PyPI - openlit - Versions diffs - 1.16.1__tar.gz → 1.17.0__tar.gz - Mend

openlit 1.16.1tar.gz → 1.17.0tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (58) hide show

{openlit-1.16.1 → openlit-1.17.0}/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: openlit
-Version: 1.16.1
+Version: 1.17.0
 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

{openlit-1.16.1 → openlit-1.17.0}/pyproject.toml RENAMED Viewed

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "openlit"
-version = "1.16.1"
+version = "1.17.0"
 description = "OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications, facilitating the integration of observability into your GenAI-driven projects"
 authors = ["OpenLIT"]
 repository = "https://github.com/openlit/openlit/tree/main/openlit/python"

{openlit-1.16.1 → openlit-1.17.0}/src/openlit/instrumentation/anthropic/anthropic.py RENAMED Viewed

@@ -130,7 +130,7 @@ def messages(gen_ai_endpoint, version, environment, application_name, tracer,
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_K,
                                             kwargs.get("top_k", ""))
                         span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
-                                            finish_reason)
+                                            [finish_reason])
                         span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
                                             prompt_tokens)
                         span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
@@ -140,10 +140,18 @@ def messages(gen_ai_endpoint, version, environment, application_name, tracer,
                         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.add_event(
+                                name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
+                                attributes={
+                                    SemanticConvetion.GEN_AI_CONTENT_PROMPT: prompt,
+                                },
+                            )
+                            span.add_event(
+                                name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
+                                attributes={
+                                    SemanticConvetion.GEN_AI_CONTENT_COMPLETION: llmresponse,
+                                },
+                            )
                         span.set_status(Status(StatusCode.OK))
@@ -234,7 +242,7 @@ def messages(gen_ai_endpoint, version, environment, application_name, tracer,
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_K,
                                         kwargs.get("top_k", ""))
                     span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
-                                        response.stop_reason)
+                                        [response.stop_reason])
                     span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
                                         response.usage.input_tokens)
                     span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
@@ -244,11 +252,21 @@ def messages(gen_ai_endpoint, version, environment, application_name, tracer,
                                         response.usage.output_tokens)
                     span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
                                         cost)
                     if trace_content:
-                        span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
-                                            prompt)
-                        # pylint: disable=line-too-long
-                        span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_COMPLETION, response.content[0].text if response.content else "")
+                        span.add_event(
+                            name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
+                            attributes={
+                                SemanticConvetion.GEN_AI_CONTENT_PROMPT: prompt,
+                            },
+                        )
+                        span.add_event(
+                            name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
+                            attributes={
+                                # pylint: disable=line-too-long
+                                SemanticConvetion.GEN_AI_CONTENT_COMPLETION: response.content[0].text if response.content else "",
+                            },
+                        )
                     span.set_status(Status(StatusCode.OK))

{openlit-1.16.1 → openlit-1.17.0}/src/openlit/instrumentation/anthropic/async_anthropic.py RENAMED Viewed

@@ -130,7 +130,7 @@ def async_messages(gen_ai_endpoint, version, environment, application_name,
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_K,
                                             kwargs.get("top_k", ""))
                         span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
-                                            finish_reason)
+                                            [finish_reason])
                         span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
                                             prompt_tokens)
                         span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
@@ -140,10 +140,18 @@ def async_messages(gen_ai_endpoint, version, environment, application_name,
                         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.add_event(
+                                name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
+                                attributes={
+                                    SemanticConvetion.GEN_AI_CONTENT_PROMPT: prompt,
+                                },
+                            )
+                            span.add_event(
+                                name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
+                                attributes={
+                                    SemanticConvetion.GEN_AI_CONTENT_COMPLETION: llmresponse,
+                                },
+                            )
                         span.set_status(Status(StatusCode.OK))
@@ -234,7 +242,7 @@ def async_messages(gen_ai_endpoint, version, environment, application_name,
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_K,
                                         kwargs.get("top_k", ""))
                     span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
-                                        response.stop_reason)
+                                        [response.stop_reason])
                     span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
                                         response.usage.input_tokens)
                     span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
@@ -245,10 +253,19 @@ def async_messages(gen_ai_endpoint, version, environment, application_name,
                     span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
                                         cost)
                     if trace_content:
-                        span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
-                                            prompt)
-                        # pylint: disable=line-too-long
-                        span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_COMPLETION, response.content[0].text if response.content else "")
+                        span.add_event(
+                            name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
+                            attributes={
+                                SemanticConvetion.GEN_AI_CONTENT_PROMPT: prompt,
+                            },
+                        )
+                        span.add_event(
+                            name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
+                            attributes={
+                                # pylint: disable=line-too-long
+                                SemanticConvetion.GEN_AI_CONTENT_COMPLETION: response.content[0].text if response.content else "",
+                            },
+                        )
                     span.set_status(Status(StatusCode.OK))

{openlit-1.16.1 → openlit-1.17.0}/src/openlit/instrumentation/bedrock/__init__.py RENAMED Viewed

@@ -6,9 +6,9 @@ import importlib.metadata
 from opentelemetry.instrumentation.instrumentor import BaseInstrumentor
 from wrapt import wrap_function_wrapper
-from openlit.instrumentation.bedrock.bedrock import chat
+from openlit.instrumentation.bedrock.bedrock import converse
-_instruments = ("boto3 >= 1.34.93",)
+_instruments = ("boto3 >= 1.34.138",)
 class BedrockInstrumentor(BaseInstrumentor):
     """
@@ -32,7 +32,7 @@ class BedrockInstrumentor(BaseInstrumentor):
         wrap_function_wrapper(
             "botocore.client",
             "ClientCreator.create_client",
-            chat("bedrock.invoke_model", version, environment, application_name,
+            converse("bedrock.converse", version, environment, application_name,
                      tracer, pricing_info, trace_content, metrics, disable_metrics),
         )

openlit-1.17.0/src/openlit/instrumentation/bedrock/bedrock.py ADDED Viewed

@@ -0,0 +1,206 @@
+# pylint: disable=duplicate-code, broad-exception-caught, too-many-statements, unused-argument, protected-access, too-many-branches
+"""
+Module for monitoring Amazon Bedrock API calls.
+"""
+import logging
+from botocore.response import StreamingBody
+from botocore.exceptions import ReadTimeoutError, ResponseStreamingError
+from urllib3.exceptions import ProtocolError as URLLib3ProtocolError
+from urllib3.exceptions import ReadTimeoutError as URLLib3ReadTimeoutError
+from opentelemetry.trace import SpanKind, Status, StatusCode
+from opentelemetry.sdk.resources import TELEMETRY_SDK_NAME
+from openlit.__helpers import get_chat_model_cost
+from openlit.__helpers import handle_exception
+from openlit.semcov import SemanticConvetion
+# Initialize logger for logging potential issues and operations
+logger = logging.getLogger(__name__)
+class CustomStreamWrapper(StreamingBody):
+    """Handle streaming responses with the ability to read multiple times."""
+    def __init__(self, stream_source, length):
+        super().__init__(stream_source, length)
+        self._stream_data = None
+        self._read_position = 0
+    def read(self, amt=None):
+        if self._stream_data is None:
+            try:
+                self._stream_data = self._raw_stream.read()
+            except URLLib3ReadTimeoutError as error:
+                raise ReadTimeoutError(endpoint_url=error.url, error=error) from error
+            except URLLib3ProtocolError as error:
+                raise ResponseStreamingError(error=error) from error
+            self._amount_read += len(self._stream_data)
+            if amt is None or (not self._stream_data and amt > 0):
+                self._verify_content_length()
+        if amt is None:
+            data_chunk = self._stream_data[self._read_position:]
+        else:
+            data_start = self._read_position
+            self._read_position += amt
+            data_chunk = self._stream_data[data_start:self._read_position]
+        return data_chunk
+def converse(gen_ai_endpoint, version, environment, application_name, tracer,
+         pricing_info, trace_content, metrics, disable_metrics):
+    """
+    Generates a telemetry wrapper for messages to collect metrics.
+    Args:
+        gen_ai_endpoint: Endpoint identifier for logging and tracing.
+        version: The monitoring package version.
+        environment: Deployment environment (e.g. production, staging).
+        application_name: Name of the application using the Bedrock API.
+        tracer: OpenTelemetry tracer for creating spans.
+        pricing_info: Information for calculating Bedrock usage cost.
+        trace_content: Whether to trace the actual content.
+        metrics: Metrics collector.
+        disable_metrics: Flag to toggle metrics collection.
+    Returns:
+        A function that wraps the chat method to add telemetry.
+    """
+    def wrapper(wrapped, instance, args, kwargs):
+        """
+        Wraps an API call to add telemetry.
+        Args:
+            wrapped: Original method.
+            instance: Instance of the class.
+            args: Positional arguments of the 'messages' method.
+            kwargs: Keyword arguments of the 'messages' method.
+        Returns:
+            Response from the original method.
+        """
+        def converse_wrapper(original_method, *method_args, **method_kwargs):
+            """
+            Adds instrumentation to the invoke model call.
+            Args:
+                original_method: The original invoke model method.
+                *method_args: Positional arguments for the method.
+                **method_kwargs: Keyword arguments for the method.
+            Returns:
+                The modified response with telemetry.
+            """
+            with tracer.start_as_current_span(gen_ai_endpoint, kind=SpanKind.CLIENT) as span:
+                response = original_method(*method_args, **method_kwargs)
+                try:
+                    message_prompt = method_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)
+                    model = method_kwargs.get("modelId", "amazon.titan-text-express-v1")
+                    input_tokens = response["usage"]["inputTokens"]
+                    output_tokens = response["usage"]["outputTokens"]
+                    span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+                    span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
+                                        SemanticConvetion.GEN_AI_SYSTEM_BEDROCK)
+                    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,
+                                        model)
+                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                        input_tokens)
+                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                                        output_tokens)
+                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                        input_tokens + output_tokens)
+                    # Calculate cost of the operation
+                    cost = get_chat_model_cost(model,
+                                            pricing_info, input_tokens,
+                                            output_tokens)
+                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
+                                cost)
+                    if trace_content:
+                        span.add_event(
+                            name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
+                            attributes={
+                                SemanticConvetion.GEN_AI_CONTENT_PROMPT: prompt,
+                            },
+                        )
+                        span.add_event(
+                            name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
+                            attributes={
+                                # pylint: disable=line-too-long
+                                SemanticConvetion.GEN_AI_CONTENT_COMPLETION: response["output"]["message"]["content"][0]["text"],
+                            },
+                        )
+                    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_BEDROCK,
+                            SemanticConvetion.GEN_AI_ENVIRONMENT:
+                                environment,
+                            SemanticConvetion.GEN_AI_TYPE:
+                                SemanticConvetion.GEN_AI_TYPE_CHAT,
+                            SemanticConvetion.GEN_AI_REQUEST_MODEL:
+                                model
+                        }
+                        metrics["genai_requests"].add(1, attributes)
+                        metrics["genai_total_tokens"].add(
+                            input_tokens + output_tokens, attributes
+                        )
+                        metrics["genai_completion_tokens"].add(output_tokens, attributes)
+                        metrics["genai_prompt_tokens"].add(input_tokens, attributes)
+                        metrics["genai_cost"].record(cost, attributes)
+                    return response
+                except Exception as e:
+                    handle_exception(span, e)
+                    logger.error("Error in trace creation: %s", e)
+                    # Return original response
+                    return response
+        # Get the original client instance from the wrapper
+        client = wrapped(*args, **kwargs)
+        # Replace the original method with the instrumented one
+        if kwargs.get("service_name") == "bedrock-runtime":
+            original_invoke_model = client.converse
+            client.converse = lambda *args, **kwargs: converse_wrapper(original_invoke_model,
+                                                                            *args, **kwargs)
+        return client
+    return wrapper

{openlit-1.16.1 → openlit-1.17.0}/src/openlit/instrumentation/cohere/cohere.py RENAMED Viewed

@@ -89,8 +89,12 @@ def embed(gen_ai_endpoint, version, environment, application_name, tracer,
                 span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
                                     cost)
                 if trace_content:
-                    span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
-                                        prompt)
+                    span.add_event(
+                        name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
+                        attributes={
+                            SemanticConvetion.GEN_AI_CONTENT_PROMPT: prompt,
+                        },
+                    )
                 span.set_status(Status(StatusCode.OK))
@@ -205,7 +209,7 @@ def chat(gen_ai_endpoint, version, environment, application_name, tracer,
                 span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_ID,
                                     response.generation_id)
                 span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
-                                    response.finish_reason)
+                                    [response.finish_reason])
                 span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
                                     response.meta.billed_units.input_tokens)
                 span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
@@ -215,11 +219,20 @@ def chat(gen_ai_endpoint, version, environment, application_name, tracer,
                                     response.meta.billed_units.output_tokens)
                 span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
                                     cost)
                 if trace_content:
-                    span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
-                                        kwargs.get("message", ""))
-                    span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_COMPLETION,
-                                        response.text)
+                    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,
+                        attributes={
+                            SemanticConvetion.GEN_AI_CONTENT_COMPLETION: response.text,
+                        },
+                    )
                 span.set_status(Status(StatusCode.OK))
@@ -348,7 +361,7 @@ def chat_stream(gen_ai_endpoint, version, environment, application_name,
                     span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_ID,
                                         response_id)
                     span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
-                                        finish_reason)
+                                        [finish_reason])
                     span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
                                         prompt_tokens)
                     span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
@@ -358,10 +371,18 @@ def chat_stream(gen_ai_endpoint, version, environment, application_name,
                     span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
                                         cost)
                     if trace_content:
-                        span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
-                                            kwargs.get("message", ""))
-                        span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_COMPLETION,
-                                            llmresponse)
+                        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,
+                            attributes={
+                                SemanticConvetion.GEN_AI_CONTENT_COMPLETION: llmresponse,
+                            },
+                        )
                     span.set_status(Status(StatusCode.OK))

{openlit-1.16.1 → openlit-1.17.0}/src/openlit/instrumentation/elevenlabs/async_elevenlabs.py RENAMED Viewed

@@ -80,8 +80,12 @@ def async_generate(gen_ai_endpoint, version, environment, application_name,
                 span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
                                     cost)
                 if trace_content:
-                    span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
-                                        str(kwargs.get("text", "")))
+                    span.add_event(
+                        name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
+                        attributes={
+                            SemanticConvetion.GEN_AI_CONTENT_PROMPT: str(kwargs.get("text", "")),
+                        },
+                    )
                 span.set_status(Status(StatusCode.OK))

{openlit-1.16.1 → openlit-1.17.0}/src/openlit/instrumentation/elevenlabs/elevenlabs.py RENAMED Viewed

@@ -86,8 +86,12 @@ def generate(gen_ai_endpoint, version, environment, application_name,
                 span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
                                     cost)
                 if trace_content:
-                    span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
-                                        str(kwargs.get("text", "")))
+                    span.add_event(
+                        name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
+                        attributes={
+                            SemanticConvetion.GEN_AI_CONTENT_PROMPT: str(kwargs.get("text", "")),
+                        },
+                    )
                 span.set_status(Status(StatusCode.OK))

{openlit-1.16.1 → openlit-1.17.0}/src/openlit/instrumentation/gpt4all/gpt4all.py RENAMED Viewed

@@ -107,10 +107,18 @@ def generate(gen_ai_endpoint, version, environment, application_name,
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
                                             True)
                         if trace_content:
-                            span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
-                                                prompt)
-                            span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_COMPLETION,
-                                                llmresponse)
+                            span.add_event(
+                                name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
+                                attributes={
+                                    SemanticConvetion.GEN_AI_CONTENT_PROMPT: prompt,
+                                },
+                            )
+                            span.add_event(
+                                name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
+                                attributes={
+                                    SemanticConvetion.GEN_AI_CONTENT_COMPLETION: llmresponse,
+                                },
+                            )
                         span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
                                         prompt_tokens)
@@ -195,10 +203,18 @@ def generate(gen_ai_endpoint, version, environment, application_name,
                     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)
+                        span.add_event(
+                            name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
+                            attributes={
+                                SemanticConvetion.GEN_AI_CONTENT_PROMPT: prompt,
+                            },
+                        )
+                        span.add_event(
+                            name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
+                            attributes={
+                                SemanticConvetion.GEN_AI_CONTENT_COMPLETION: response,
+                            },
+                        )
                     span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
                                         prompt_tokens)
@@ -313,8 +329,12 @@ def embed(gen_ai_endpoint, version, environment, application_name,
                 span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
                                     cost)
                 if trace_content:
-                    span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
-                                        prompt)
+                    span.add_event(
+                        name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
+                        attributes={
+                            SemanticConvetion.GEN_AI_CONTENT_PROMPT: prompt,
+                        },
+                    )
                 span.set_status(Status(StatusCode.OK))

{openlit-1.16.1 → openlit-1.17.0}/src/openlit/instrumentation/groq/async_groq.py RENAMED Viewed

@@ -141,10 +141,18 @@ def async_chat(gen_ai_endpoint, version, environment, application_name,
                         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.add_event(
+                                name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
+                                attributes={
+                                    SemanticConvetion.GEN_AI_CONTENT_PROMPT: prompt,
+                                },
+                            )
+                            span.add_event(
+                                name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
+                                attributes={
+                                    SemanticConvetion.GEN_AI_CONTENT_COMPLETION: llmresponse,
+                                },
+                            )
                         span.set_status(Status(StatusCode.OK))
@@ -237,8 +245,12 @@ def async_chat(gen_ai_endpoint, version, environment, application_name,
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
                                         False)
                     if trace_content:
-                        span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
-                                            prompt)
+                        span.add_event(
+                            name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
+                            attributes={
+                                SemanticConvetion.GEN_AI_CONTENT_PROMPT: prompt,
+                            },
+                        )
                     # Set span attributes when tools is not passed to the function call
                     if "tools" not in kwargs:
@@ -254,23 +266,31 @@ def async_chat(gen_ai_endpoint, version, environment, application_name,
                         span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
                                             response.usage.total_tokens)
                         span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
-                                            response.choices[0].finish_reason)
+                                            [response.choices[0].finish_reason])
                         span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
                                             cost)
                         # Set span attributes for when n = 1 (default)
                         if "n" not in kwargs or kwargs["n"] == 1:
                             if trace_content:
-                                span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_COMPLETION,
-                                                    response.choices[0].message.content)
+                                span.add_event(
+                                    name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
+                                    attributes={
+                                        SemanticConvetion.GEN_AI_CONTENT_COMPLETION: response.choices[0].message.content,
+                                    },
+                                )
                         # Set span attributes for when n > 0
                         else:
                             i = 0
                             while i < kwargs["n"] and trace_content is True:
                                 attribute_name = f"gen_ai.completion.{i}"
-                                span.set_attribute(attribute_name,
-                                                    response.choices[i].message.content)
+                                span.add_event(
+                                    name=attribute_name,
+                                    attributes={
+                                        SemanticConvetion.GEN_AI_CONTENT_COMPLETION: response.choices[i].message.content,
+                                    },
+                                )
                                 i += 1
                             # Return original response

openlit 1.16.1__tar.gz → 1.17.0__tar.gz

openlit 1.16.1tar.gz → 1.17.0tar.gz