             is used for instance methods. For static and classmethods,
+                             this may be None.
+        - args (tuple): Positional arguments passed to the wrapped function.
+        - kwargs (dict): Keyword arguments passed to the wrapped function.
+
+        Returns:
+        - The result of the wrapped function call.
+        
+        The wrapper initiates a span with the provided tracer, sets various attributes
+        on the span based on the function's execution and response, and ensures
+        errors are handled and logged appropriately.
+        """
+        with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
+            response = wrapped(*args, **kwargs)
+
+            try:
+                input_tokens = response.response_metadata["prompt_eval_count"] or 0
+                output_tokens = response.response_metadata["eval_count"] or 0
+
+                # Calculate cost of the operation
+                cost = get_chat_model_cost(
+                    str(getattr(instance, 'model')),
+                    pricing_info, input_tokens, output_tokens
+                )
+
+                span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+                span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
+                                    SemanticConvetion.GEN_AI_SYSTEM_LANGCHAIN)
+                span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
+                                    gen_ai_endpoint)
+                span.set_attribute(SemanticConvetion.GEN_AI_ENVIRONMENT,
+                                    environment)
+                span.set_attribute(SemanticConvetion.GEN_AI_TYPE,
+                                    SemanticConvetion.GEN_AI_TYPE_CHAT)
+                span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
+                                    application_name)
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
+                                    str(getattr(instance, 'model')))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
+                                    str(getattr(instance, 'temperature')))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_K,
+                                    str(getattr(instance, 'top_k')))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
+                                    str(getattr(instance, 'top_p')))
+                span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
+                                    [response.response_metadata["done_reason"]])
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
+                                    False)
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                    input_tokens)
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                                    output_tokens)
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                    input_tokens + output_tokens)
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
+                                    cost)
                 if trace_content:
-                    span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
-                                        args[0])
-                    span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_COMPLETION,
-                                        response)
+                    span.add_event(
+                        name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
+                        attributes={
+                            SemanticConvetion.GEN_AI_CONTENT_PROMPT: args[0],
+                        },
+                    )
+                    span.add_event(
+                        name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
+                        attributes={
+                            SemanticConvetion.GEN_AI_CONTENT_COMPLETION: response.content,
+                        },
+                    )
+
                 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_LANGCHAIN,
+                        SemanticConvetion.GEN_AI_ENVIRONMENT:
+                            environment,
+                        SemanticConvetion.GEN_AI_TYPE:
+                            SemanticConvetion.GEN_AI_TYPE_CHAT,
+                        SemanticConvetion.GEN_AI_REQUEST_MODEL:
+                            str(getattr(instance, 'model'))
+                    }
+
+                    metrics["genai_requests"].add(1, attributes)
+                    metrics["genai_total_tokens"].add(
+                        input_tokens + output_tokens, attributes
+                    )
+                    metrics["genai_completion_tokens"].add(output_tokens, attributes)
+                    metrics["genai_prompt_tokens"].add(input_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
+
+def achat(gen_ai_endpoint, version, environment, application_name,
+                 tracer, pricing_info, trace_content, metrics, disable_metrics):
+    """
+    Creates a wrapper around a function call to trace and log its execution metrics.
+
+    This function wraps any given function to measure its execution time,
+    log its operation, and trace its execution using OpenTelemetry.
+    
+    Parameters:
+    - gen_ai_endpoint (str): A descriptor or name for the endpoint being traced.
+    - version (str): The version of the Langchain application.
+    - environment (str): The deployment environment (e.g., 'production', 'development').
+    - application_name (str): Name of the Langchain application.
+    - tracer (opentelemetry.trace.Tracer): The tracer object used for OpenTelemetry tracing.
+    - pricing_info (dict): Information about the pricing for internal metrics (currently not used).
+    - trace_content (bool): Flag indicating whether to trace the content of the response.
+
+    Returns:
+    - function: A higher-order function that takes a function 'wrapped' and returns
+                a new function that wraps 'wrapped' with additional tracing and logging.
+    """
+
+    async def wrapper(wrapped, instance, args, kwargs):
+        """
+        An inner wrapper function that executes the wrapped function, measures execution
+        time, and records trace data using OpenTelemetry.
+
+        Parameters:
+        - wrapped (Callable): The original function that this wrapper will execute.
+        - instance (object): The instance to which the wrapped function belongs. This
+                             is used for instance methods. For static and classmethods,
+                             this may be None.
+        - args (tuple): Positional arguments passed to the wrapped function.
+        - kwargs (dict): Keyword arguments passed to the wrapped function.
+
+        Returns:
+        - The result of the wrapped function call.
+        
+        The wrapper initiates a span with the provided tracer, sets various attributes
+        on the span based on the function's execution and response, and ensures
+        errors are handled and logged appropriately.
+        """
+        with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
+            response = await wrapped(*args, **kwargs)
+
+            try:
+                input_tokens = response.response_metadata["prompt_eval_count"] or 0
+                output_tokens = response.response_metadata["eval_count"] or 0
+
+                # Calculate cost of the operation
+                cost = get_chat_model_cost(
+                    str(getattr(instance, 'model')),
+                    pricing_info, input_tokens, output_tokens
+                )
+
+                span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+                span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
+                                    SemanticConvetion.GEN_AI_SYSTEM_LANGCHAIN)
+                span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
+                                    gen_ai_endpoint)
+                span.set_attribute(SemanticConvetion.GEN_AI_ENVIRONMENT,
+                                    environment)
+                span.set_attribute(SemanticConvetion.GEN_AI_TYPE,
+                                    SemanticConvetion.GEN_AI_TYPE_CHAT)
+                span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
+                                    application_name)
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
+                                    str(getattr(instance, 'model')))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
+                                    str(getattr(instance, 'temperature')))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_K,
+                                    str(getattr(instance, 'top_k')))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
+                                    str(getattr(instance, 'top_p')))
+                span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
+                                    [response.response_metadata["done_reason"]])
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
+                                    False)
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                    input_tokens)
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                                    output_tokens)
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                    input_tokens + output_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: args[0],
+                        },
+                    )
+                    span.add_event(
+                        name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
+                        attributes={
+                            SemanticConvetion.GEN_AI_CONTENT_COMPLETION: response.content,
+                        },
+                    )
+
+                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_LANGCHAIN,
+                        SemanticConvetion.GEN_AI_ENVIRONMENT:
+                            environment,
+                        SemanticConvetion.GEN_AI_TYPE:
+                            SemanticConvetion.GEN_AI_TYPE_CHAT,
+                        SemanticConvetion.GEN_AI_REQUEST_MODEL:
+                            str(getattr(instance, 'model'))
+                    }
+
+                    metrics["genai_requests"].add(1, attributes)
+                    metrics["genai_total_tokens"].add(
+                        input_tokens + output_tokens, attributes
+                    )
+                    metrics["genai_completion_tokens"].add(output_tokens, attributes)
+                    metrics["genai_prompt_tokens"].add(input_tokens, attributes)
+                    metrics["genai_cost"].record(cost, attributes)
+
                 # Return original response
                 return response
 

openlit/instrumentation/mistral/__init__.py

@@ -9,10 +9,10 @@ from openlit.instrumentation.mistral.mistral import chat, chat_stream, embedding
 from openlit.instrumentation.mistral.async_mistral import async_chat, async_chat_stream
 from openlit.instrumentation.mistral.async_mistral import async_embeddings
 
-_instruments = ("mistralai >= 0.1.0",)
+_instruments = ("mistralai >= 1.0.0",)
 
 class MistralInstrumentor(BaseInstrumentor):
-    """An instrumentor for Azure Mistral's client library."""
+    """An instrumentor for Mistral's client library."""
 
     def instrumentation_dependencies(self) -> Collection[str]:
         return _instruments
@@ -27,50 +27,50 @@ class MistralInstrumentor(BaseInstrumentor):
         disable_metrics = kwargs.get("disable_metrics")
         version = importlib.metadata.version("mistralai")
 
-        #sync
+        # sync
         wrap_function_wrapper(
-            "mistralai.client",  
-            "MistralClient.chat",  
+            "mistralai.chat",  
+            "Chat.complete",  
             chat("mistral.chat", version, environment, application_name,
                  tracer, pricing_info, trace_content, metrics, disable_metrics),
         )
 
-        #sync
+        # sync
         wrap_function_wrapper(
-            "mistralai.client",  
-            "MistralClient.chat_stream",  
+            "mistralai.chat",  
+            "Chat.stream",  
             chat_stream("mistral.chat", version, environment, application_name,
                         tracer, pricing_info, trace_content, metrics, disable_metrics),
         )
 
-        #sync
+        # sync
         wrap_function_wrapper(
-            "mistralai.client",  
-            "MistralClient.embeddings",  
+            "mistralai.embeddings",  
+            "Embeddings.create",  
             embeddings("mistral.embeddings", version, environment, application_name,
                        tracer, pricing_info, trace_content, metrics, disable_metrics),
         )
 
         # Async
         wrap_function_wrapper(
-            "mistralai.async_client",  
-            "MistralAsyncClient.chat",  
+            "mistralai.chat",  
+            "Chat.complete_async",  
             async_chat("mistral.chat", version, environment, application_name,
                        tracer, pricing_info, trace_content, metrics, disable_metrics),
         )
 
-        #sync
+        # Async
         wrap_function_wrapper(
-            "mistralai.async_client",  
-            "MistralAsyncClient.chat_stream",  
+            "mistralai.chat",  
+            "Chat.stream_async",  
             async_chat_stream("mistral.chat", version, environment, application_name,
                               tracer, pricing_info, trace_content, metrics, disable_metrics),
         )
 
         #sync
         wrap_function_wrapper(
-            "mistralai.async_client",  
-            "MistralAsyncClient.embeddings",  
+            "mistralai.embeddings",  
+            "Embeddings.create_async",  
             async_embeddings("mistral.embeddings", version, environment, application_name,
                              tracer, pricing_info, trace_content, metrics, disable_metrics),
         )

openlit/instrumentation/mistral/async_mistral.py

@@ -56,8 +56,8 @@ def async_chat(gen_ai_endpoint, version, environment, application_name,
                 message_prompt = kwargs.get('messages', "")
                 formatted_messages = []
                 for message in message_prompt:
-                    role = message.role
-                    content = message.content
+                    role = message["role"]
+                    content = message["content"]
 
                     if isinstance(content, list):
                         content_str = ", ".join(
@@ -207,14 +207,14 @@ def async_chat_stream(gen_ai_endpoint, version, environment, application_name,
                 llmresponse = ""
 
                 # Loop through streaming events capturing relevant details
-                async for event in wrapped(*args, **kwargs):
-                    response_id = event.id
-                    llmresponse += event.choices[0].delta.content
-                    if event.usage is not None:
-                        prompt_tokens = event.usage.prompt_tokens
-                        completion_tokens = event.usage.completion_tokens
-                        total_tokens = event.usage.total_tokens
-                        finish_reason = event.choices[0].finish_reason
+                async for event in await wrapped(*args, **kwargs):
+                    response_id = event.data.id
+                    llmresponse += event.data.choices[0].delta.content
+                    if event.data.usage is not None:
+                        prompt_tokens = event.data.usage.prompt_tokens
+                        completion_tokens = event.data.usage.completion_tokens
+                        total_tokens = event.data.usage.total_tokens
+                        finish_reason = event.data.choices[0].finish_reason
                     yield event
 
                 # Handling exception ensure observability without disrupting operation
@@ -223,8 +223,8 @@ def async_chat_stream(gen_ai_endpoint, version, environment, application_name,
                     message_prompt = kwargs.get('messages', "")
                     formatted_messages = []
                     for message in message_prompt:
-                        role = message.role
-                        content = message.content
+                        role = message["role"]
+                        content = message["content"]
 
                         if isinstance(content, list):
                             content_str = ", ".join(
@@ -364,7 +364,7 @@ def async_embeddings(gen_ai_endpoint, version, environment, application_name,
 
             try:
                 # Get prompt from kwargs and store as a single string
-                prompt = ', '.join(kwargs.get('input', []))
+                prompt = ', '.join(kwargs.get('inputs', []))
 
                 # Calculate cost of the operation
                 cost = get_embed_model_cost(kwargs.get('model', "mistral-embed"),

openlit/instrumentation/mistral/mistral.py

@@ -55,8 +55,8 @@ def chat(gen_ai_endpoint, version, environment, application_name,
                 message_prompt = kwargs.get('messages', "")
                 formatted_messages = []
                 for message in message_prompt:
-                    role = message.role
-                    content = message.content
+                    role = message["role"]
+                    content = message["content"]
 
                     if isinstance(content, list):
                         content_str = ", ".join(
@@ -207,13 +207,13 @@ def chat_stream(gen_ai_endpoint, version, environment, application_name,
 
                 # Loop through streaming events capturing relevant details
                 for event in wrapped(*args, **kwargs):
-                    response_id = event.id
-                    llmresponse += event.choices[0].delta.content
-                    if event.usage is not None:
-                        prompt_tokens = event.usage.prompt_tokens
-                        completion_tokens = event.usage.completion_tokens
-                        total_tokens = event.usage.total_tokens
-                        finish_reason = event.choices[0].finish_reason
+                    response_id = event.data.id
+                    llmresponse += event.data.choices[0].delta.content
+                    if event.data.usage is not None:
+                        prompt_tokens = event.data.usage.prompt_tokens
+                        completion_tokens = event.data.usage.completion_tokens
+                        total_tokens = event.data.usage.total_tokens
+                        finish_reason = event.data.choices[0].finish_reason
                     yield event
 
                 # Handling exception ensure observability without disrupting operation
@@ -222,8 +222,8 @@ def chat_stream(gen_ai_endpoint, version, environment, application_name,
                     message_prompt = kwargs.get('messages', "")
                     formatted_messages = []
                     for message in message_prompt:
-                        role = message.role
-                        content = message.content
+                        role = message["role"]
+                        content = message["content"]
 
                         if isinstance(content, list):
                             content_str = ", ".join(
@@ -363,7 +363,7 @@ def embeddings(gen_ai_endpoint, version, environment, application_name,
 
             try:
                 # Get prompt from kwargs and store as a single string
-                prompt = ', '.join(kwargs.get('input', []))
+                prompt = ', '.join(kwargs.get('inputs', []))
 
                 # Calculate cost of the operation
                 cost = get_embed_model_cost(kwargs.get('model', "mistral-embed"),

{openlit-1.18.1.dist-info → openlit-1.19.0.dist-info}/METADATA

@@ -1,9 +1,9 @@
 Metadata-Version: 2.1
 Name: openlit
-Version: 1.18.1
-Summary: OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications, facilitating the integration of observability into your GenAI-driven projects
+Version: 1.19.0
+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
+Keywords: OpenTelemetry,otel,otlp,llm,tracing,openai,anthropic,claude,cohere,llm monitoring,observability,monitoring,gpt,Generative AI,chatGPT,gpu
 Author: OpenLIT
 Requires-Python: >=3.7.1,<4.0.0
 Classifier: Programming Language :: Python :: 3
@@ -61,14 +61,15 @@ This project adheres to the [Semantic Conventions](https://github.com/open-telem
 | [✅ Anthropic](https://docs.openlit.io/latest/integrations/anthropic)        | [✅ Qdrant](https://docs.openlit.io/latest/integrations/qdrant)           | [✅ LlamaIndex](https://docs.openlit.io/latest/integrations/llama-index)  |               |
 | [✅ GPT4All](https://docs.openlit.io/latest/integrations/gpt4all)            | [✅ Milvus](https://docs.openlit.io/latest/integrations/milvus)           | [✅ Haystack](https://docs.openlit.io/latest/integrations/haystack)       |               |
 | [✅ Cohere](https://docs.openlit.io/latest/integrations/cohere)              |                                                                          | [✅ EmbedChain](https://docs.openlit.io/latest/integrations/embedchain)   |               |                                       
-| [✅ Mistral](https://docs.openlit.io/latest/integrations/mistral)            |                                                                          |                                       |               |
-| [✅ Azure OpenAI](https://docs.openlit.io/latest/integrations/azure-openai)  |                                                                          |                                        |               |
-| [✅ HuggingFace Transformers](https://docs.openlit.io/latest/integrations/huggingface) |                                                                          |                                       |               |
-| [✅ Amazon Bedrock](https://docs.openlit.io/latest/integrations/bedrock)     |                                                                          |                                        |               |
+| [✅ 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)  |                                                                          |                                       |               |
+| [✅ HuggingFace Transformers](https://docs.openlit.io/latest/integrations/huggingface) |                                                                          |                                        |               |
+| [✅ Amazon Bedrock](https://docs.openlit.io/latest/integrations/bedrock)     |                                                                          |                                       |               |
 | [✅ Vertex AI](https://docs.openlit.io/latest/integrations/vertexai)         |                                                                          |                                       |               |
 | [✅ Groq](https://docs.openlit.io/latest/integrations/groq)                  |                                                                          |                                       |               |
 | [✅ ElevenLabs](https://docs.openlit.io/latest/integrations/elevenlabs)      |                                                                          |                                       |               |
 | [✅ vLLM](https://docs.openlit.io/latest/integrations/vllm)                  |                                                                          |                                       |               |
+| [✅ OLA Krutrim](https://docs.openlit.io/latest/integrations/krutrim)                  |                                                                          |                                       |               |
 
 ## Supported Destinations
 - [✅ OpenTelemetry Collector](https://docs.openlit.io/latest/connections/otelcol)
@@ -77,8 +78,10 @@ This project adheres to the [Semantic Conventions](https://github.com/open-telem
 - [✅ Grafana Cloud](https://docs.openlit.io/latest/connections/grafanacloud)
 - [✅ New Relic](https://docs.openlit.io/latest/connections/new-relic)
 - [✅ Elastic](https://docs.openlit.io/latest/connections/elastic)
+- [✅ HyperDX](https://docs.openlit.io/latest/connections/hyperdx)
 - [✅ DataDog](https://docs.openlit.io/latest/connections/datadog)
 - [✅ SigNoz](https://docs.openlit.io/latest/connections/signoz)
+- [✅ OneUptime](https://docs.openlit.io/latest/connections/oneuptime)
 - [✅ Dynatrace](https://docs.openlit.io/latest/connections/dynatrace)
 - [✅ OpenObserve](https://docs.openlit.io/latest/connections/openobserve)
 - [✅ Highlight.io](https://docs.openlit.io/latest/connections/highlight)

{openlit-1.18.1.dist-info → openlit-1.19.0.dist-info}/RECORD

@@ -22,15 +22,15 @@ openlit/instrumentation/groq/async_groq.py,sha256=myob-d9V66YiNmkFd9rtmMaXjlLiSM
 openlit/instrumentation/groq/groq.py,sha256=m4gFPbYzjUUIgjXZ0Alu2Zy1HcO5takCFA2XFnkcGVo,19975
 openlit/instrumentation/haystack/__init__.py,sha256=QK6XxxZUHX8vMv2Crk7rNBOc64iOOBLhJGL_lPlAZ8s,1758
 openlit/instrumentation/haystack/haystack.py,sha256=oQIZiDhdp3gnJnhYQ1OouJMc9YT0pQ-_31cmNuopa68,3891
-openlit/instrumentation/langchain/__init__.py,sha256=19C7YGSF-6u5VlvKkThNS4zZqvxw-fQfRsKufZ9onfk,2881
-openlit/instrumentation/langchain/langchain.py,sha256=xGiRb3Z_fY1PU09hfSBFt6ipfYJIQrwFFm5HEDaawOY,16243
+openlit/instrumentation/langchain/__init__.py,sha256=0AI2Dnqw81IcJw3jM--gGkv_HRh2GtosOGJjvOpw7Zk,3431
+openlit/instrumentation/langchain/langchain.py,sha256=7K-m35sS3yTu9IklRo6n9LCcymeg6OyIYKrMzMG_uDQ,35730
 openlit/instrumentation/llamaindex/__init__.py,sha256=vPtK65G6b-TwJERowVRUVl7f_nBSlFdwPBtpg8dOGos,1977
 openlit/instrumentation/llamaindex/llamaindex.py,sha256=uiIigbwhonSbJWA7LpgOVI1R4kxxPODS1K5wyHIQ4hM,4048
 openlit/instrumentation/milvus/__init__.py,sha256=qi1yfmMrvkDtnrN_6toW8qC9BRL78bq7ayWpObJ8Bq4,2961
 openlit/instrumentation/milvus/milvus.py,sha256=qhKIoggBAJhRctRrBYz69AcvXH-eh7oBn_l9WfxpAjI,9121
-openlit/instrumentation/mistral/__init__.py,sha256=zJCIpFWRbsYrvooOJYuqwyuKeSOQLWbyXWCObL-Snks,3156
-openlit/instrumentation/mistral/async_mistral.py,sha256=WXU46nbe61IglfGehrwdprMVB6hNiuqqmJHE3XvvP0E,22192
-openlit/instrumentation/mistral/mistral.py,sha256=DC-wLIypokPEEAbVSKX5sytv94DY2QDnk12401e5vq8,22039
+openlit/instrumentation/mistral/__init__.py,sha256=niWn0gYNOTPS5zoTjtCciDqQVj-iJehnpdh7ElB-H9w,3088
+openlit/instrumentation/mistral/async_mistral.py,sha256=l-kcaGPrX3sqPH-RXWo6ope0Ui3nUvExNJ4KX9QgDMY,22246
+openlit/instrumentation/mistral/mistral.py,sha256=Q7MMRvVFsM8o0_ebZ0EfnhGjs16SJSnmu-oE798gYMQ,22087
 openlit/instrumentation/ollama/__init__.py,sha256=cOax8PiypDuo_FC4WvDCYBRo7lH5nV9xU92h7k-eZbg,3812
 openlit/instrumentation/ollama/async_ollama.py,sha256=7lbikD-I9k8VL63idqj3VMEfiEKJmFNUPR8Xb6g2phQ,31366
 openlit/instrumentation/ollama/ollama.py,sha256=lBt1d3rFnF1tFbfdOccwjEafHnmTAUGsiOKSHku6Fkw,31277
@@ -53,7 +53,7 @@ openlit/instrumentation/vllm/vllm.py,sha256=lDzM7F5pgxvh8nKL0dcKB4TD0Mc9wXOWeXOs
 openlit/otel/metrics.py,sha256=O7NoaDz0bY19mqpE4-0PcKwEe-B-iJFRgOCaanAuZAc,4291
 openlit/otel/tracing.py,sha256=vL1ifMbARPBpqK--yXYsCM6y5dSu5LFIKqkhZXtYmUc,3712
 openlit/semcov/__init__.py,sha256=EvoNOKtc7UKwLZ3Gp0-B1zwmeTcAIbx8O7wvAw8wXP4,7498
-openlit-1.18.1.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-openlit-1.18.1.dist-info/METADATA,sha256=l-nXpcuMqzXPGB-IiwqWhvkjq-pW4lsK_8Q5_rH3uoo,14334
-openlit-1.18.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-openlit-1.18.1.dist-info/RECORD,,
+openlit-1.19.0.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+openlit-1.19.0.dist-info/METADATA,sha256=7P2h2TmPkrD-DTeqa0qqaC_oiqp8LdcEZ-pjuVepCjY,14746
+openlit-1.19.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+openlit-1.19.0.dist-info/RECORD,,