openlit 1.34.29__py3-none-any.whl → 1.34.31__py3-none-any.whl

openlit/instrumentation/google_ai_studio/utils.py

@@ -1,8 +1,13 @@
 """
 Google AI Studio OpenTelemetry instrumentation utility functions
 """
+
 import time
-from opentelemetry.sdk.resources import SERVICE_NAME, TELEMETRY_SDK_NAME, DEPLOYMENT_ENVIRONMENT
+from opentelemetry.sdk.resources import (
+    SERVICE_NAME,
+    TELEMETRY_SDK_NAME,
+    DEPLOYMENT_ENVIRONMENT,
+)
 from opentelemetry.trace import Status, StatusCode
 from openlit.__helpers import (
     calculate_ttft,
@@ -13,6 +18,7 @@ from openlit.__helpers import (
 )
 from openlit.semcov import SemanticConvention
 
+
 def format_content(messages):
     """
     Process a list of messages to extract content.
@@ -37,7 +43,9 @@ def format_content(messages):
                     if part.thought:
                         content_str.append(f"thought: {part.thought}")
                     if part.code_execution_result:
-                        content_str.append(f"code_execution_result: {part.code_execution_result}")
+                        content_str.append(
+                            f"code_execution_result: {part.code_execution_result}"
+                        )
                     if part.executable_code:
                         content_str.append(f"executable_code: {part.executable_code}")
                     if part.file_data:
@@ -45,7 +53,9 @@ def format_content(messages):
                     if part.function_call:
                         content_str.append(f"function_call: {part.function_call}")
                     if part.function_response:
-                        content_str.append(f"function_response: {part.function_response}")
+                        content_str.append(
+                            f"function_response: {part.function_response}"
+                        )
                     if part.inline_data:
                         content_str.append(f"inline_data: {part.inline_data}")
 
@@ -61,6 +71,7 @@ def format_content(messages):
 
     return prompt
 
+
 def process_chunk(self, chunk):
     """
     Process a chunk of response data and update state.
@@ -76,25 +87,41 @@ def process_chunk(self, chunk):
 
     chunked = response_as_dict(chunk)
 
-
-    self._response_id = str(chunked.get('response_id'))
-    self._input_tokens = chunked.get('usage_metadata').get('prompt_token_count')
-    self._response_model = chunked.get('model_version')
+    self._response_id = str(chunked.get("response_id"))
+    self._input_tokens = chunked.get("usage_metadata").get("prompt_token_count")
+    self._response_model = chunked.get("model_version")
 
     if chunk.text:
         self._llmresponse += str(chunk.text)
 
-    self._output_tokens = chunked.get('usage_metadata').get('candidates_token_count')
-    self._reasoning_tokens = chunked.get('usage_metadata').get('thoughts_token_count') or 0
-    self._finish_reason = str(chunked.get('candidates')[0].get('finish_reason'))
+    self._output_tokens = chunked.get("usage_metadata").get("candidates_token_count")
+    self._reasoning_tokens = (
+        chunked.get("usage_metadata").get("thoughts_token_count") or 0
+    )
+    self._finish_reason = str(chunked.get("candidates")[0].get("finish_reason"))
 
     try:
-        self._tools = chunked.get('candidates', [])[0].get('content', {}).get('parts', [])[0].get('function_call', '')
+        self._tools = (
+            chunked.get("candidates", [])[0]
+            .get("content", {})
+            .get("parts", [])[0]
+            .get("function_call", "")
+        )
     except:
         self._tools = None
 
-def common_chat_logic(scope, pricing_info, environment, application_name, metrics,
-    capture_message_content, disable_metrics, version, is_stream):
+
+def common_chat_logic(
+    scope,
+    pricing_info,
+    environment,
+    application_name,
+    metrics,
+    capture_message_content,
+    disable_metrics,
+    version,
+    is_stream,
+):
     """
     Process chat request and generate Telemetry
     """
@@ -103,29 +130,36 @@ def common_chat_logic(scope, pricing_info, environment, application_name, metric
     if len(scope._timestamps) > 1:
         scope._tbt = calculate_tbt(scope._timestamps)
 
-    prompt = format_content(scope._kwargs.get('contents', ''))
+    prompt = format_content(scope._kwargs.get("contents", ""))
     request_model = scope._kwargs.get("model", "gemini-2.0-flash")
 
-    cost = get_chat_model_cost(request_model, pricing_info, scope._input_tokens, scope._output_tokens)
+    cost = get_chat_model_cost(
+        request_model, pricing_info, scope._input_tokens, scope._output_tokens
+    )
 
     # Set Span attributes (OTel Semconv)
-    scope._span.set_attribute(TELEMETRY_SDK_NAME, 'openlit')
-    scope._span.set_attribute(SemanticConvention.GEN_AI_OPERATION, SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT)
-    scope._span.set_attribute(SemanticConvention.GEN_AI_SYSTEM, SemanticConvention.GEN_AI_SYSTEM_GEMINI)
+    scope._span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+    scope._span.set_attribute(
+        SemanticConvention.GEN_AI_OPERATION,
+        SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT,
+    )
+    scope._span.set_attribute(
+        SemanticConvention.GEN_AI_SYSTEM, SemanticConvention.GEN_AI_SYSTEM_GEMINI
+    )
     scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_MODEL, request_model)
     scope._span.set_attribute(SemanticConvention.SERVER_PORT, scope._server_port)
     scope._span.set_attribute(SemanticConvention.SERVER_ADDRESS, scope._server_address)
 
-    inference_config = scope._kwargs.get('config', {})
+    inference_config = scope._kwargs.get("config", {})
 
     attributes = [
-        (SemanticConvention.GEN_AI_REQUEST_FREQUENCY_PENALTY, 'frequency_penalty'),
-        (SemanticConvention.GEN_AI_REQUEST_MAX_TOKENS, 'max_tokens'),
-        (SemanticConvention.GEN_AI_REQUEST_PRESENCE_PENALTY, 'presence_penalty'),
-        (SemanticConvention.GEN_AI_REQUEST_STOP_SEQUENCES, 'stop_sequences'),
-        (SemanticConvention.GEN_AI_REQUEST_TEMPERATURE, 'temperature'),
-        (SemanticConvention.GEN_AI_REQUEST_TOP_P, 'top_p'),
-        (SemanticConvention.GEN_AI_REQUEST_TOP_K, 'top_k'),
+        (SemanticConvention.GEN_AI_REQUEST_FREQUENCY_PENALTY, "frequency_penalty"),
+        (SemanticConvention.GEN_AI_REQUEST_MAX_TOKENS, "max_tokens"),
+        (SemanticConvention.GEN_AI_REQUEST_PRESENCE_PENALTY, "presence_penalty"),
+        (SemanticConvention.GEN_AI_REQUEST_STOP_SEQUENCES, "stop_sequences"),
+        (SemanticConvention.GEN_AI_REQUEST_TEMPERATURE, "temperature"),
+        (SemanticConvention.GEN_AI_REQUEST_TOP_P, "top_p"),
+        (SemanticConvention.GEN_AI_REQUEST_TOP_K, "top_k"),
     ]
 
     # Set each attribute if the corresponding value exists and is not None
@@ -135,14 +169,26 @@ def common_chat_logic(scope, pricing_info, environment, application_name, metric
         if value is not None:
             scope._span.set_attribute(attribute, value)
 
-    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_FINISH_REASON, [scope._finish_reason])
-    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_MODEL, scope._response_model)
-    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_INPUT_TOKENS, scope._input_tokens)
-    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_OUTPUT_TOKENS, scope._output_tokens)
-    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_REASONING_TOKENS, scope._reasoning_tokens)
-
-    scope._span.set_attribute(SemanticConvention.GEN_AI_OUTPUT_TYPE,
-                              'text' if isinstance(scope._llmresponse, str) else 'json')
+    scope._span.set_attribute(
+        SemanticConvention.GEN_AI_RESPONSE_FINISH_REASON, [scope._finish_reason]
+    )
+    scope._span.set_attribute(
+        SemanticConvention.GEN_AI_RESPONSE_MODEL, scope._response_model
+    )
+    scope._span.set_attribute(
+        SemanticConvention.GEN_AI_USAGE_INPUT_TOKENS, scope._input_tokens
+    )
+    scope._span.set_attribute(
+        SemanticConvention.GEN_AI_USAGE_OUTPUT_TOKENS, scope._output_tokens
+    )
+    scope._span.set_attribute(
+        SemanticConvention.GEN_AI_USAGE_REASONING_TOKENS, scope._reasoning_tokens
+    )
+
+    scope._span.set_attribute(
+        SemanticConvention.GEN_AI_OUTPUT_TYPE,
+        "text" if isinstance(scope._llmresponse, str) else "json",
+    )
 
     scope._span.set_attribute(DEPLOYMENT_ENVIRONMENT, environment)
     scope._span.set_attribute(SERVICE_NAME, application_name)
@@ -151,18 +197,28 @@ def common_chat_logic(scope, pricing_info, environment, application_name, metric
     scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TBT, scope._tbt)
     scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TTFT, scope._ttft)
     scope._span.set_attribute(SemanticConvention.GEN_AI_SDK_VERSION, version)
-    scope._span.set_attribute(SemanticConvention.GEN_AI_CLIENT_TOKEN_USAGE,
-        scope._input_tokens + scope._output_tokens + scope._reasoning_tokens)
+    scope._span.set_attribute(
+        SemanticConvention.GEN_AI_CLIENT_TOKEN_USAGE,
+        scope._input_tokens + scope._output_tokens + scope._reasoning_tokens,
+    )
 
     if scope._tools:
-        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_NAME, scope._tools.get('name',''))
-        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_CALL_ID, str(scope._tools.get('id','')))
-        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_ARGS, str(scope._tools.get('args','')))
+        scope._span.set_attribute(
+            SemanticConvention.GEN_AI_TOOL_NAME, scope._tools.get("name", "")
+        )
+        scope._span.set_attribute(
+            SemanticConvention.GEN_AI_TOOL_CALL_ID, str(scope._tools.get("id", ""))
+        )
+        scope._span.set_attribute(
+            SemanticConvention.GEN_AI_TOOL_ARGS, str(scope._tools.get("args", ""))
+        )
 
     # To be removed one the change to span_attributes (from span events) is complete
     if capture_message_content:
         scope._span.set_attribute(SemanticConvention.GEN_AI_CONTENT_PROMPT, prompt)
-        scope._span.set_attribute(SemanticConvention.GEN_AI_CONTENT_COMPLETION, scope._llmresponse)
+        scope._span.set_attribute(
+            SemanticConvention.GEN_AI_CONTENT_COMPLETION, scope._llmresponse
+        )
         scope._span.add_event(
             name=SemanticConvention.GEN_AI_CONTENT_PROMPT_EVENT,
             attributes={
@@ -190,57 +246,114 @@ def common_chat_logic(scope, pricing_info, environment, application_name, metric
             response_model=scope._response_model,
         )
 
-        metrics['genai_client_operation_duration'].record(scope._end_time - scope._start_time, metrics_attributes)
-        metrics['genai_server_tbt'].record(scope._tbt, metrics_attributes)
-        metrics['genai_server_ttft'].record(scope._ttft, metrics_attributes)
-        metrics['genai_requests'].add(1, metrics_attributes)
-        metrics['genai_completion_tokens'].add(scope._output_tokens, metrics_attributes)
-        metrics['genai_prompt_tokens'].add(scope._input_tokens, metrics_attributes)
-        metrics['genai_reasoning_tokens'].add(scope._reasoning_tokens, metrics_attributes)
-        metrics['genai_cost'].record(cost, metrics_attributes)
-        metrics['genai_client_usage_tokens'].record(
-            scope._input_tokens + scope._output_tokens + scope._reasoning_tokens, metrics_attributes)
+        metrics["genai_client_operation_duration"].record(
+            scope._end_time - scope._start_time, metrics_attributes
+        )
+        metrics["genai_server_tbt"].record(scope._tbt, metrics_attributes)
+        metrics["genai_server_ttft"].record(scope._ttft, metrics_attributes)
+        metrics["genai_requests"].add(1, metrics_attributes)
+        metrics["genai_completion_tokens"].add(scope._output_tokens, metrics_attributes)
+        metrics["genai_prompt_tokens"].add(scope._input_tokens, metrics_attributes)
+        metrics["genai_reasoning_tokens"].add(
+            scope._reasoning_tokens, metrics_attributes
+        )
+        metrics["genai_cost"].record(cost, metrics_attributes)
+        metrics["genai_client_usage_tokens"].record(
+            scope._input_tokens + scope._output_tokens + scope._reasoning_tokens,
+            metrics_attributes,
+        )
 
 
-def process_streaming_chat_response(self, pricing_info, environment, application_name, metrics,
-    capture_message_content=False, disable_metrics=False, version=''):
+def process_streaming_chat_response(
+    self,
+    pricing_info,
+    environment,
+    application_name,
+    metrics,
+    capture_message_content=False,
+    disable_metrics=False,
+    version="",
+):
     """
     Process chat request and generate Telemetry
     """
 
-    common_chat_logic(self, pricing_info, environment, application_name, metrics,
-        capture_message_content, disable_metrics, version, is_stream=True)
-
-def process_chat_response(instance, response, request_model, pricing_info, server_port, server_address,
-    environment, application_name, metrics, start_time,
-    span, args, kwargs, capture_message_content=False, disable_metrics=False, version="1.0.0"):
+    common_chat_logic(
+        self,
+        pricing_info,
+        environment,
+        application_name,
+        metrics,
+        capture_message_content,
+        disable_metrics,
+        version,
+        is_stream=True,
+    )
+
+
+def process_chat_response(
+    instance,
+    response,
+    request_model,
+    pricing_info,
+    server_port,
+    server_address,
+    environment,
+    application_name,
+    metrics,
+    start_time,
+    span,
+    args,
+    kwargs,
+    capture_message_content=False,
+    disable_metrics=False,
+    version="1.0.0",
+):
     """
     Process chat request and generate Telemetry
     """
 
-    self = type('GenericScope', (), {})()
+    self = type("GenericScope", (), {})()
     response_dict = response_as_dict(response)
 
     self._start_time = start_time
     self._end_time = time.time()
     self._span = span
     self._llmresponse = str(response.text)
-    self._input_tokens = response_dict.get('usage_metadata').get('prompt_token_count')
-    self._output_tokens = response_dict.get('usage_metadata').get('candidates_token_count')
-    self._reasoning_tokens = response_dict.get('usage_metadata').get('thoughts_token_count') or 0
-    self._response_model = response_dict.get('model_version')
+    self._input_tokens = response_dict.get("usage_metadata").get("prompt_token_count")
+    self._output_tokens = response_dict.get("usage_metadata").get(
+        "candidates_token_count"
+    )
+    self._reasoning_tokens = (
+        response_dict.get("usage_metadata").get("thoughts_token_count") or 0
+    )
+    self._response_model = response_dict.get("model_version")
     self._timestamps = []
     self._ttft, self._tbt = self._end_time - self._start_time, 0
     self._server_address, self._server_port = server_address, server_port
     self._kwargs = kwargs
-    self._finish_reason = str(response_dict.get('candidates')[0].get('finish_reason'))
+    self._finish_reason = str(response_dict.get("candidates")[0].get("finish_reason"))
 
     try:
-        self._tools = response_dict.get('candidates', [])[0].get('content', {}).get('parts', [])[0].get('function_call', '')
+        self._tools = (
+            response_dict.get("candidates", [])[0]
+            .get("content", {})
+            .get("parts", [])[0]
+            .get("function_call", "")
+        )
     except:
         self._tools = None
 
-    common_chat_logic(self, pricing_info, environment, application_name, metrics,
-        capture_message_content, disable_metrics, version, is_stream=False)
+    common_chat_logic(
+        self,
+        pricing_info,
+        environment,
+        application_name,
+        metrics,
+        capture_message_content,
+        disable_metrics,
+        version,
+        is_stream=False,
+    )
 
     return response

openlit/instrumentation/gpt4all/__init__.py

@@ -5,12 +5,11 @@ import importlib.metadata
 from opentelemetry.instrumentation.instrumentor import BaseInstrumentor
 from wrapt import wrap_function_wrapper
 
-from openlit.instrumentation.gpt4all.gpt4all import (
-    embed, generate
-)
+from openlit.instrumentation.gpt4all.gpt4all import embed, generate
 
 _instruments = ("gpt4all >= 2.6.0",)
 
+
 class GPT4AllInstrumentor(BaseInstrumentor):
     """
     An instrumentor for GPT4All client library.
@@ -33,16 +32,32 @@ class GPT4AllInstrumentor(BaseInstrumentor):
         wrap_function_wrapper(
             "gpt4all",
             "GPT4All.generate",
-            generate(version, environment, application_name,
-                  tracer, pricing_info, capture_message_content, metrics, disable_metrics),
+            generate(
+                version,
+                environment,
+                application_name,
+                tracer,
+                pricing_info,
+                capture_message_content,
+                metrics,
+                disable_metrics,
+            ),
         )
 
         # embed
         wrap_function_wrapper(
             "gpt4all",
             "Embed4All.embed",
-            embed(version, environment, application_name,
-                  tracer, pricing_info, capture_message_content, metrics, disable_metrics),
+            embed(
+                version,
+                environment,
+                application_name,
+                tracer,
+                pricing_info,
+                capture_message_content,
+                metrics,
+                disable_metrics,
+            ),
         )
 
     def _uninstrument(self, **kwargs):

openlit/instrumentation/gpt4all/gpt4all.py

@@ -4,20 +4,26 @@ Module for monitoring GPT4All API calls.
 
 import time
 from opentelemetry.trace import SpanKind
-from openlit.__helpers import (
-    handle_exception,
-    set_server_address_and_port
-)
+from openlit.__helpers import handle_exception, set_server_address_and_port
 from openlit.instrumentation.gpt4all.utils import (
     process_generate_response,
     process_chunk,
     process_streaming_generate_response,
-    process_embedding_response
+    process_embedding_response,
 )
 from openlit.semcov import SemanticConvention
 
-def generate(version, environment, application_name,
-    tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+
+def generate(
+    version,
+    environment,
+    application_name,
+    tracer,
+    pricing_info,
+    capture_message_content,
+    metrics,
+    disable_metrics,
+):
     """
     Generates a telemetry wrapper for GenAI function call
     """
@@ -28,16 +34,16 @@ def generate(version, environment, application_name,
         """
 
         def __init__(
-                self,
-                wrapped,
-                span,
-                span_name,
-                args,
-                kwargs,
-                server_address,
-                server_port,
-                request_model,
-            ):
+            self,
+            wrapped,
+            span,
+            span_name,
+            args,
+            kwargs,
+            server_address,
+            server_port,
+            request_model,
+        ):
             self.__wrapped__ = wrapped
             self._span = span
             self._span_name = span_name
@@ -75,7 +81,9 @@ def generate(version, environment, application_name,
                 return chunk
             except StopIteration:
                 try:
-                    with tracer.start_as_current_span(self._span_name, kind=SpanKind.CLIENT) as self._span:
+                    with tracer.start_as_current_span(
+                        self._span_name, kind=SpanKind.CLIENT
+                    ) as self._span:
                         process_streaming_generate_response(
                             self,
                             pricing_info=pricing_info,
@@ -84,7 +92,7 @@ def generate(version, environment, application_name,
                             metrics=metrics,
                             capture_message_content=capture_message_content,
                             disable_metrics=disable_metrics,
-                            version=version
+                            version=version,
                         )
 
                 except Exception as e:
@@ -100,8 +108,13 @@ def generate(version, environment, application_name,
         # Check if streaming is enabled for the API call
         streaming = kwargs.get("streaming", False)
 
-        server_address, server_port = set_server_address_and_port(instance, "127.0.0.1", 80)
-        request_model = str(instance.model.model_path).rsplit("/", maxsplit=1)[-1] or "orca-mini-3b-gguf2-q4_0.gguf"
+        server_address, server_port = set_server_address_and_port(
+            instance, "127.0.0.1", 80
+        )
+        request_model = (
+            str(instance.model.model_path).rsplit("/", maxsplit=1)[-1]
+            or "orca-mini-3b-gguf2-q4_0.gguf"
+        )
 
         span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
 
@@ -109,7 +122,16 @@ def generate(version, environment, application_name,
             # Special handling for streaming response to accommodate the nature of data flow
             awaited_wrapped = wrapped(*args, **kwargs)
             span = tracer.start_span(span_name, kind=SpanKind.CLIENT)
-            return TracedSyncStream(awaited_wrapped, span, span_name, args, kwargs, server_address, server_port, request_model)
+            return TracedSyncStream(
+                awaited_wrapped,
+                span,
+                span_name,
+                args,
+                kwargs,
+                server_address,
+                server_port,
+                request_model,
+            )
 
         # Handling for non-streaming responses
         else:
@@ -133,7 +155,7 @@ def generate(version, environment, application_name,
                         kwargs=kwargs,
                         capture_message_content=capture_message_content,
                         disable_metrics=disable_metrics,
-                        version=version
+                        version=version,
                     )
 
                 except Exception as e:
@@ -143,8 +165,17 @@ def generate(version, environment, application_name,
 
     return wrapper
 
-def embed(version, environment, application_name,
-    tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+
+def embed(
+    version,
+    environment,
+    application_name,
+    tracer,
+    pricing_info,
+    capture_message_content,
+    metrics,
+    disable_metrics,
+):
     """
     Generates a telemetry wrapper for GenAI function call
     """
@@ -154,10 +185,17 @@ def embed(version, environment, application_name,
         Wraps the GenAI function call.
         """
 
-        server_address, server_port = set_server_address_and_port(instance, "127.0.0.1", 80)
-        request_model = str(instance.gpt4all.model.model_path).rsplit("/", maxsplit=1)[-1] or "all-MiniLM-L6-v2.gguf2.f16.gguf"
+        server_address, server_port = set_server_address_and_port(
+            instance, "127.0.0.1", 80
+        )
+        request_model = (
+            str(instance.gpt4all.model.model_path).rsplit("/", maxsplit=1)[-1]
+            or "all-MiniLM-L6-v2.gguf2.f16.gguf"
+        )
 
-        span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING} {request_model}"
+        span_name = (
+            f"{SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING} {request_model}"
+        )
 
         with tracer.start_as_current_span(span_name, kind=SpanKind.CLIENT) as span:
             start_time = time.time()
@@ -178,7 +216,7 @@ def embed(version, environment, application_name,
                     capture_message_content=capture_message_content,
                     disable_metrics=disable_metrics,
                     version=version,
-                    **kwargs
+                    **kwargs,
                 )
 
             except Exception as e: