PyPI - openlit - Versions diffs - 1.33.9__py3-none-any.whl → 1.33.10__py3-none-any.whl - Mend

openlit 1.33.9py3-none-any.whl → 1.33.10py3-none-any.whl

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 (77) hide show

openlit/__helpers.py +5 -0
openlit/__init__.py +3 -2
openlit/instrumentation/ag2/ag2.py +3 -3
openlit/instrumentation/ai21/ai21.py +1 -1
openlit/instrumentation/ai21/async_ai21.py +1 -1
openlit/instrumentation/anthropic/anthropic.py +1 -1
openlit/instrumentation/anthropic/async_anthropic.py +1 -1
openlit/instrumentation/astra/astra.py +5 -5
openlit/instrumentation/astra/async_astra.py +5 -5
openlit/instrumentation/azure_ai_inference/async_azure_ai_inference.py +3 -3
openlit/instrumentation/azure_ai_inference/azure_ai_inference.py +3 -3
openlit/instrumentation/chroma/chroma.py +5 -5
openlit/instrumentation/cohere/async_cohere.py +1 -1
openlit/instrumentation/cohere/cohere.py +2 -2
openlit/instrumentation/controlflow/controlflow.py +3 -3
openlit/instrumentation/crawl4ai/async_crawl4ai.py +3 -3
openlit/instrumentation/crawl4ai/crawl4ai.py +3 -3
openlit/instrumentation/crewai/crewai.py +4 -2
openlit/instrumentation/dynamiq/dynamiq.py +3 -3
openlit/instrumentation/elevenlabs/async_elevenlabs.py +1 -2
openlit/instrumentation/elevenlabs/elevenlabs.py +1 -2
openlit/instrumentation/embedchain/embedchain.py +5 -5
openlit/instrumentation/firecrawl/firecrawl.py +3 -3
openlit/instrumentation/gpt4all/__init__.py +2 -2
openlit/instrumentation/gpt4all/gpt4all.py +345 -220
openlit/instrumentation/gpu/__init__.py +5 -5
openlit/instrumentation/groq/__init__.py +2 -2
openlit/instrumentation/groq/async_groq.py +356 -240
openlit/instrumentation/groq/groq.py +356 -240
openlit/instrumentation/haystack/haystack.py +3 -3
openlit/instrumentation/julep/async_julep.py +3 -3
openlit/instrumentation/julep/julep.py +3 -3
openlit/instrumentation/langchain/__init__.py +13 -7
openlit/instrumentation/langchain/async_langchain.py +384 -0
openlit/instrumentation/langchain/langchain.py +98 -490
openlit/instrumentation/letta/letta.py +5 -3
openlit/instrumentation/litellm/__init__.py +4 -5
openlit/instrumentation/litellm/async_litellm.py +316 -245
openlit/instrumentation/litellm/litellm.py +312 -241
openlit/instrumentation/llamaindex/llamaindex.py +3 -3
openlit/instrumentation/mem0/mem0.py +3 -3
openlit/instrumentation/milvus/milvus.py +5 -5
openlit/instrumentation/mistral/__init__.py +6 -6
openlit/instrumentation/mistral/async_mistral.py +421 -248
openlit/instrumentation/mistral/mistral.py +418 -244
openlit/instrumentation/multion/async_multion.py +4 -2
openlit/instrumentation/multion/multion.py +4 -2
openlit/instrumentation/ollama/__init__.py +8 -30
openlit/instrumentation/ollama/async_ollama.py +385 -417
openlit/instrumentation/ollama/ollama.py +384 -417
openlit/instrumentation/openai/async_openai.py +7 -9
openlit/instrumentation/openai/openai.py +7 -9
openlit/instrumentation/phidata/phidata.py +4 -2
openlit/instrumentation/pinecone/pinecone.py +5 -5
openlit/instrumentation/premai/__init__.py +2 -2
openlit/instrumentation/premai/premai.py +262 -213
openlit/instrumentation/qdrant/async_qdrant.py +5 -5
openlit/instrumentation/qdrant/qdrant.py +5 -5
openlit/instrumentation/reka/__init__.py +2 -2
openlit/instrumentation/reka/async_reka.py +90 -52
openlit/instrumentation/reka/reka.py +90 -52
openlit/instrumentation/together/__init__.py +4 -4
openlit/instrumentation/together/async_together.py +278 -236
openlit/instrumentation/together/together.py +278 -236
openlit/instrumentation/transformers/__init__.py +1 -1
openlit/instrumentation/transformers/transformers.py +75 -44
openlit/instrumentation/vertexai/__init__.py +14 -64
openlit/instrumentation/vertexai/async_vertexai.py +329 -986
openlit/instrumentation/vertexai/vertexai.py +329 -986
openlit/instrumentation/vllm/__init__.py +1 -1
openlit/instrumentation/vllm/vllm.py +62 -32
openlit/semcov/__init__.py +3 -3
{openlit-1.33.9.dist-info → openlit-1.33.10.dist-info}/METADATA +1 -1
openlit-1.33.10.dist-info/RECORD +122 -0
openlit-1.33.9.dist-info/RECORD +0 -121
{openlit-1.33.9.dist-info → openlit-1.33.10.dist-info}/LICENSE +0 -0
{openlit-1.33.9.dist-info → openlit-1.33.10.dist-info}/WHEEL +0 -0

openlit/instrumentation/qdrant/async_qdrant.py CHANGED Viewed

@@ -5,7 +5,7 @@ Module for monitoring Qdrant.
 import logging
 from opentelemetry.trace import SpanKind, Status, StatusCode
-from opentelemetry.sdk.resources import TELEMETRY_SDK_NAME
+from opentelemetry.sdk.resources import SERVICE_NAME, TELEMETRY_SDK_NAME, DEPLOYMENT_ENVIRONMENT
 from openlit.__helpers import handle_exception
 from openlit.semcov import SemanticConvetion
@@ -73,9 +73,9 @@ def async_general_wrap(gen_ai_endpoint, version, environment, application_name,
                 span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
                 span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
                                    gen_ai_endpoint)
-                span.set_attribute(SemanticConvetion.GEN_AI_ENVIRONMENT,
+                span.set_attribute(DEPLOYMENT_ENVIRONMENT,
                                    environment)
-                span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
+                span.set_attribute(SERVICE_NAME,
                                    application_name)
                 span.set_attribute(SemanticConvetion.GEN_AI_OPERATION,
                                    SemanticConvetion.GEN_AI_OPERATION_TYPE_VECTORDB)
@@ -241,11 +241,11 @@ def async_general_wrap(gen_ai_endpoint, version, environment, application_name,
                     attributes = {
                         TELEMETRY_SDK_NAME:
                             "openlit",
-                        SemanticConvetion.GEN_AI_APPLICATION_NAME:
+                        SERVICE_NAME:
                             application_name,
                         SemanticConvetion.DB_SYSTEM:
                             SemanticConvetion.DB_SYSTEM_QDRANT,
-                        SemanticConvetion.GEN_AI_ENVIRONMENT:
+                        DEPLOYMENT_ENVIRONMENT:
                             environment,
                         SemanticConvetion.GEN_AI_OPERATION:
                             SemanticConvetion.GEN_AI_OPERATION_TYPE_VECTORDB,

openlit/instrumentation/qdrant/qdrant.py CHANGED Viewed

@@ -5,7 +5,7 @@ Module for monitoring Qdrant.
 import logging
 from opentelemetry.trace import SpanKind, Status, StatusCode
-from opentelemetry.sdk.resources import TELEMETRY_SDK_NAME
+from opentelemetry.sdk.resources import SERVICE_NAME, TELEMETRY_SDK_NAME, DEPLOYMENT_ENVIRONMENT
 from openlit.__helpers import handle_exception
 from openlit.semcov import SemanticConvetion
@@ -73,9 +73,9 @@ def general_wrap(gen_ai_endpoint, version, environment, application_name,
                 span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
                 span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
                                    gen_ai_endpoint)
-                span.set_attribute(SemanticConvetion.GEN_AI_ENVIRONMENT,
+                span.set_attribute(DEPLOYMENT_ENVIRONMENT,
                                    environment)
-                span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
+                span.set_attribute(SERVICE_NAME,
                                    application_name)
                 span.set_attribute(SemanticConvetion.GEN_AI_OPERATION,
                                    SemanticConvetion.GEN_AI_OPERATION_TYPE_VECTORDB)
@@ -248,11 +248,11 @@ def general_wrap(gen_ai_endpoint, version, environment, application_name,
                     attributes = {
                         TELEMETRY_SDK_NAME:
                             "openlit",
-                        SemanticConvetion.GEN_AI_APPLICATION_NAME:
+                        SERVICE_NAME:
                             application_name,
                         SemanticConvetion.DB_SYSTEM:
                             SemanticConvetion.DB_SYSTEM_QDRANT,
-                        SemanticConvetion.GEN_AI_ENVIRONMENT:
+                        DEPLOYMENT_ENVIRONMENT:
                             environment,
                         SemanticConvetion.GEN_AI_OPERATION:
                             SemanticConvetion.GEN_AI_OPERATION_TYPE_VECTORDB,

openlit/instrumentation/reka/__init__.py CHANGED Viewed

@@ -37,7 +37,7 @@ class RekaInstrumentor(BaseInstrumentor):
         wrap_function_wrapper(
             "reka.chat.client",
             "ChatClient.create",
-            chat("reka.chat", version, environment, application_name,
+            chat(version, environment, application_name,
                   tracer, pricing_info, trace_content, metrics, disable_metrics),
         )
@@ -45,7 +45,7 @@ class RekaInstrumentor(BaseInstrumentor):
         wrap_function_wrapper(
             "reka.chat.client",
             "AsyncChatClient.create",
-            async_chat("reka.chat", version, environment, application_name,
+            async_chat(version, environment, application_name,
                   tracer, pricing_info, trace_content, metrics, disable_metrics),
         )

openlit/instrumentation/reka/async_reka.py CHANGED Viewed

@@ -1,27 +1,28 @@
-# pylint: disable=duplicate-code, broad-exception-caught, too-many-statements, unused-argument, possibly-used-before-assignment
 """
 Module for monitoring Reka API calls.
 """
 import logging
+import time
 from opentelemetry.trace import SpanKind, Status, StatusCode
-from opentelemetry.sdk.resources import TELEMETRY_SDK_NAME
+from opentelemetry.sdk.resources import SERVICE_NAME, TELEMETRY_SDK_NAME, DEPLOYMENT_ENVIRONMENT
 from openlit.__helpers import (
-    handle_exception,
     get_chat_model_cost,
+    handle_exception,
+    create_metrics_attributes,
+    set_server_address_and_port
 )
 from openlit.semcov import SemanticConvetion
 # Initialize logger for logging potential issues and operations
 logger = logging.getLogger(__name__)
-def async_chat(gen_ai_endpoint, version, environment, application_name,
+def async_chat(version, environment, application_name,
                      tracer, pricing_info, trace_content, metrics, disable_metrics):
     """
     Generates a telemetry wrapper for chat to collect metrics.
     Args:
-        gen_ai_endpoint: Endpoint identifier for logging and tracing.
         version: Version of the monitoring package.
         environment: Deployment environment (e.g., production, staging).
         application_name: Name of the application using the Reka API.
@@ -50,8 +51,15 @@ def async_chat(gen_ai_endpoint, version, environment, application_name,
             The response from the original 'chat' method.
         """
-        with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
+        server_address, server_port = set_server_address_and_port(instance, "api.reka.ai", 443)
+        request_model = kwargs.get("model", "reka-core-20240501")
+        span_name = f"{SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
+        with tracer.start_as_current_span(span_name, kind= SpanKind.CLIENT) as span:
+            start_time = time.time()
             response = await wrapped(*args, **kwargs)
+            end_time = time.time()
             try:
                 # Format 'messages' into a single string
@@ -63,7 +71,6 @@ def async_chat(gen_ai_endpoint, version, environment, application_name,
                     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
@@ -73,22 +80,68 @@ def async_chat(gen_ai_endpoint, version, environment, application_name,
                         formatted_messages.append(f"{role}: {content}")
                 prompt = "\n".join(formatted_messages)
-                # Set base span attribues
+                input_tokens = response.usage.input_tokens
+                output_tokens = response.usage.output_tokens
+                # Calculate cost of the operation
+                cost = get_chat_model_cost(request_model,
+                                            pricing_info, input_tokens, output_tokens)
+                # Set Span attributes (OTel Semconv)
                 span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
-                span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
-                                    SemanticConvetion.GEN_AI_SYSTEM_REKAAI)
                 span.set_attribute(SemanticConvetion.GEN_AI_OPERATION,
                                     SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT)
-                span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
-                                    gen_ai_endpoint)
-                span.set_attribute(SemanticConvetion.GEN_AI_ENVIRONMENT,
+                span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
+                                    SemanticConvetion.GEN_AI_SYSTEM_REKAAI)
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
+                                    request_model)
+                span.set_attribute(SemanticConvetion.SERVER_PORT,
+                                    server_port)
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
+                                    kwargs.get("seed", ""))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
+                                    kwargs.get("max_tokens", -1))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_STOP_SEQUENCES,
+                                    kwargs.get("stop", []))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
+                                    kwargs.get("presence_penalty", 0.0))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
+                                    kwargs.get("temperature", 0.4))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_K,
+                                    kwargs.get("top_k", 1.0))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
+                                    kwargs.get("top_p", 1.0))
+                span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
+                                    [response.responses[0].finish_reason])
+                span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_ID,
+                                    response.id)
+                span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_MODEL,
+                                    response.model)
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_INPUT_TOKENS,
+                                    input_tokens)
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_OUTPUT_TOKENS,
+                                    output_tokens)
+                span.set_attribute(SemanticConvetion.SERVER_ADDRESS,
+                                    server_address)
+                span.set_attribute(SemanticConvetion.GEN_AI_OUTPUT_TYPE,
+                                    'text')
+                # Set Span attributes (Extra)
+                span.set_attribute(DEPLOYMENT_ENVIRONMENT,
                                     environment)
-                span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
+                span.set_attribute(SERVICE_NAME,
                                     application_name)
-                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
-                                    kwargs.get("model", "reka-core"))
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
                                     False)
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                    input_tokens + output_tokens)
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
+                                    cost)
+                span.set_attribute(SemanticConvetion.GEN_AI_SERVER_TTFT,
+                                    end_time - start_time)
+                span.set_attribute(SemanticConvetion.GEN_AI_SDK_VERSION,
+                                    version)
                 if trace_content:
                     span.add_event(
                         name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
@@ -99,51 +152,36 @@ def async_chat(gen_ai_endpoint, version, environment, application_name,
                     span.add_event(
                         name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
                         attributes={
-                            # pylint: disable=line-too-long
                             SemanticConvetion.GEN_AI_CONTENT_COMPLETION: response.responses[0].message.content,
                         },
                     )
-                prompt_tokens = response.usage.input_tokens
-                completion_tokens = response.usage.output_tokens
-                total_tokens = prompt_tokens + completion_tokens
-                # Calculate cost of the operation
-                cost = get_chat_model_cost(kwargs.get("model", "reka-core"),
-                                            pricing_info, prompt_tokens, completion_tokens)
-                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_INPUT_TOKENS,
-                                    prompt_tokens)
-                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_OUTPUT_TOKENS,
-                                    completion_tokens)
-                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                                    total_tokens)
-                span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
-                                    [response.responses[0].finish_reason])
-                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
-                                    cost)
                 span.set_status(Status(StatusCode.OK))
                 if disable_metrics is False:
-                    attributes = {
-                        TELEMETRY_SDK_NAME:
-                            "openlit",
-                        SemanticConvetion.GEN_AI_APPLICATION_NAME:
-                            application_name,
-                        SemanticConvetion.GEN_AI_SYSTEM:
-                            SemanticConvetion.GEN_AI_SYSTEM_REKAAI,
-                        SemanticConvetion.GEN_AI_ENVIRONMENT:
-                            environment,
-                        SemanticConvetion.GEN_AI_OPERATION:
-                            SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT,
-                        SemanticConvetion.GEN_AI_REQUEST_MODEL:
-                            kwargs.get("model", "reka-core")
-                    }
+                    attributes = create_metrics_attributes(
+                        service_name=application_name,
+                        deployment_environment=environment,
+                        operation=SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT,
+                        system=SemanticConvetion.GEN_AI_SYSTEM_REKAAI,
+                        request_model=request_model,
+                        server_address=server_address,
+                        server_port=server_port,
+                        response_model=response.model,
+                    )
+                    metrics["genai_client_usage_tokens"].record(
+                        input_tokens + output_tokens, attributes
+                    )
+                    metrics["genai_client_operation_duration"].record(
+                        end_time - start_time, attributes
+                    )
+                    metrics["genai_server_ttft"].record(
+                        end_time - start_time, attributes
+                    )
                     metrics["genai_requests"].add(1, attributes)
-                    metrics["genai_total_tokens"].add(total_tokens, attributes)
-                    metrics["genai_completion_tokens"].add(completion_tokens, attributes)
-                    metrics["genai_prompt_tokens"].add(prompt_tokens, attributes)
+                    metrics["genai_completion_tokens"].add(output_tokens, attributes)
+                    metrics["genai_prompt_tokens"].add(input_tokens, attributes)
                     metrics["genai_cost"].record(cost, attributes)
                 # Return original response

openlit/instrumentation/reka/reka.py CHANGED Viewed

@@ -1,27 +1,28 @@
-# pylint: disable=duplicate-code, broad-exception-caught, too-many-statements, unused-argument, possibly-used-before-assignment
 """
 Module for monitoring Reka API calls.
 """
 import logging
+import time
 from opentelemetry.trace import SpanKind, Status, StatusCode
-from opentelemetry.sdk.resources import TELEMETRY_SDK_NAME
+from opentelemetry.sdk.resources import SERVICE_NAME, TELEMETRY_SDK_NAME, DEPLOYMENT_ENVIRONMENT
 from openlit.__helpers import (
-    handle_exception,
     get_chat_model_cost,
+    handle_exception,
+    create_metrics_attributes,
+    set_server_address_and_port
 )
 from openlit.semcov import SemanticConvetion
 # Initialize logger for logging potential issues and operations
 logger = logging.getLogger(__name__)
-def chat(gen_ai_endpoint, version, environment, application_name,
+def chat(version, environment, application_name,
                      tracer, pricing_info, trace_content, metrics, disable_metrics):
     """
     Generates a telemetry wrapper for chat to collect metrics.
     Args:
-        gen_ai_endpoint: Endpoint identifier for logging and tracing.
         version: Version of the monitoring package.
         environment: Deployment environment (e.g., production, staging).
         application_name: Name of the application using the Reka API.
@@ -50,8 +51,15 @@ def chat(gen_ai_endpoint, version, environment, application_name,
             The response from the original 'chat' method.
         """
-        with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
+        server_address, server_port = set_server_address_and_port(instance, "api.reka.ai", 443)
+        request_model = kwargs.get("model", "reka-core-20240501")
+        span_name = f"{SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
+        with tracer.start_as_current_span(span_name, kind= SpanKind.CLIENT) as span:
+            start_time = time.time()
             response = wrapped(*args, **kwargs)
+            end_time = time.time()
             try:
                 # Format 'messages' into a single string
@@ -63,7 +71,6 @@ def chat(gen_ai_endpoint, version, environment, application_name,
                     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
@@ -73,22 +80,68 @@ def chat(gen_ai_endpoint, version, environment, application_name,
                         formatted_messages.append(f"{role}: {content}")
                 prompt = "\n".join(formatted_messages)
-                # Set base span attribues
+                input_tokens = response.usage.input_tokens
+                output_tokens = response.usage.output_tokens
+                # Calculate cost of the operation
+                cost = get_chat_model_cost(request_model,
+                                            pricing_info, input_tokens, output_tokens)
+                # Set Span attributes (OTel Semconv)
                 span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
-                span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
-                                    SemanticConvetion.GEN_AI_SYSTEM_REKAAI)
                 span.set_attribute(SemanticConvetion.GEN_AI_OPERATION,
                                     SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT)
-                span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
-                                    gen_ai_endpoint)
-                span.set_attribute(SemanticConvetion.GEN_AI_ENVIRONMENT,
+                span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
+                                    SemanticConvetion.GEN_AI_SYSTEM_REKAAI)
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
+                                    request_model)
+                span.set_attribute(SemanticConvetion.SERVER_PORT,
+                                    server_port)
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
+                                    kwargs.get("seed", ""))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
+                                    kwargs.get("max_tokens", -1))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_STOP_SEQUENCES,
+                                    kwargs.get("stop", []))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
+                                    kwargs.get("presence_penalty", 0.0))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
+                                    kwargs.get("temperature", 0.4))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_K,
+                                    kwargs.get("top_k", 1.0))
+                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
+                                    kwargs.get("top_p", 1.0))
+                span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
+                                    [response.responses[0].finish_reason])
+                span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_ID,
+                                    response.id)
+                span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_MODEL,
+                                    response.model)
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_INPUT_TOKENS,
+                                    input_tokens)
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_OUTPUT_TOKENS,
+                                    output_tokens)
+                span.set_attribute(SemanticConvetion.SERVER_ADDRESS,
+                                    server_address)
+                span.set_attribute(SemanticConvetion.GEN_AI_OUTPUT_TYPE,
+                                    'text')
+                # Set Span attributes (Extra)
+                span.set_attribute(DEPLOYMENT_ENVIRONMENT,
                                     environment)
-                span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
+                span.set_attribute(SERVICE_NAME,
                                     application_name)
-                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
-                                    kwargs.get("model", "reka-core"))
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
                                     False)
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                    input_tokens + output_tokens)
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
+                                    cost)
+                span.set_attribute(SemanticConvetion.GEN_AI_SERVER_TTFT,
+                                    end_time - start_time)
+                span.set_attribute(SemanticConvetion.GEN_AI_SDK_VERSION,
+                                    version)
                 if trace_content:
                     span.add_event(
                         name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
@@ -99,51 +152,36 @@ def chat(gen_ai_endpoint, version, environment, application_name,
                     span.add_event(
                         name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
                         attributes={
-                            # pylint: disable=line-too-long
                             SemanticConvetion.GEN_AI_CONTENT_COMPLETION: response.responses[0].message.content,
                         },
                     )
-                prompt_tokens = response.usage.input_tokens
-                completion_tokens = response.usage.output_tokens
-                total_tokens = prompt_tokens + completion_tokens
-                # Calculate cost of the operation
-                cost = get_chat_model_cost(kwargs.get("model", "reka-core"),
-                                            pricing_info, prompt_tokens, completion_tokens)
-                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_INPUT_TOKENS,
-                                    prompt_tokens)
-                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_OUTPUT_TOKENS,
-                                    completion_tokens)
-                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                                    total_tokens)
-                span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
-                                    [response.responses[0].finish_reason])
-                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
-                                    cost)
                 span.set_status(Status(StatusCode.OK))
                 if disable_metrics is False:
-                    attributes = {
-                        TELEMETRY_SDK_NAME:
-                            "openlit",
-                        SemanticConvetion.GEN_AI_APPLICATION_NAME:
-                            application_name,
-                        SemanticConvetion.GEN_AI_SYSTEM:
-                            SemanticConvetion.GEN_AI_SYSTEM_REKAAI,
-                        SemanticConvetion.GEN_AI_ENVIRONMENT:
-                            environment,
-                        SemanticConvetion.GEN_AI_OPERATION:
-                            SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT,
-                        SemanticConvetion.GEN_AI_REQUEST_MODEL:
-                            kwargs.get("model", "reka-core")
-                    }
+                    attributes = create_metrics_attributes(
+                        service_name=application_name,
+                        deployment_environment=environment,
+                        operation=SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT,
+                        system=SemanticConvetion.GEN_AI_SYSTEM_REKAAI,
+                        request_model=request_model,
+                        server_address=server_address,
+                        server_port=server_port,
+                        response_model=response.model,
+                    )
+                    metrics["genai_client_usage_tokens"].record(
+                        input_tokens + output_tokens, attributes
+                    )
+                    metrics["genai_client_operation_duration"].record(
+                        end_time - start_time, attributes
+                    )
+                    metrics["genai_server_ttft"].record(
+                        end_time - start_time, attributes
+                    )
                     metrics["genai_requests"].add(1, attributes)
-                    metrics["genai_total_tokens"].add(total_tokens, attributes)
-                    metrics["genai_completion_tokens"].add(completion_tokens, attributes)
-                    metrics["genai_prompt_tokens"].add(prompt_tokens, attributes)
+                    metrics["genai_completion_tokens"].add(output_tokens, attributes)
+                    metrics["genai_prompt_tokens"].add(input_tokens, attributes)
                     metrics["genai_cost"].record(cost, attributes)
                 # Return original response

openlit/instrumentation/together/__init__.py CHANGED Viewed

@@ -37,7 +37,7 @@ class TogetherInstrumentor(BaseInstrumentor):
         wrap_function_wrapper(
             "together.resources.chat.completions",
             "ChatCompletions.create",
-            completion("together.chat.completions", version, environment, application_name,
+            completion(version, environment, application_name,
                   tracer, pricing_info, trace_content, metrics, disable_metrics),
         )
@@ -45,7 +45,7 @@ class TogetherInstrumentor(BaseInstrumentor):
         wrap_function_wrapper(
             "together.resources.images",
             "Images.generate",
-            image_generate("together.image.generate", version, environment, application_name,
+            image_generate(version, environment, application_name,
                   tracer, pricing_info, trace_content, metrics, disable_metrics),
         )
@@ -53,7 +53,7 @@ class TogetherInstrumentor(BaseInstrumentor):
         wrap_function_wrapper(
             "together.resources.chat.completions",
             "AsyncChatCompletions.create",
-            async_completion("together.chat.completions", version, environment, application_name,
+            async_completion(version, environment, application_name,
                   tracer, pricing_info, trace_content, metrics, disable_metrics),
         )
@@ -61,7 +61,7 @@ class TogetherInstrumentor(BaseInstrumentor):
         wrap_function_wrapper(
             "together.resources.images",
             "AsyncImages.generate",
-            async_image_generate("together.image.generate", version, environment, application_name,
+            async_image_generate(version, environment, application_name,
                   tracer, pricing_info, trace_content, metrics, disable_metrics),
         )

openlit 1.33.9__py3-none-any.whl → 1.33.10__py3-none-any.whl

openlit 1.33.9py3-none-any.whl → 1.33.10py3-none-any.whl