openlit 1.33.9__py3-none-any.whl → 1.33.11__py3-none-any.whl

openlit/instrumentation/ollama/async_ollama.py

@@ -1,610 +1,184 @@
-# pylint: disable=duplicate-code, broad-exception-caught, too-many-statements, unused-argument, possibly-used-before-assignment
 """
 Module for monitoring Ollama API calls.
 """
 
 import logging
-from opentelemetry.trace import SpanKind, Status, StatusCode
-from opentelemetry.sdk.resources import TELEMETRY_SDK_NAME
+import time
+from opentelemetry.trace import SpanKind
 from openlit.__helpers import (
     handle_exception,
-    general_tokens,
-    get_chat_model_cost,
-    get_embed_model_cost)
+    set_server_address_and_port
+)
+from openlit.instrumentation.ollama.utils import (
+    process_chunk,
+    process_chat_response,
+    process_streaming_chat_response,
+    process_embedding_response
+)
 from openlit.semcov import SemanticConvetion
 
-# Initialize logger for logging potential issues and operations
 logger = logging.getLogger(__name__)
 
-def async_chat(gen_ai_endpoint, version, environment, application_name,
-                     tracer, pricing_info, trace_content, metrics, disable_metrics):
+def async_chat(version, environment, application_name,
+            tracer, event_provider, pricing_info, capture_message_content, metrics, disable_metrics):
     """
-    Generates a telemetry wrapper for chat 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 Ollama API.
-        tracer: OpenTelemetry tracer for creating spans.
-        pricing_info: Information used for calculating the cost of Ollama usage.
-        trace_content: Flag indicating whether to trace the actual content.
-
-    Returns:
-        A function that wraps the chat method to add telemetry.
+    Generates a telemetry wrapper for GenAI function call
     """
 
-    async def wrapper(wrapped, instance, args, kwargs):
+    class TracedAsyncStream:
         """
-        Wraps the 'chat' 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 'chat' method to be wrapped.
-            instance: The instance of the class where the original method is defined.
-            args: Positional arguments for the 'chat' method.
-            kwargs: Keyword arguments for the 'chat' method.
-
-        Returns:
-            The response from the original 'chat' method.
+        Wrapper for streaming responses to collect telemetry.
         """
 
-        # Check if streaming is enabled for the API call
-        streaming = kwargs.get("stream", False)
-
-        # pylint: disable=no-else-return
-        if streaming:
-            # Special handling for streaming response to accommodate the nature of data flow
-            async def stream_generator():
-                with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
-                    # Placeholder for aggregating streaming response
-                    llmresponse = ""
-
-                    # Loop through streaming events capturing relevant details
-                    async for chunk in await wrapped(*args, **kwargs):
-                        # Collect aggregated response from events
-                        content = chunk['message']['content']
-                        llmresponse += content
-
-                        if chunk['done'] is True:
-                            completion_tokens = chunk["eval_count"]
-
-                        yield chunk
-
-                    # Handling exception ensure observability without disrupting operation
-                    try:
-                        # Format 'messages' into a single string
-                        message_prompt = kwargs.get("messages", "")
-                        formatted_messages = []
-                        for message in message_prompt:
-                            role = message["role"]
-                            content = message["content"]
-
-                            if isinstance(content, list):
-                                content_str = ", ".join(
-                                    # pylint: disable=line-too-long
-                                    f'{item["type"]}: {item["text"] if "text" in item else item["image_url"]}'
-                                    if "type" in item else f'text: {item["text"]}'
-                                    for item in content
-                                )
-                                formatted_messages.append(f"{role}: {content_str}")
-                            else:
-                                formatted_messages.append(f"{role}: {content}")
-                        prompt = "\n".join(formatted_messages)
-
-                        prompt_tokens = general_tokens(prompt)
-                        total_tokens = prompt_tokens + completion_tokens
-                        # Calculate cost of the operation
-                        cost = get_chat_model_cost(kwargs.get("model", "llama3"),
-                                                pricing_info, prompt_tokens, completion_tokens)
-
-                        # Set Span attributes
-                        span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
-                        span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
-                                            SemanticConvetion.GEN_AI_SYSTEM_OLLAMA)
-                        span.set_attribute(SemanticConvetion.GEN_AI_OPERATION,
-                                            SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT)
-                        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", "llama3"))
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
-                                            True)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_INPUT_TOKENS,
-                                            prompt_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_OUTPUT_TOKENS,
-                                            completion_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                                            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: prompt,
-                                },
-                            )
-                            span.add_event(
-                                name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
-                                attributes={
-                                    SemanticConvetion.GEN_AI_CONTENT_COMPLETION: llmresponse,
-                                },
-                            )
-
-                        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_OLLAMA,
-                                SemanticConvetion.GEN_AI_ENVIRONMENT:
-                                    environment,
-                                SemanticConvetion.GEN_AI_OPERATION:
-                                    SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT,
-                                SemanticConvetion.GEN_AI_REQUEST_MODEL:
-                                    kwargs.get("model", "llama3")
-                            }
-
-                            metrics["genai_requests"].add(1, attributes)
-                            metrics["genai_total_tokens"].add(total_tokens, attributes)
-                            metrics["genai_completion_tokens"].add(completion_tokens, attributes)
-                            metrics["genai_prompt_tokens"].add(prompt_tokens, attributes)
-                            metrics["genai_cost"].record(cost, attributes)
-
-                    except Exception as e:
-                        handle_exception(span, e)
-                        logger.error("Error in trace creation: %s", e)
-
-            return stream_generator()
-
-        # Handling for non-streaming responses
-        else:
-            # pylint: disable=line-too-long
-            with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
-                response = await wrapped(*args, **kwargs)
-
+        def __init__(
+                self,
+                wrapped,
+                span,
+                span_name,
+                kwargs,
+                server_address,
+                server_port,
+                **args,
+            ):
+            self.__wrapped__ = wrapped
+            self._span = span
+            self._llmresponse = ""
+            self._response_model = ""
+            self._finish_reason = ""
+            self._tool_calls = []
+            self._input_tokens = 0
+            self._output_tokens = 0
+            self._response_role = ''
+            self._span_name = span_name
+            self._args = args
+            self._kwargs = kwargs
+            self._start_time = time.time()
+            self._end_time = None
+            self._timestamps = []
+            self._ttft = 0
+            self._tbt = 0
+            self._server_address = server_address
+            self._server_port = server_port
+
+        async def __aenter__(self):
+            await self.__wrapped__.__aenter__()
+            return self
+
+        async def __aexit__(self, exc_type, exc_value, traceback):
+            await self.__wrapped__.__aexit__(exc_type, exc_value, traceback)
+
+        def __aiter__(self):
+            return self
+
+        async def __getattr__(self, name):
+            """Delegate attribute access to the wrapped object."""
+            return getattr(await self.__wrapped__, name)
+
+        async def __anext__(self):
+            try:
+                chunk = await self.__wrapped__.__anext__()
+                process_chunk(self, chunk)
+                return chunk
+            except StopAsyncIteration:
                 try:
-                    # Format 'messages' into a single string
-                    message_prompt = kwargs.get("messages", "")
-                    formatted_messages = []
-                    for message in message_prompt:
-                        role = message["role"]
-                        content = message["content"]
-
-                        if isinstance(content, list):
-                            content_str = ", ".join(
-                                # pylint: disable=line-too-long
-                                f'{item["type"]}: {item["text"] if "text" in item else item["image_url"]}'
-                                if "type" in item else f'text: {item["text"]}'
-                                for item in content
-                            )
-                            formatted_messages.append(f"{role}: {content_str}")
-                        else:
-                            formatted_messages.append(f"{role}: {content}")
-                    prompt = "\n".join(formatted_messages)
-
-                    # Set base span attribues
-                    span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
-                    span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
-                                        SemanticConvetion.GEN_AI_SYSTEM_OLLAMA)
-                    span.set_attribute(SemanticConvetion.GEN_AI_OPERATION,
-                                        SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT)
-                    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", "llama3"))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
-                                        False)
-                    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['message']['content'],
-                            },
+                    with tracer.start_as_current_span(self._span_name, kind= SpanKind.CLIENT) as self._span:
+                        process_streaming_chat_response(
+                            self,
+                            pricing_info=pricing_info,
+                            environment=environment,
+                            application_name=application_name,
+                            metrics=metrics,
+                            event_provider=event_provider,
+                            capture_message_content=capture_message_content,
+                            disable_metrics=disable_metrics,
+                            version=version
                         )
-
-                    prompt_tokens = general_tokens(prompt)
-                    completion_tokens = response["eval_count"]
-                    total_tokens = prompt_tokens + completion_tokens
-                    # Calculate cost of the operation
-                    cost = get_chat_model_cost(kwargs.get("model", "llama3"),
-                                                pricing_info, prompt_tokens, completion_tokens)
-
-                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_INPUT_TOKENS,
-                                        prompt_tokens)
-                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_OUTPUT_TOKENS,
-                                        completion_tokens)
-                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                                        total_tokens)
-                    span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
-                                        [response["done_reason"]])
-                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
-                                        cost)
-
-                    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_OLLAMA,
-                            SemanticConvetion.GEN_AI_ENVIRONMENT:
-                                environment,
-                            SemanticConvetion.GEN_AI_OPERATION:
-                                SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT,
-                            SemanticConvetion.GEN_AI_REQUEST_MODEL:
-                                kwargs.get("model", "llama3")
-                        }
-
-                        metrics["genai_requests"].add(1, attributes)
-                        metrics["genai_total_tokens"].add(total_tokens, attributes)
-                        metrics["genai_completion_tokens"].add(completion_tokens, attributes)
-                        metrics["genai_prompt_tokens"].add(prompt_tokens, attributes)
-                        metrics["genai_cost"].record(cost, attributes)
-
-                    # Return original response
-                    return response
-
                 except Exception as e:
-                    handle_exception(span, e)
+                    handle_exception(self._span, e)
                     logger.error("Error in trace creation: %s", e)
-
-                    # Return original response
-                    return response
-
-    return wrapper
-
-def async_generate(gen_ai_endpoint, version, environment, application_name,
-                     tracer, pricing_info, trace_content, metrics, disable_metrics):
-    """
-    Generates a telemetry wrapper for generate 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 Ollama API.
-        tracer: OpenTelemetry tracer for creating spans.
-        pricing_info: Information used for calculating the cost of Ollama usage.
-        trace_content: Flag indicating whether to trace the actual content.
-
-    Returns:
-        A function that wraps the generate method to add telemetry.
-    """
+                raise
 
     async def wrapper(wrapped, instance, args, kwargs):
         """
-        Wraps the 'generate' 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 'generate' method to be wrapped.
-            instance: The instance of the class where the original method is defined.
-            args: Positional arguments for the 'generate' method.
-            kwargs: Keyword arguments for the 'generate' method.
-
-        Returns:
-            The response from the original 'generate' method.
+        Wraps the GenAI function call.
         """
 
-        # Check if streaming is enabled for the API call
         streaming = kwargs.get("stream", False)
 
-        # pylint: disable=no-else-return
-        if streaming:
-            # Special handling for streaming response to accommodate the nature of data flow
-            async def stream_generator():
-                with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
-                    # Placeholder for aggregating streaming response
-                    llmresponse = ""
-
-                    # Loop through streaming events capturing relevant details
-                    async for chunk in await wrapped(*args, **kwargs):
-                        # Collect aggregated response from events
-                        content = chunk['response']
-                        llmresponse += content
-
-                        if chunk['done'] is True:
-                            completion_tokens = chunk["eval_count"]
-
-                        yield chunk
-
-                    # Handling exception ensure observability without disrupting operation
-                    try:
-                        prompt_tokens = general_tokens(kwargs.get("prompt", ""))
-                        total_tokens = prompt_tokens + completion_tokens
-                        # Calculate cost of the operation
-                        cost = get_chat_model_cost(kwargs.get("model", "llama3"),
-                                                pricing_info, prompt_tokens, completion_tokens)
-
-                        # Set Span attributes
-                        span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
-                        span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
-                                            SemanticConvetion.GEN_AI_SYSTEM_OLLAMA)
-                        span.set_attribute(SemanticConvetion.GEN_AI_OPERATION,
-                                            SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT)
-                        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", "llama3"))
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
-                                            True)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_INPUT_TOKENS,
-                                            prompt_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_OUTPUT_TOKENS,
-                                            completion_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                                            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={
-                                    # pylint: disable=line-too-long
-                                    SemanticConvetion.GEN_AI_CONTENT_PROMPT: kwargs.get("prompt", ""),
-                                },
-                            )
-                            span.add_event(
-                                name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
-                                attributes={
-                                    SemanticConvetion.GEN_AI_CONTENT_COMPLETION: llmresponse,
-                                },
-                            )
+        server_address, server_port = set_server_address_and_port(instance, "127.0.0.1", 11434)
+        request_model = kwargs.get("model", "gpt-4o")
 
-                        span.set_status(Status(StatusCode.OK))
+        span_name = f"{SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
 
-                        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_OLLAMA,
-                                SemanticConvetion.GEN_AI_ENVIRONMENT:
-                                    environment,
-                                SemanticConvetion.GEN_AI_OPERATION:
-                                    SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT,
-                                SemanticConvetion.GEN_AI_REQUEST_MODEL:
-                                    kwargs.get("model", "llama3")
-                            }
-
-                            metrics["genai_requests"].add(1, attributes)
-                            metrics["genai_total_tokens"].add(total_tokens, attributes)
-                            metrics["genai_completion_tokens"].add(completion_tokens, attributes)
-                            metrics["genai_prompt_tokens"].add(prompt_tokens, attributes)
-                            metrics["genai_cost"].record(cost, attributes)
-
-                    except Exception as e:
-                        handle_exception(span, e)
-                        logger.error("Error in trace creation: %s", e)
-
-            return stream_generator()
+        # pylint: disable=no-else-return
+        if streaming:
+            awaited_wrapped = await wrapped(*args, **kwargs)
+            span = tracer.start_span(span_name, kind=SpanKind.CLIENT)
+            return TracedAsyncStream(awaited_wrapped, span, span_name, kwargs, server_address, server_port)
 
-        # Handling for non-streaming responses
         else:
-            # pylint: disable=line-too-long
-            with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
+            with tracer.start_as_current_span(span_name, kind= SpanKind.CLIENT) as span:
+                start_time = time.time()
                 response = await wrapped(*args, **kwargs)
-
-                try:
-                    # Set base span attribues
-                    span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
-                    span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
-                                        SemanticConvetion.GEN_AI_SYSTEM_OLLAMA)
-                    span.set_attribute(SemanticConvetion.GEN_AI_OPERATION,
-                                        SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT)
-                    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", "llama3"))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
-                                        False)
-                    if trace_content:
-                        span.add_event(
-                            name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
-                            attributes={
-                                SemanticConvetion.GEN_AI_CONTENT_PROMPT: kwargs.get("prompt", ""),
-                            },
-                        )
-                        span.add_event(
-                            name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
-                            attributes={
-                                SemanticConvetion.GEN_AI_CONTENT_COMPLETION: response['response'],
-                            },
-                        )
-
-                    prompt_tokens = response["prompt_eval_count"]
-                    completion_tokens = response["eval_count"]
-                    total_tokens = prompt_tokens + completion_tokens
-                    # Calculate cost of the operation
-                    cost = get_chat_model_cost(kwargs.get("model", "llama3"),
-                                                pricing_info, prompt_tokens, completion_tokens)
-
-                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_INPUT_TOKENS,
-                                        prompt_tokens)
-                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_OUTPUT_TOKENS,
-                                        completion_tokens)
-                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                                        total_tokens)
-                    span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
-                                        [response["done_reason"]])
-                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
-                                        cost)
-
-                    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_OLLAMA,
-                            SemanticConvetion.GEN_AI_ENVIRONMENT:
-                                environment,
-                            SemanticConvetion.GEN_AI_OPERATION:
-                                SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT,
-                            SemanticConvetion.GEN_AI_REQUEST_MODEL:
-                                kwargs.get("model", "llama3")
-                        }
-
-                        metrics["genai_requests"].add(1, attributes)
-                        metrics["genai_total_tokens"].add(total_tokens, attributes)
-                        metrics["genai_completion_tokens"].add(completion_tokens, attributes)
-                        metrics["genai_prompt_tokens"].add(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
+                response = process_chat_response(
+                    response=response,
+                    request_model=request_model,
+                    pricing_info=pricing_info,
+                    server_port=server_port,
+                    server_address=server_address,
+                    environment=environment,
+                    application_name=application_name,
+                    metrics=metrics,
+                    event_provider=event_provider,
+                    start_time=start_time,
+                    span=span,
+                    capture_message_content=capture_message_content,
+                    disable_metrics=disable_metrics,
+                    version=version,
+                    **kwargs
+                )
+
+            return response
 
     return wrapper
 
-def async_embeddings(gen_ai_endpoint, version, environment, application_name,
-               tracer, pricing_info, trace_content, metrics, disable_metrics):
+def async_embeddings(version, environment, application_name,
+              tracer, event_provider, pricing_info, capture_message_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 Ollama API.
-        tracer: OpenTelemetry tracer for creating spans.
-        pricing_info: Information used for calculating the cost of Ollama usage.
-        trace_content: Flag indicating whether to trace the actual content.
-    
-    Returns:
-        A function that wraps the embeddings method to add telemetry.
+    Generates a telemetry wrapper for GenAI function call
     """
 
     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.
+        Wraps the GenAI function call.
         """
 
-        with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
-            response = await wrapped(*args, **kwargs)
-
-            try:
-                prompt_tokens = general_tokens(kwargs.get('prompt', ""))
-                # Calculate cost of the operation
-                cost = get_embed_model_cost(kwargs.get('model', "mistral-embed"),
-                                            pricing_info, prompt_tokens)
-                # Set Span attributes
-                span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
-                span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
-                                    SemanticConvetion.GEN_AI_SYSTEM_OLLAMA)
-                span.set_attribute(SemanticConvetion.GEN_AI_OPERATION,
-                                    SemanticConvetion.GEN_AI_OPERATION_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', "llama3"))
-                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_INPUT_TOKENS,
-                                    prompt_tokens)
-                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                                    prompt_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("prompt", ""),
-                        },
-                    )
-
-                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_OLLAMA,
-                        SemanticConvetion.GEN_AI_ENVIRONMENT:
-                            environment,
-                        SemanticConvetion.GEN_AI_OPERATION:
-                            SemanticConvetion.GEN_AI_OPERATION_TYPE_EMBEDDING,
-                        SemanticConvetion.GEN_AI_REQUEST_MODEL:
-                            kwargs.get('model', "llama3")
-                    }
-
-                    metrics["genai_requests"].add(1, attributes)
-                    metrics["genai_total_tokens"].add(prompt_tokens, attributes)
-                    metrics["genai_prompt_tokens"].add(prompt_tokens, attributes)
-                    metrics["genai_cost"].record(cost, attributes)
+        server_address, server_port = set_server_address_and_port(instance, '127.0.0.1', 11434)
+        request_model = kwargs.get('model', 'all-minilm')
 
-                # Return original response
-                return response
+        span_name = f'{SemanticConvetion.GEN_AI_OPERATION_TYPE_EMBEDDING} {request_model}'
 
-            except Exception as e:
-                handle_exception(span, e)
-                logger.error("Error in trace creation: %s", e)
-
-                # Return original response
-                return response
+        with tracer.start_as_current_span(span_name, kind= SpanKind.CLIENT) as span:
+            start_time = time.time()
+            response = await wrapped(*args, **kwargs)
+            response = process_embedding_response(
+                response=response,
+                request_model=request_model,
+                pricing_info=pricing_info,
+                server_port=server_port,
+                server_address=server_address,
+                environment=environment,
+                application_name=application_name,
+                metrics=metrics,
+                event_provider=event_provider,
+                start_time=start_time,
+                span=span,
+                capture_message_content=capture_message_content,
+                disable_metrics=disable_metrics,
+                version=version,
+                **kwargs
+            )
+
+        return response
 
     return wrapper