openlit 1.5.0__py3-none-any.whl → 1.6.0__py3-none-any.whl

openlit/__init__.py

@@ -20,6 +20,7 @@ from openlit.instrumentation.mistral import MistralInstrumentor
 from openlit.instrumentation.bedrock import BedrockInstrumentor
 from openlit.instrumentation.vertexai import VertexAIInstrumentor
 from openlit.instrumentation.groq import GroqInstrumentor
+from openlit.instrumentation.ollama import OllamaInstrumentor
 from openlit.instrumentation.langchain import LangChainInstrumentor
 from openlit.instrumentation.llamaindex import LlamaIndexInstrumentor
 from openlit.instrumentation.haystack import HaystackInstrumentor
@@ -154,6 +155,7 @@ def init(environment="default", application_name="default", tracer=None, otlp_en
         "bedrock": "boto3",
         "vertexai": "vertexai",
         "groq": "groq",
+        "ollama": "ollama",
         "langchain": "langchain",
         "llama_index": "llama_index",
         "haystack": "haystack",
@@ -206,6 +208,7 @@ def init(environment="default", application_name="default", tracer=None, otlp_en
             "bedrock": BedrockInstrumentor(),
             "vertexai": VertexAIInstrumentor(),
             "groq": GroqInstrumentor(),
+            "ollama": OllamaInstrumentor(),
             "langchain": LangChainInstrumentor(),
             "llama_index": LlamaIndexInstrumentor(),
             "haystack": HaystackInstrumentor(),

openlit/instrumentation/ollama/__init__.py

@@ -0,0 +1,104 @@
+# pylint: disable=useless-return, bad-staticmethod-argument, disable=duplicate-code
+"""Initializer of Auto Instrumentation of Ollama Functions"""
+
+from typing import Collection
+import importlib.metadata
+from opentelemetry.instrumentation.instrumentor import BaseInstrumentor
+from wrapt import wrap_function_wrapper
+
+from openlit.instrumentation.ollama.ollama import (
+    chat, embeddings, generate
+)
+from openlit.instrumentation.ollama.async_ollama import (
+    async_chat, async_embeddings, async_generate
+)
+
+_instruments = ("ollama >= 0.2.0",)
+
+class OllamaInstrumentor(BaseInstrumentor):
+    """
+    An instrumentor for Ollama's client library.
+    """
+
+    def instrumentation_dependencies(self) -> Collection[str]:
+        return _instruments
+
+    def _instrument(self, **kwargs):
+        application_name = kwargs.get("application_name", "default_application")
+        environment = kwargs.get("environment", "default_environment")
+        tracer = kwargs.get("tracer")
+        metrics = kwargs.get("metrics_dict")
+        pricing_info = kwargs.get("pricing_info", {})
+        trace_content = kwargs.get("trace_content", False)
+        disable_metrics = kwargs.get("disable_metrics")
+        version = importlib.metadata.version("ollama")
+
+        # sync chat
+        wrap_function_wrapper(
+            "ollama",
+            "chat",
+            chat("ollama.chat", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+        wrap_function_wrapper(
+            "ollama",
+            "Client.chat",
+            chat("ollama.chat", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+        # sync embeddings
+        wrap_function_wrapper(
+            "ollama",
+            "embeddings",
+            embeddings("ollama.embeddings", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+        wrap_function_wrapper(
+            "ollama",
+            "Client.embeddings",
+            embeddings("ollama.embeddings", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+        # sync generate
+        wrap_function_wrapper(
+            "ollama",
+            "generate",
+            generate("ollama.generate", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+        wrap_function_wrapper(
+            "ollama",
+            "Client.generate",
+            generate("ollama.generate", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+        # async chat
+        wrap_function_wrapper(
+            "ollama",
+            "AsyncClient.chat",
+            async_chat("ollama.chat", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+        # async embeddings
+        wrap_function_wrapper(
+            "ollama",
+            "AsyncClient.embeddings",
+            async_embeddings("ollama.embeddings", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+        # aync generate
+        wrap_function_wrapper(
+            "ollama",
+            "AsyncClient.generate",
+            async_generate("ollama.generate", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+    def _uninstrument(self, **kwargs):
+        # Proper uninstrumentation logic to revert patched methods
+        pass

openlit/instrumentation/ollama/async_ollama.py

@@ -0,0 +1,564 @@
+# 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
+from openlit.__helpers import handle_exception, general_tokens
+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):
+    """
+    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.
+    """
+
+    async def wrapper(wrapped, instance, args, kwargs):
+        """
+        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.
+        """
+
+        # 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)
+
+                        # Calculate cost of the operation
+                        cost = 0
+                        prompt_tokens = general_tokens(prompt)
+                        total_tokens = 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_TYPE,
+                                            SemanticConvetion.GEN_AI_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_PROMPT_TOKENS,
+                                            prompt_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_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.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
+                                                prompt)
+                            span.set_attribute(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_TYPE:
+                                    SemanticConvetion.GEN_AI_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)
+
+                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_TYPE,
+                                        SemanticConvetion.GEN_AI_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.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
+                                            prompt)
+                        span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_COMPLETION,
+                                            response['message']['content'])
+
+                    # Calculate cost of the operation
+                    cost = 0
+                    prompt_tokens = general_tokens(prompt)
+                    completion_tokens = response["eval_count"]
+                    total_tokens = prompt_tokens + completion_tokens
+
+                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                        prompt_tokens)
+                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_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_TYPE:
+                                SemanticConvetion.GEN_AI_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
+
+    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.
+    """
+
+    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.
+        """
+
+        # 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:
+                        # Calculate cost of the operation
+                        cost = 0
+                        prompt_tokens = general_tokens(kwargs.get("prompt", ""))
+                        total_tokens = 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_TYPE,
+                                            SemanticConvetion.GEN_AI_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_PROMPT_TOKENS,
+                                            prompt_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_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.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
+                                                kwargs.get("prompt", ""))
+                            span.set_attribute(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_TYPE:
+                                    SemanticConvetion.GEN_AI_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)
+
+                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_TYPE,
+                                        SemanticConvetion.GEN_AI_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.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
+                                            kwargs.get("prompt", ""))
+                        span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_COMPLETION,
+                                            response['response'])
+
+                    # Calculate cost of the operation
+                    cost = 0
+                    prompt_tokens = response["prompt_eval_count"]
+                    completion_tokens = response["eval_count"]
+                    total_tokens = prompt_tokens + completion_tokens
+
+                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                        prompt_tokens)
+                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_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_TYPE:
+                                SemanticConvetion.GEN_AI_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
+
+    return wrapper
+
+def async_embeddings(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 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.
+    """
+
+    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)
+
+            try:
+                # Calculate cost of the operation
+                cost = 0
+                prompt_tokens = general_tokens(kwargs.get('prompt', ""))
+                # 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_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', "llama3"))
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_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.set_attribute(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_TYPE:
+                            SemanticConvetion.GEN_AI_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)
+
+                # 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/instrumentation/ollama/ollama.py

@@ -0,0 +1,564 @@
+# 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
+from openlit.__helpers import handle_exception, general_tokens
+from openlit.semcov import SemanticConvetion
+
+# Initialize logger for logging potential issues and operations
+logger = logging.getLogger(__name__)
+
+def chat(gen_ai_endpoint, version, environment, application_name,
+                     tracer, pricing_info, trace_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.
+    """
+
+    def wrapper(wrapped, instance, args, kwargs):
+        """
+        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.
+        """
+
+        # 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
+            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
+                    for chunk in 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)
+
+                        # Calculate cost of the operation
+                        cost = 0
+                        prompt_tokens = general_tokens(prompt)
+                        total_tokens = 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_TYPE,
+                                            SemanticConvetion.GEN_AI_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_PROMPT_TOKENS,
+                                            prompt_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_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.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
+                                                prompt)
+                            span.set_attribute(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_TYPE:
+                                    SemanticConvetion.GEN_AI_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 = wrapped(*args, **kwargs)
+
+                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_TYPE,
+                                        SemanticConvetion.GEN_AI_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.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
+                                            prompt)
+                        span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_COMPLETION,
+                                            response['message']['content'])
+
+                    # Calculate cost of the operation
+                    cost = 0
+                    prompt_tokens = general_tokens(prompt)
+                    completion_tokens = response["eval_count"]
+                    total_tokens = prompt_tokens + completion_tokens
+
+                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                        prompt_tokens)
+                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_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_TYPE:
+                                SemanticConvetion.GEN_AI_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
+
+    return wrapper
+
+def 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.
+    """
+
+    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.
+        """
+
+        # 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
+            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
+                    for chunk in 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:
+                        # Calculate cost of the operation
+                        cost = 0
+                        prompt_tokens = general_tokens(kwargs.get("prompt", ""))
+                        total_tokens = 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_TYPE,
+                                            SemanticConvetion.GEN_AI_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_PROMPT_TOKENS,
+                                            prompt_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_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.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
+                                                kwargs.get("prompt", ""))
+                            span.set_attribute(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_TYPE:
+                                    SemanticConvetion.GEN_AI_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 = 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_TYPE,
+                                        SemanticConvetion.GEN_AI_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.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
+                                            kwargs.get("prompt", ""))
+                        span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_COMPLETION,
+                                            response['response'])
+
+                    # Calculate cost of the operation
+                    cost = 0
+                    prompt_tokens = response["prompt_eval_count"]
+                    completion_tokens = response["eval_count"]
+                    total_tokens = prompt_tokens + completion_tokens
+
+                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                        prompt_tokens)
+                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_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_TYPE:
+                                SemanticConvetion.GEN_AI_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
+
+    return wrapper
+
+def embeddings(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 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.
+    """
+
+    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)
+
+            try:
+                # Calculate cost of the operation
+                cost = 0
+                prompt_tokens = general_tokens(kwargs.get('prompt', ""))
+                # 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_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', "llama3"))
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_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.set_attribute(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_TYPE:
+                            SemanticConvetion.GEN_AI_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)
+
+                # 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/semcov/__init__.py

@@ -88,6 +88,7 @@ class SemanticConvetion:
     GEN_AI_SYSTEM_BEDROCK = "bedrock"
     GEN_AI_SYSTEM_VERTEXAI = "vertexai"
     GEN_AI_SYSTEM_GROQ = "groq"
+    GEN_AI_SYSTEM_OLLAMA = "ollama"
     GEN_AI_SYSTEM_LANGCHAIN = "langchain"
     GEN_AI_SYSTEM_LLAMAINDEX = "llama_index"
     GEN_AI_SYSTEM_HAYSTACK = "haystack"

{openlit-1.5.0.dist-info → openlit-1.6.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: openlit
-Version: 1.5.0
+Version: 1.6.0
 Summary: OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications, 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
@@ -50,6 +50,7 @@ This project adheres to the [Semantic Conventions](https://github.com/open-telem
 
 ### LLMs
 - [✅ OpenAI](https://docs.openlit.io/latest/integrations/openai)
+- [✅ Ollama](https://docs.openlit.io/latest/integrations/ollama)
 - [✅ Anthropic](https://docs.openlit.io/latest/integrations/anthropic)
 - [✅ Cohere](https://docs.openlit.io/latest/integrations/cohere)
 - [✅ Mistral](https://docs.openlit.io/latest/integrations/mistral)

{openlit-1.5.0.dist-info → openlit-1.6.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
 openlit/__helpers.py,sha256=EEbLEUKuCiBp0WiieAvUnGcaU5D7grFgNVDCBgMKjQE,4651
-openlit/__init__.py,sha256=nm6JVVYnaslW5RQRvj1x0qnCQA_WBhAjHioY3w_IXlk,9647
+openlit/__init__.py,sha256=6D83ebOY_LRaOtppUrgJdJfjosF3Ao4FtomEhH21pYY,9781
 openlit/instrumentation/anthropic/__init__.py,sha256=oaU53BOPyfUKbEzYvLr1DPymDluurSnwo4Hernf2XdU,1955
 openlit/instrumentation/anthropic/anthropic.py,sha256=CYBui5eEfWdSfFF0xtCQjh1xO-gCVJc_V9Hli0szVZE,16026
 openlit/instrumentation/anthropic/async_anthropic.py,sha256=NW84kTQ3BkUx1zZuMRps_J7zTYkmq5BxOrqSjqWInBs,16068
@@ -21,6 +21,9 @@ openlit/instrumentation/llamaindex/llamaindex.py,sha256=uiIigbwhonSbJWA7LpgOVI1R
 openlit/instrumentation/mistral/__init__.py,sha256=zJCIpFWRbsYrvooOJYuqwyuKeSOQLWbyXWCObL-Snks,3156
 openlit/instrumentation/mistral/async_mistral.py,sha256=PXpiLwkonTtAPVOUh9pXMSYeabwH0GFG_HRDWrEKhMM,21361
 openlit/instrumentation/mistral/mistral.py,sha256=nbAyMlPiuA9hihePkM_nnxAjahZSndT-B-qXRO5VIhk,21212
+openlit/instrumentation/ollama/__init__.py,sha256=cOax8PiypDuo_FC4WvDCYBRo7lH5nV9xU92h7k-eZbg,3812
+openlit/instrumentation/ollama/async_ollama.py,sha256=ESk1zZTj2hPmkWIH5F2owuoo0apleDSSx5VORlO3e3w,28991
+openlit/instrumentation/ollama/ollama.py,sha256=PLGF9RB3TRNZ9GSGqeGVvKFBtgUK8Hc8xwvk-3NPeGI,28901
 openlit/instrumentation/openai/__init__.py,sha256=AZ2cPr3TMKkgGdMl_yXMeSi7bWhtmMqOW1iHdzHHGHA,16265
 openlit/instrumentation/openai/async_azure_openai.py,sha256=QE_5KHaCHAndkf7Y2Iq66mZUc0I1qtqIJ6iYPnwiuXA,46297
 openlit/instrumentation/openai/async_openai.py,sha256=qfJG_gIkSz3Gjau0zQ_G3tvkqkOd-md5LBK6wIjvH0U,45841
@@ -37,8 +40,8 @@ openlit/instrumentation/vertexai/async_vertexai.py,sha256=PMHYyLf1J4gZpC_-KZ_ZVx
 openlit/instrumentation/vertexai/vertexai.py,sha256=UvpNKBHPoV9idVMfGigZnmWuEQiyqSwZn0zK9-U7Lzw,52125
 openlit/otel/metrics.py,sha256=O7NoaDz0bY19mqpE4-0PcKwEe-B-iJFRgOCaanAuZAc,4291
 openlit/otel/tracing.py,sha256=vL1ifMbARPBpqK--yXYsCM6y5dSu5LFIKqkhZXtYmUc,3712
-openlit/semcov/__init__.py,sha256=0BHZuWE4strAmc-ilcVf6Nzoe0FEx0v9FStkccxs6mc,6168
-openlit-1.5.0.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-openlit-1.5.0.dist-info/METADATA,sha256=Z0jWHca3OkoU_dcT2STaAvAFDf3xLbPtAXfOxGAK2m0,12146
-openlit-1.5.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-openlit-1.5.0.dist-info/RECORD,,
+openlit/semcov/__init__.py,sha256=3Whg8caSmGi-rF2PVkJohpCf5O3QjpgN7ai8r4XBIVI,6204
+openlit-1.6.0.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+openlit-1.6.0.dist-info/METADATA,sha256=4qtHtjElIivkXWyJFXfUt-0_tTaidonqmJbT7Uvq8rc,12213
+openlit-1.6.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+openlit-1.6.0.dist-info/RECORD,,