PyPI - openlit - Versions diffs - 1.16.0__tar.gz → 1.16.2__tar.gz - Mend

openlit 1.16.0tar.gz → 1.16.2tar.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-1.16.0 → openlit-1.16.2}/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: openlit
-Version: 1.16.0
+Version: 1.16.2
 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
@@ -21,7 +21,7 @@ Requires-Dist: opentelemetry-instrumentation (>=0.45b0,<0.46)
 Requires-Dist: opentelemetry-sdk (>=1.24.0,<2.0.0)
 Requires-Dist: requests (>=2.26.0,<3.0.0)
 Requires-Dist: schedule (>=1.2.2,<2.0.0)
-Requires-Dist: tiktoken (>=0.6.0,<0.7.0)
+Requires-Dist: tiktoken (>=0.7.0,<0.8.0)
 Project-URL: Repository, https://github.com/openlit/openlit/tree/main/openlit/python
 Description-Content-Type: text/markdown

{openlit-1.16.0 → openlit-1.16.2}/pyproject.toml RENAMED Viewed

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "openlit"
-version = "1.16.0"
+version = "1.16.2"
 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"
@@ -12,7 +12,7 @@ keywords = ["OpenTelemetry", "otel", "otlp","llm", "tracing", "openai", "anthrop
 python = "^3.7.1"
 requests = "^2.26.0"
 schedule = "^1.2.2"
-tiktoken = "^0.6.0"
+tiktoken = "^0.7.0"
 gpustat = "^1.1.1"
 boto3 = "^1.34.0"
 botocore = "^1.34.0"

{openlit-1.16.0 → openlit-1.16.2}/src/openlit/instrumentation/anthropic/anthropic.py RENAMED Viewed

@@ -120,7 +120,7 @@ def messages(gen_ai_endpoint, version, environment, application_name, tracer,
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
                                             kwargs.get("model", "claude-3-sonnet-20240229"))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
-                                            kwargs.get("max_tokens", ""))
+                                            kwargs.get("max_tokens", -1))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
                                             True)
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
@@ -224,7 +224,7 @@ def messages(gen_ai_endpoint, version, environment, application_name, tracer,
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
                                         kwargs.get("model", "claude-3-sonnet-20240229"))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
-                                        kwargs.get("max_tokens", ""))
+                                        kwargs.get("max_tokens", -1))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
                                         False)
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,

{openlit-1.16.0 → openlit-1.16.2}/src/openlit/instrumentation/anthropic/async_anthropic.py RENAMED Viewed

@@ -120,7 +120,7 @@ def async_messages(gen_ai_endpoint, version, environment, application_name,
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
                                             kwargs.get("model", "claude-3-sonnet-20240229"))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
-                                            kwargs.get("max_tokens", ""))
+                                            kwargs.get("max_tokens", -1))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
                                             True)
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
@@ -224,7 +224,7 @@ def async_messages(gen_ai_endpoint, version, environment, application_name,
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
                                         kwargs.get("model", "claude-3-sonnet-20240229"))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
-                                        kwargs.get("max_tokens", ""))
+                                        kwargs.get("max_tokens", -1))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
                                         False)
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,

{openlit-1.16.0 → openlit-1.16.2}/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-1.16.2/src/openlit/instrumentation/bedrock/bedrock.py ADDED Viewed

@@ -0,0 +1,198 @@
+# 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", "")
+                    print(message_prompt)
+                    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.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
+                                        prompt)
+                        span.set_attribute(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-1.16.0 → openlit-1.16.2}/src/openlit/instrumentation/cohere/cohere.py RENAMED Viewed

@@ -193,7 +193,7 @@ def chat(gen_ai_endpoint, version, environment, application_name, tracer,
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
                                     kwargs.get("temperature", 0.3))
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
-                                    kwargs.get("max_tokens", ""))
+                                    kwargs.get("max_tokens", -1))
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
                                     kwargs.get("seed", ""))
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
@@ -336,7 +336,7 @@ def chat_stream(gen_ai_endpoint, version, environment, application_name,
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
                                         kwargs.get("temperature", 0.3))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
-                                        kwargs.get("max_tokens", ""))
+                                        kwargs.get("max_tokens", -1))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
                                         kwargs.get("seed", ""))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,

{openlit-1.16.0 → openlit-1.16.2}/src/openlit/instrumentation/groq/async_groq.py RENAMED Viewed

@@ -119,15 +119,15 @@ def async_chat(gen_ai_endpoint, version, environment, application_name,
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
                                             kwargs.get("user", ""))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
-                                            kwargs.get("top_p", 1))
+                                            kwargs.get("top_p", 1.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
-                                            kwargs.get("max_tokens", ""))
+                                            kwargs.get("max_tokens", -1))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                            kwargs.get("temperature", 1))
+                                            kwargs.get("temperature", 1.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                            kwargs.get("presence_penalty", 0))
+                                            kwargs.get("presence_penalty", 0.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
-                                            kwargs.get("frequency_penalty", 0))
+                                            kwargs.get("frequency_penalty", 0.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
                                             kwargs.get("seed", ""))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
@@ -221,17 +221,17 @@ def async_chat(gen_ai_endpoint, version, environment, application_name,
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
                                         kwargs.get("model", "llama3-8b-8192"))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
-                                        kwargs.get("top_p", 1))
+                                        kwargs.get("top_p", 1.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
-                                        kwargs.get("max_tokens", ""))
+                                        kwargs.get("max_tokens", -1))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
                                         kwargs.get("name", ""))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                        kwargs.get("temperature", 1))
+                                        kwargs.get("temperature", 1.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                        kwargs.get("presence_penalty", 0))
+                                        kwargs.get("presence_penalty", 0.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
-                                        kwargs.get("frequency_penalty", 0))
+                                        kwargs.get("frequency_penalty", 0.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
                                         kwargs.get("seed", ""))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,

{openlit-1.16.0 → openlit-1.16.2}/src/openlit/instrumentation/groq/groq.py RENAMED Viewed

@@ -119,15 +119,15 @@ def chat(gen_ai_endpoint, version, environment, application_name,
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
                                             kwargs.get("user", ""))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
-                                            kwargs.get("top_p", 1))
+                                            kwargs.get("top_p", 1.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
-                                            kwargs.get("max_tokens", ""))
+                                            kwargs.get("max_tokens", -1))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                            kwargs.get("temperature", 1))
+                                            kwargs.get("temperature", 1.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                            kwargs.get("presence_penalty", 0))
+                                            kwargs.get("presence_penalty", 0.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
-                                            kwargs.get("frequency_penalty", 0))
+                                            kwargs.get("frequency_penalty", 0.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
                                             kwargs.get("seed", ""))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
@@ -221,17 +221,17 @@ def chat(gen_ai_endpoint, version, environment, application_name,
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
                                         kwargs.get("model", "llama3-8b-8192"))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
-                                        kwargs.get("top_p", 1))
+                                        kwargs.get("top_p", 1.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
-                                        kwargs.get("max_tokens", ""))
+                                        kwargs.get("max_tokens", -1))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
                                         kwargs.get("name", ""))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                        kwargs.get("temperature", 1))
+                                        kwargs.get("temperature", 1.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                        kwargs.get("presence_penalty", 0))
+                                        kwargs.get("presence_penalty", 0.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
-                                        kwargs.get("frequency_penalty", 0))
+                                        kwargs.get("frequency_penalty", 0.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
                                         kwargs.get("seed", ""))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,

{openlit-1.16.0 → openlit-1.16.2}/src/openlit/instrumentation/mistral/async_mistral.py RENAMED Viewed

@@ -95,9 +95,9 @@ def async_chat(gen_ai_endpoint, version, environment, application_name,
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
                                     kwargs.get("temperature", 0.7))
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
-                                    kwargs.get("top_p", 1))
+                                    kwargs.get("top_p", 1.0))
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
-                                    kwargs.get("max_tokens", ""))
+                                    kwargs.get("max_tokens", -1))
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
                                     kwargs.get("random_seed", ""))
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
@@ -252,9 +252,9 @@ def async_chat_stream(gen_ai_endpoint, version, environment, application_name,
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
                                         kwargs.get("temperature", 0.7))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
-                                        kwargs.get("top_p", 1))
+                                        kwargs.get("top_p", 1.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
-                                        kwargs.get("max_tokens", ""))
+                                        kwargs.get("max_tokens", -1))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
                                         kwargs.get("random_seed", ""))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,

{openlit-1.16.0 → openlit-1.16.2}/src/openlit/instrumentation/mistral/mistral.py RENAMED Viewed

@@ -94,9 +94,9 @@ def chat(gen_ai_endpoint, version, environment, application_name,
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
                                     kwargs.get("temperature", 0.7))
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
-                                    kwargs.get("top_p", 1))
+                                    kwargs.get("top_p", 1.0))
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
-                                    kwargs.get("max_tokens", ""))
+                                    kwargs.get("max_tokens", -1))
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
                                     kwargs.get("random_seed", ""))
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
@@ -251,9 +251,9 @@ def chat_stream(gen_ai_endpoint, version, environment, application_name,
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
                                         kwargs.get("temperature", 0.7))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
-                                        kwargs.get("top_p", 1))
+                                        kwargs.get("top_p", 1.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
-                                        kwargs.get("max_tokens", ""))
+                                        kwargs.get("max_tokens", -1))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
                                         kwargs.get("random_seed", ""))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,

{openlit-1.16.0 → openlit-1.16.2}/src/openlit/instrumentation/openai/async_azure_openai.py RENAMED Viewed

@@ -125,11 +125,11 @@ def azure_async_chat_completions(gen_ai_endpoint, version, environment, applicat
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOOL_CHOICE,
                                             kwargs.get("tool_choice", ""))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                            kwargs.get("temperature", 1))
+                                            kwargs.get("temperature", 1.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                            kwargs.get("presence_penalty", 0))
+                                            kwargs.get("presence_penalty", 0.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
-                                            kwargs.get("frequency_penalty", 0))
+                                            kwargs.get("frequency_penalty", 0.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
                                             kwargs.get("seed", ""))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
@@ -228,11 +228,11 @@ def azure_async_chat_completions(gen_ai_endpoint, version, environment, applicat
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOOL_CHOICE,
                                         kwargs.get("tool_choice", ""))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                        kwargs.get("temperature", 1))
+                                        kwargs.get("temperature", 1.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                        kwargs.get("presence_penalty", 0))
+                                        kwargs.get("presence_penalty", 0.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
-                                        kwargs.get("frequency_penalty", 0))
+                                        kwargs.get("frequency_penalty", 0.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
                                         kwargs.get("seed", ""))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
@@ -425,11 +425,11 @@ def azure_async_completions(gen_ai_endpoint, version, environment, application_n
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOOL_CHOICE,
                                             kwargs.get("tool_choice", ""))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                            kwargs.get("temperature", 1))
+                                            kwargs.get("temperature", 1.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                            kwargs.get("presence_penalty", 0))
+                                            kwargs.get("presence_penalty", 0.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
-                                            kwargs.get("frequency_penalty", 0))
+                                            kwargs.get("frequency_penalty", 0.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
                                             kwargs.get("seed", ""))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
@@ -509,11 +509,11 @@ def azure_async_completions(gen_ai_endpoint, version, environment, application_n
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOOL_CHOICE,
                                         kwargs.get("tool_choice", ""))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                        kwargs.get("temperature", 1))
+                                        kwargs.get("temperature", 1.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                        kwargs.get("presence_penalty", 0))
+                                        kwargs.get("presence_penalty", 0.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
-                                        kwargs.get("frequency_penalty", 0))
+                                        kwargs.get("frequency_penalty", 0.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
                                         kwargs.get("seed", ""))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,

{openlit-1.16.0 → openlit-1.16.2}/src/openlit/instrumentation/openai/async_openai.py RENAMED Viewed

@@ -122,15 +122,15 @@ def async_chat_completions(gen_ai_endpoint, version, environment, application_na
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
                                             kwargs.get("user", ""))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
-                                            kwargs.get("top_p", 1))
+                                            kwargs.get("top_p", 1.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
-                                            kwargs.get("max_tokens", ""))
+                                            kwargs.get("max_tokens", -1))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                            kwargs.get("temperature", 1))
+                                            kwargs.get("temperature", 1.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                            kwargs.get("presence_penalty", 0))
+                                            kwargs.get("presence_penalty", 0.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
-                                            kwargs.get("frequency_penalty", 0))
+                                            kwargs.get("frequency_penalty", 0.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
                                             kwargs.get("seed", ""))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
@@ -224,17 +224,17 @@ def async_chat_completions(gen_ai_endpoint, version, environment, application_na
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
                                         kwargs.get("model", "gpt-3.5-turbo"))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
-                                        kwargs.get("top_p", 1))
+                                        kwargs.get("top_p", 1.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
-                                        kwargs.get("max_tokens", ""))
+                                        kwargs.get("max_tokens", -1))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
                                         kwargs.get("user", ""))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                        kwargs.get("temperature", 1))
+                                        kwargs.get("temperature", 1.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                        kwargs.get("presence_penalty", 0))
+                                        kwargs.get("presence_penalty", 0.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
-                                        kwargs.get("frequency_penalty", 0))
+                                        kwargs.get("frequency_penalty", 0.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
                                         kwargs.get("seed", ""))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,

{openlit-1.16.0 → openlit-1.16.2}/src/openlit/instrumentation/openai/azure_openai.py RENAMED Viewed

@@ -125,11 +125,11 @@ def azure_chat_completions(gen_ai_endpoint, version, environment, application_na
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOOL_CHOICE,
                                             kwargs.get("tool_choice", ""))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                            kwargs.get("temperature", 1))
+                                            kwargs.get("temperature", 1.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                            kwargs.get("presence_penalty", 0))
+                                            kwargs.get("presence_penalty", 0.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
-                                            kwargs.get("frequency_penalty", 0))
+                                            kwargs.get("frequency_penalty", 0.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
                                             kwargs.get("seed", ""))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
@@ -228,11 +228,11 @@ def azure_chat_completions(gen_ai_endpoint, version, environment, application_na
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOOL_CHOICE,
                                         kwargs.get("tool_choice", ""))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                        kwargs.get("temperature", 1))
+                                        kwargs.get("temperature", 1.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                        kwargs.get("presence_penalty", 0))
+                                        kwargs.get("presence_penalty", 0.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
-                                        kwargs.get("frequency_penalty", 0))
+                                        kwargs.get("frequency_penalty", 0.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
                                         kwargs.get("seed", ""))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
@@ -423,11 +423,11 @@ def azure_completions(gen_ai_endpoint, version, environment, application_name,
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOOL_CHOICE,
                                             kwargs.get("tool_choice", ""))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                            kwargs.get("temperature", 1))
+                                            kwargs.get("temperature", 1.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                            kwargs.get("presence_penalty", 0))
+                                            kwargs.get("presence_penalty", 0.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
-                                            kwargs.get("frequency_penalty", 0))
+                                            kwargs.get("frequency_penalty", 0.0))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
                                             kwargs.get("seed", ""))
                         span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
@@ -507,11 +507,11 @@ def azure_completions(gen_ai_endpoint, version, environment, application_name,
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOOL_CHOICE,
                                         kwargs.get("tool_choice", ""))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                        kwargs.get("temperature", 1))
+                                        kwargs.get("temperature", 1.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                        kwargs.get("presence_penalty", 0))
+                                        kwargs.get("presence_penalty", 0.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
-                                        kwargs.get("frequency_penalty", 0))
+                                        kwargs.get("frequency_penalty", 0.0))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
                                         kwargs.get("seed", ""))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,

openlit 1.16.0__tar.gz → 1.16.2__tar.gz

openlit 1.16.0tar.gz → 1.16.2tar.gz