openlit 1.32.11__tar.gz → 1.33.1__tar.gz

{openlit-1.32.11 → openlit-1.33.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: openlit
-Version: 1.32.11
+Version: 1.33.1
 Summary: OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications and GPUs, facilitating the integration of observability into your GenAI-driven projects
 Home-page: https://github.com/openlit/openlit/tree/main/openlit/python
 Keywords: OpenTelemetry,otel,otlp,llm,tracing,openai,anthropic,claude,cohere,llm monitoring,observability,monitoring,gpt,Generative AI,chatGPT,gpu
@@ -13,7 +13,7 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
-Requires-Dist: anthropic (>=0.21.0,<0.22.0)
+Requires-Dist: anthropic (>=0.42.0,<0.43.0)
 Requires-Dist: boto3 (>=1.34.0,<2.0.0)
 Requires-Dist: botocore (>=1.34.0,<2.0.0)
 Requires-Dist: openai (>=1.1.1,<2.0.0)
@@ -56,7 +56,7 @@ This project proudly follows and maintains the [Semantic Conventions](https://gi
 
 ## ⚡ Features
 
-- 🔎 **Auto Instrumentation**: Works with 40+ LLM providers, Agents, Vector databases, and GPUs with just one line of code.
+- 🔎 **Auto Instrumentation**: Works with 50+ LLM providers, Agents, Vector databases, and GPUs with just one line of code.
 - 🔭 **OpenTelemetry-Native Observability SDKs**: Vendor-neutral SDKs that can send traces and metrics to your existing observability tool like Prometheus and Jaeger.
 - 💲 **Cost Tracking for Custom and Fine-Tuned Models**: Pass custom pricing files for accurate budgeting of custom and fine-tuned models.
 - 🚀 **Suppport for OpenLIT Features**: Includes suppprt for prompt management and secrets management features available in OpenLIT.
@@ -82,13 +82,14 @@ This project proudly follows and maintains the [Semantic Conventions](https://gi
 | [✅ ElevenLabs](https://docs.openlit.io/latest/integrations/elevenlabs)              |                                                                          | [✅ ControlFlow](https://docs.openlit.io/latest/integrations/controlflow)  |               |
 | [✅ vLLM](https://docs.openlit.io/latest/integrations/vllm)                          |                                                                          | [✅ Crawl4AI](https://docs.openlit.io/latest/integrations/crawl4ai)        |               |
 | [✅ OLA Krutrim](https://docs.openlit.io/latest/integrations/krutrim)                |                                                                          | [✅ FireCrawl](https://docs.openlit.io/latest/integrations/firecrawl)      |               |
-| [✅ Google AI Studio](https://docs.openlit.io/latest/integrations/google-ai-studio)  |                                                                          |                                                |               |
+| [✅ Google AI Studio](https://docs.openlit.io/latest/integrations/google-ai-studio)  |                                                                          | [✅ Letta](https://docs.openlit.io/latest/integrations/letta)              |               |
 | [✅ NVIDIA NIM](https://docs.openlit.io/latest/integrations/nvidia-nim)              |                                                                          |                                                |               |
 | [✅ Titan ML](https://docs.openlit.io/latest/integrations/titan-ml)                  |                                                                          |                                                |               |
 | [✅ Reka AI](https://docs.openlit.io/latest/integrations/reka)                       |                                                                          |                                                |               |
 | [✅ xAI](https://docs.openlit.io/latest/integrations/xai)                            |                                                                          |                                                |               |
 | [✅ Prem AI](https://docs.openlit.io/latest/integrations/premai)                     |                                                                          |                                                |               |
 | [✅ Assembly AI](https://docs.openlit.io/latest/integrations/assemblyai)             |                                                                          |                                                |               |
+| [✅ Together](https://docs.openlit.io/latest/integrations/together)                  |                                                                          |                                                |               |
 
 ## Supported Destinations
 - [✅ OpenTelemetry Collector](https://docs.openlit.io/latest/connections/otelcol)

{openlit-1.32.11 → openlit-1.33.1}/README.md

@@ -25,7 +25,7 @@ This project proudly follows and maintains the [Semantic Conventions](https://gi
 
 ## ⚡ Features
 
-- 🔎 **Auto Instrumentation**: Works with 40+ LLM providers, Agents, Vector databases, and GPUs with just one line of code.
+- 🔎 **Auto Instrumentation**: Works with 50+ LLM providers, Agents, Vector databases, and GPUs with just one line of code.
 - 🔭 **OpenTelemetry-Native Observability SDKs**: Vendor-neutral SDKs that can send traces and metrics to your existing observability tool like Prometheus and Jaeger.
 - 💲 **Cost Tracking for Custom and Fine-Tuned Models**: Pass custom pricing files for accurate budgeting of custom and fine-tuned models.
 - 🚀 **Suppport for OpenLIT Features**: Includes suppprt for prompt management and secrets management features available in OpenLIT.
@@ -51,13 +51,14 @@ This project proudly follows and maintains the [Semantic Conventions](https://gi
 | [✅ ElevenLabs](https://docs.openlit.io/latest/integrations/elevenlabs)              |                                                                          | [✅ ControlFlow](https://docs.openlit.io/latest/integrations/controlflow)  |               |
 | [✅ vLLM](https://docs.openlit.io/latest/integrations/vllm)                          |                                                                          | [✅ Crawl4AI](https://docs.openlit.io/latest/integrations/crawl4ai)        |               |
 | [✅ OLA Krutrim](https://docs.openlit.io/latest/integrations/krutrim)                |                                                                          | [✅ FireCrawl](https://docs.openlit.io/latest/integrations/firecrawl)      |               |
-| [✅ Google AI Studio](https://docs.openlit.io/latest/integrations/google-ai-studio)  |                                                                          |                                                |               |
+| [✅ Google AI Studio](https://docs.openlit.io/latest/integrations/google-ai-studio)  |                                                                          | [✅ Letta](https://docs.openlit.io/latest/integrations/letta)              |               |
 | [✅ NVIDIA NIM](https://docs.openlit.io/latest/integrations/nvidia-nim)              |                                                                          |                                                |               |
 | [✅ Titan ML](https://docs.openlit.io/latest/integrations/titan-ml)                  |                                                                          |                                                |               |
 | [✅ Reka AI](https://docs.openlit.io/latest/integrations/reka)                       |                                                                          |                                                |               |
 | [✅ xAI](https://docs.openlit.io/latest/integrations/xai)                            |                                                                          |                                                |               |
 | [✅ Prem AI](https://docs.openlit.io/latest/integrations/premai)                     |                                                                          |                                                |               |
 | [✅ Assembly AI](https://docs.openlit.io/latest/integrations/assemblyai)             |                                                                          |                                                |               |
+| [✅ Together](https://docs.openlit.io/latest/integrations/together)                  |                                                                          |                                                |               |
 
 ## Supported Destinations
 - [✅ OpenTelemetry Collector](https://docs.openlit.io/latest/connections/otelcol)

{openlit-1.32.11 → openlit-1.33.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "openlit"
-version = "1.32.11"
+version = "1.33.1"
 description = "OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications and GPUs, facilitating the integration of observability into your GenAI-driven projects"
 authors = ["OpenLIT"]
 repository = "https://github.com/openlit/openlit/tree/main/openlit/python"
@@ -22,7 +22,7 @@ opentelemetry-sdk = "^1.27.0"
 opentelemetry-exporter-otlp = "^1.27.0"
 opentelemetry-instrumentation = "^0.48b0"
 openai = "^1.1.1"
-anthropic = "^0.21.0"
+anthropic = "^0.42.0"
 
 [build-system]
 requires = ["poetry-core>=1.1.0"]

{openlit-1.32.11 → openlit-1.33.1}/src/openlit/__init__.py

@@ -52,6 +52,7 @@ from openlit.instrumentation.milvus import MilvusInstrumentor
 from openlit.instrumentation.astra import AstraInstrumentor
 from openlit.instrumentation.transformers import TransformersInstrumentor
 from openlit.instrumentation.litellm import LiteLLMInstrumentor
+from openlit.instrumentation.together import TogetherInstrumentor
 from openlit.instrumentation.crewai import CrewAIInstrumentor
 from openlit.instrumentation.ag2 import AG2Instrumentor
 from openlit.instrumentation.multion import MultiOnInstrumentor
@@ -62,6 +63,7 @@ from openlit.instrumentation.ai21 import AI21Instrumentor
 from openlit.instrumentation.controlflow import ControlFlowInstrumentor
 from openlit.instrumentation.crawl4ai import Crawl4AIInstrumentor
 from openlit.instrumentation.firecrawl import FireCrawlInstrumentor
+from openlit.instrumentation.letta import LettaInstrumentor
 from openlit.instrumentation.gpu import GPUInstrumentor
 import openlit.guard
 import openlit.evals
@@ -187,7 +189,6 @@ def instrument_if_available(
                 metrics_dict=config.metrics_dict,
                 disable_metrics=config.disable_metrics,
             )
-            logger.info("Instrumented %s", instrumentor_name)
         else:
             # pylint: disable=line-too-long
             logger.info("Library for %s (%s) not found. Skipping instrumentation", instrumentor_name, module_name)
@@ -262,6 +263,8 @@ def init(environment="default", application_name="default", tracer=None, otlp_en
         "assemblyai": "assemblyai",
         "crawl4ai": "crawl4ai",
         "firecrawl": "firecrawl",
+        "letta": "letta",
+        "together": "together",
     }
 
     invalid_instrumentors = [
@@ -357,6 +360,8 @@ def init(environment="default", application_name="default", tracer=None, otlp_en
             "assemblyai": AssemblyAIInstrumentor(),
             "crawl4ai": Crawl4AIInstrumentor(),
             "firecrawl": FireCrawlInstrumentor(),
+            "letta": LettaInstrumentor(),
+            "together": TogetherInstrumentor(),
         }
 
         # Initialize and instrument only the enabled instrumentors

openlit-1.33.1/src/openlit/instrumentation/letta/__init__.py

@@ -0,0 +1,77 @@
+# pylint: disable=useless-return, bad-staticmethod-argument, disable=duplicate-code
+"""Initializer of Auto Instrumentation of Letta Functions"""
+
+from typing import Collection
+import importlib.metadata
+from opentelemetry.instrumentation.instrumentor import BaseInstrumentor
+from wrapt import wrap_function_wrapper
+
+from openlit.instrumentation.letta.letta import (
+    create_agent, send_message
+)
+
+_instruments = ("letta >= 0.6.2",)
+
+class LettaInstrumentor(BaseInstrumentor):
+    """
+    An instrumentor for Letta'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("letta")
+
+        wrap_function_wrapper(
+            "letta.client.client",
+            "LocalClient.create_agent",
+            create_agent("letta.create_agent", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+        wrap_function_wrapper(
+            "letta.client.client",
+            "LocalClient.get_agent",
+            create_agent("letta.get_agent", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+        wrap_function_wrapper(
+            "letta.client.client",
+            "LocalClient.send_message",
+            send_message("letta.send_message", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+        wrap_function_wrapper(
+            "letta.client.client",
+            "RESTClient.create_agent",
+            create_agent("letta.create_agent", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+        wrap_function_wrapper(
+            "letta.client.client",
+            "RESTClient.get_agent",
+            create_agent("letta.get_agent", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+        wrap_function_wrapper(
+            "letta.client.client",
+            "RESTClient.send_message",
+            send_message("letta.send_message", 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-1.33.1/src/openlit/instrumentation/letta/letta.py

@@ -0,0 +1,186 @@
+# pylint: disable=duplicate-code, broad-exception-caught, too-many-statements, unused-argument, too-many-branches
+"""
+Module for monitoring Letta calls.
+"""
+
+import logging
+from opentelemetry.trace import SpanKind, Status, StatusCode
+from opentelemetry.sdk.resources import TELEMETRY_SDK_NAME
+from openlit.__helpers import (
+    handle_exception, get_chat_model_cost
+)
+from openlit.semcov import SemanticConvetion
+
+# Initialize logger for logging potential issues and operations
+logger = logging.getLogger(__name__)
+
+def create_agent(gen_ai_endpoint, version, environment, application_name,
+                     tracer, pricing_info, trace_content, metrics, disable_metrics):
+    """
+    Generates a telemetry wrapper for chat completions 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 Letta Agent.
+        tracer: OpenTelemetry tracer for creating spans.
+        pricing_info: Information used for calculating the cost of Letta usage.
+        trace_content: Flag indicating whether to trace the actual content.
+
+    Returns:
+        A function that wraps the chat completions method to add telemetry.
+    """
+
+    def wrapper(wrapped, instance, args, kwargs):
+        """
+        Wraps the 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 method to be wrapped.
+            instance: The instance of the class where the original method is defined.
+            args: Positional arguments for the method.
+            kwargs: Keyword arguments for the method.
+
+        Returns:
+            The response from the original method.
+        """
+
+        # 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_LETTA)
+                span.set_attribute(SemanticConvetion.GEN_AI_TYPE,
+                                    SemanticConvetion.GEN_AI_TYPE_AGENT)
+                span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
+                                    gen_ai_endpoint)
+                span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
+                                    application_name)
+                span.set_attribute(SemanticConvetion.GEN_AI_AGENT_ID,
+                                    response.id)
+                span.set_attribute(SemanticConvetion.GEN_AI_AGENT_ROLE,
+                                    response.name)
+                span.set_attribute(SemanticConvetion.GEN_AI_AGENT_INSTRUCTIONS,
+                                    response.system)
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
+                                    response.llm_config.model)
+                span.set_attribute(SemanticConvetion.GEN_AI_AGENT_TYPE,
+                                    response.agent_type)
+                span.set_attribute(SemanticConvetion.GEN_AI_AGENT_TOOLS,
+                                    response.tool_names)
+
+                span.set_status(Status(StatusCode.OK))
+
+                # 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 send_message(gen_ai_endpoint, version, environment, application_name,
+                     tracer, pricing_info, trace_content, metrics, disable_metrics):
+    """
+    Generates a telemetry wrapper for chat completions 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 Letta Agent.
+        tracer: OpenTelemetry tracer for creating spans.
+        pricing_info: Information used for calculating the cost of Letta usage.
+        trace_content: Flag indicating whether to trace the actual content.
+
+    Returns:
+        A function that wraps the chat completions method to add telemetry.
+    """
+
+    def wrapper(wrapped, instance, args, kwargs):
+        """
+        Wraps the 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 method to be wrapped.
+            instance: The instance of the class where the original method is defined.
+            args: Positional arguments for the method.
+            kwargs: Keyword arguments for the method.
+
+        Returns:
+            The response from the original method.
+        """
+
+        # pylint: disable=line-too-long
+        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 = get_chat_model_cost(kwargs.get("model", "gpt-4o"),
+                                            pricing_info, response.usage.prompt_tokens,
+                                            response.usage.completion_tokens)
+                # Set base span attribues
+                span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+                span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
+                                    SemanticConvetion.GEN_AI_SYSTEM_LETTA)
+                span.set_attribute(SemanticConvetion.GEN_AI_TYPE,
+                                    SemanticConvetion.GEN_AI_TYPE_AGENT)
+                span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
+                                    gen_ai_endpoint)
+                span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
+                                    application_name)
+                span.set_attribute(SemanticConvetion.GEN_AI_AGENT_STEP_COUNT,
+                                    response.usage.step_count)
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                    response.usage.prompt_tokens)
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                                    response.usage.completion_tokens)
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                    response.usage.total_tokens)
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
+                                    cost)
+
+                if trace_content:
+                    span.add_event(
+                        name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
+                        attributes={
+                            SemanticConvetion.GEN_AI_CONTENT_PROMPT: kwargs.get("message", ""),
+                        },
+                    )
+                    span.add_event(
+                        name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
+                        # pylint: disable=line-too-long
+                        attributes={
+                            SemanticConvetion.GEN_AI_CONTENT_COMPLETION: str(response.messages),
+                        },
+                    )
+
+                span.set_status(Status(StatusCode.OK))
+
+                # Return original response
+                return response
+
+            except Exception as e:
+                handle_exception(span, e)
+                logger.error("Error in trace creation: %s", e)
+
+                # Return original response
+                return response
+
+    return wrapper

openlit-1.33.1/src/openlit/instrumentation/together/__init__.py

@@ -0,0 +1,70 @@
+# pylint: disable=useless-return, bad-staticmethod-argument, disable=duplicate-code
+"""Initializer of Auto Instrumentation of Together AI Functions"""
+
+from typing import Collection
+import importlib.metadata
+from opentelemetry.instrumentation.instrumentor import BaseInstrumentor
+from wrapt import wrap_function_wrapper
+
+from openlit.instrumentation.together.together import (
+    completion, image_generate
+)
+from openlit.instrumentation.together.async_together import (
+    async_completion, async_image_generate
+)
+
+_instruments = ("together >= 1.3.5",)
+
+class TogetherInstrumentor(BaseInstrumentor):
+    """
+    An instrumentor for Together'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("together")
+
+        # Chat completions
+        wrap_function_wrapper(
+            "together.resources.chat.completions",  
+            "ChatCompletions.create",  
+            completion("together.chat.completions", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+        # Image generate
+        wrap_function_wrapper(
+            "together.resources.images",  
+            "Images.generate",  
+            image_generate("together.image.generate", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+        # Chat completions
+        wrap_function_wrapper(
+            "together.resources.chat.completions",  
+            "AsyncChatCompletions.create",  
+            async_completion("together.chat.completions", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+        # Image generate
+        wrap_function_wrapper(
+            "together.resources.images",  
+            "AsyncImages.generate",  
+            async_image_generate("together.image.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