openlit 1.33.8__py3-none-any.whl → 1.33.10__py3-none-any.whl

openlit/instrumentation/vllm/__init__.py

@@ -34,7 +34,7 @@ class VLLMInstrumentor(BaseInstrumentor):
         wrap_function_wrapper(
             "vllm",
             "LLM.generate",
-            generate("vllm.generate", version, environment, application_name,
+            generate(version, environment, application_name,
                   tracer, pricing_info, trace_content, metrics, disable_metrics),
         )
 

openlit/instrumentation/vllm/vllm.py

@@ -1,24 +1,29 @@
-# pylint: disable=duplicate-code, broad-exception-caught, too-many-statements, unused-argument, possibly-used-before-assignment
 """
 Module for monitoring vLLM API calls.
 """
 
 import logging
+import time
 from opentelemetry.trace import SpanKind, Status, StatusCode
-from opentelemetry.sdk.resources import TELEMETRY_SDK_NAME
-from openlit.__helpers import handle_exception, general_tokens
+from opentelemetry.sdk.resources import SERVICE_NAME, TELEMETRY_SDK_NAME, DEPLOYMENT_ENVIRONMENT
+from openlit.__helpers import (
+    get_chat_model_cost,
+    handle_exception,
+    general_tokens,
+    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 generate(gen_ai_endpoint, version, environment, application_name,
+def generate(version, environment, application_name,
                      tracer, pricing_info, trace_content, metrics, disable_metrics):
     """
     Generates a telemetry wrapper for generate 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 vLLM API.
@@ -47,28 +52,47 @@ def generate(gen_ai_endpoint, version, environment, application_name,
             The response from the original 'generate' method.
         """
 
+        server_address, server_port = set_server_address_and_port(instance, "api.cohere.com", 443)
+        request_model = instance.llm_engine.model_config.model or "facebook/opt-125m"
+
+        span_name = f"{SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
+
         # pylint: disable=line-too-long
-        with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
+        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:
-                model = instance.llm_engine.model_config.model or "facebook/opt-125m"
                 # Set base span attribues
                 span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
                 span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
                                     SemanticConvetion.GEN_AI_SYSTEM_VLLM)
-                span.set_attribute(SemanticConvetion.GEN_AI_TYPE,
-                                    SemanticConvetion.GEN_AI_TYPE_CHAT)
-                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_OPERATION,
+                                    SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT)
+                span.set_attribute(SemanticConvetion.SERVER_PORT,
+                                    server_port)
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
-                                    model)
+                                    request_model)
+                span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_MODEL,
+                                    request_model)
+                span.set_attribute(SemanticConvetion.SERVER_ADDRESS,
+                                    server_address)
+                span.set_attribute(SemanticConvetion.GEN_AI_OUTPUT_TYPE,
+                                    "text")
+
+                # Set base span attribues (Extras)
+                span.set_attribute(DEPLOYMENT_ENVIRONMENT,
+                                     environment)
+                span.set_attribute(SERVICE_NAME,
+                                    application_name)
                 span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
                                     False)
+                span.set_attribute(SemanticConvetion.GEN_AI_SERVER_TTFT,
+                                    end_time - start_time)
+                span.set_attribute(SemanticConvetion.GEN_AI_SDK_VERSION,
+                                    version)
+
                 input_tokens = 0
                 output_tokens = 0
                 cost = 0
@@ -95,37 +119,43 @@ def generate(gen_ai_endpoint, version, environment, application_name,
                         attributes=completion_attributes,
                     )
 
-                total_tokens = input_tokens + output_tokens
-
-                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_INPUT_TOKENS,
                                     input_tokens)
-                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_OUTPUT_TOKENS,
                                     output_tokens)
                 span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                                    total_tokens)
+                                    input_tokens + output_tokens)
+
+                # Calculate cost of the operation
+                cost = get_chat_model_cost(request_model, pricing_info,
+                                            input_tokens, output_tokens)
                 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_VLLM,
-                        SemanticConvetion.GEN_AI_ENVIRONMENT:
-                            environment,
-                        SemanticConvetion.GEN_AI_TYPE:
-                            SemanticConvetion.GEN_AI_TYPE_CHAT,
-                        SemanticConvetion.GEN_AI_REQUEST_MODEL:
-                            model
-                    }
+                    attributes = create_metrics_attributes(
+                        service_name=application_name,
+                        deployment_environment=environment,
+                        operation=SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT,
+                        system=SemanticConvetion.GEN_AI_SYSTEM_VLLM,
+                        request_model=request_model,
+                        server_address=server_address,
+                        server_port=server_port,
+                        response_model=request_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(output_tokens, attributes)
                     metrics["genai_prompt_tokens"].add(input_tokens, attributes)
                     metrics["genai_cost"].record(cost, attributes)

openlit/otel/metrics.py

@@ -18,6 +18,75 @@ else:
 # Global flag to check if the meter provider initialization is complete.
 METER_SET = False
 
+_GEN_AI_CLIENT_OPERATION_DURATION_BUCKETS = [
+    0.01,
+    0.02,
+    0.04,
+    0.08,
+    0.16,
+    0.32,
+    0.64,
+    1.28,
+    2.56,
+    5.12,
+    10.24,
+    20.48,
+    40.96,
+    81.92,
+]
+
+_GEN_AI_SERVER_TBT = [
+    0.01,
+    0.025,
+    0.05,
+    0.075,
+    0.1,
+    0.15,
+    0.2,
+    0.3,
+    0.4,
+    0.5,
+    0.75,
+    1.0,
+    2.5
+]
+
+_GEN_AI_SERVER_TFTT = [
+    0.001,
+    0.005,
+    0.01,
+    0.02,
+    0.04,
+    0.06,
+    0.08,
+    0.1,
+    0.25,
+    0.5,
+    0.75,
+    1.0,
+    2.5,
+    5.0,
+    7.5,
+    10.0
+]
+
+_GEN_AI_CLIENT_TOKEN_USAGE_BUCKETS = [
+    1,
+    4,
+    16,
+    64,
+    256,
+    1024,
+    4096,
+    16384,
+    65536,
+    262144,
+    1048576,
+    4194304,
+    16777216,
+    67108864,
+]
+
 def setup_meter(application_name, environment, meter, otlp_endpoint, otlp_headers):
     """
     Sets up OpenTelemetry metrics with a counter for total requests.
@@ -73,26 +142,48 @@ def setup_meter(application_name, environment, meter, otlp_endpoint, otlp_header
 
         # Define and create the metrics
         metrics_dict = {
+            # OTel Semconv
+            "genai_client_usage_tokens": meter.create_histogram(
+                name=SemanticConvetion.GEN_AI_CLIENT_TOKEN_USAGE,
+                description="Measures number of input and output tokens used",
+                unit="{token}",
+                explicit_bucket_boundaries_advisory=_GEN_AI_CLIENT_TOKEN_USAGE_BUCKETS,
+            ),
+            "genai_client_operation_duration": meter.create_histogram(
+                name=SemanticConvetion.GEN_AI_CLIENT_OPERATION_DURATION,
+                description="GenAI operation duration",
+                unit="s",
+                explicit_bucket_boundaries_advisory=_GEN_AI_CLIENT_OPERATION_DURATION_BUCKETS,
+            ),
+            "genai_server_tbt": meter.create_histogram(
+                name=SemanticConvetion.GEN_AI_SERVER_TBT,
+                description="Time per output token generated after the first token for successful responses",
+                unit="s",
+                explicit_bucket_boundaries_advisory=_GEN_AI_SERVER_TBT,
+            ),
+            "genai_server_ttft": meter.create_histogram(
+                name=SemanticConvetion.GEN_AI_SERVER_TTFT,
+                description="Time to generate first token for successful responses",
+                unit="s",
+                explicit_bucket_boundaries_advisory=_GEN_AI_SERVER_TFTT,
+            ),
+
+            # Extra
             "genai_requests": meter.create_counter(
                 name=SemanticConvetion.GEN_AI_REQUESTS,
                 description="Number of requests to GenAI",
                 unit="1",
             ),
             "genai_prompt_tokens": meter.create_counter(
-                name=SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                name=SemanticConvetion.GEN_AI_USAGE_INPUT_TOKENS,
                 description="Number of prompt tokens processed.",
                 unit="1",
             ),
             "genai_completion_tokens": meter.create_counter(
-                name=SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                name=SemanticConvetion.GEN_AI_USAGE_OUTPUT_TOKENS,
                 description="Number of completion tokens processed.",
                 unit="1",
             ),
-            "genai_total_tokens": meter.create_counter(
-                name=SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                description="Number of total tokens processed.",
-                unit="1",
-            ),
             "genai_cost": meter.create_histogram(
                 name=SemanticConvetion.GEN_AI_USAGE_COST,
                 description="The distribution of GenAI request costs.",

openlit/semcov/__init__.py

@@ -16,30 +16,114 @@ class SemanticConvetion:
     the application's data logging and processing functionalities.
     """
 
-    # GenAI General
-    GEN_AI_ENDPOINT = "gen_ai.endpoint"
-    GEN_AI_SYSTEM = "gen_ai.system"
-    GEN_AI_ENVIRONMENT = "gen_ai.environment"
-    GEN_AI_APPLICATION_NAME = "gen_ai.application_name"
-    GEN_AI_TYPE = "gen_ai.operation.name"
-    GEN_AI_HUB_OWNER = "gen_ai.hub.owner"
-    GEN_AI_HUB_REPO = "gen_ai.hub.repo"
-    GEN_AI_RETRIEVAL_SOURCE = "gen_ai.retrieval.source"
-    GEN_AI_REQUESTS = "gen_ai.total.requests"
-    GEN_AI_DATA_SOURCES = "gen_ai.data_source_count"
+    # General Attributes (OTel Semconv)
+    SERVER_PORT = "server.port"
+    SERVER_ADDRESS = "server.address"
+    ERROR_TYPE = "error.type"
 
-    # GenAI Request
+    # GenAI Metric Names (OTel Semconv)
+    GEN_AI_CLIENT_TOKEN_USAGE = "gen_ai.client.token.usage"
+    GEN_AI_CLIENT_OPERATION_DURATION = "gen_ai.client.operation.duration"
+    GEN_AI_SERVER_REQUEST_DURATION = "gen_ai.server.request.duration"
+    GEN_AI_SERVER_TBT = "gen_ai.server.time_per_output_token"
+    GEN_AI_SERVER_TTFT = "gen_ai.server.time_to_first_token"
+
+    # GenAI Request Attributes (OTel Semconv)
+    GEN_AI_OPERATION = "gen_ai.operation.name"
+    GEN_AI_SYSTEM = "gen_ai.system"
+    GEN_AI_OUTPUT_TYPE = "gen_ai.output.type"
+    GEN_AI_ENDPOINT = "gen_ai.endpoint"
     GEN_AI_REQUEST_MODEL = "gen_ai.request.model"
+    GEN_AI_REQUEST_SEED = "gen_ai.request.seed"
+    GEN_AI_REQUEST_ENCODING_FORMATS = "gen_ai.request.encoding_formats"
+    GEN_AI_REQUEST_FREQUENCY_PENALTY = "gen_ai.request.frequency_penalty"
+    GEN_AI_REQUEST_MAX_TOKENS = "gen_ai.request.max_tokens"
+    GEN_AI_REQUEST_PRESENCE_PENALTY = "gen_ai.request.presence_penalty"
+    GEN_AI_REQUEST_STOP_SEQUENCES = "gen_ai.request.stop_sequences"
     GEN_AI_REQUEST_TEMPERATURE = "gen_ai.request.temperature"
-    GEN_AI_REQUEST_TOP_P = "gen_ai.request.top_p"
     GEN_AI_REQUEST_TOP_K = "gen_ai.request.top_k"
-    GEN_AI_REQUEST_MAX_TOKENS = "gen_ai.request.max_tokens"
+    GEN_AI_REQUEST_TOP_P = "gen_ai.request.top_p"
+
+    # GenAI Response Attributes (OTel Semconv)
+    GEN_AI_TOKEN_TYPE = "gen_ai.token.type"
+    GEN_AI_RESPONSE_FINISH_REASON = "gen_ai.response.finish_reasons"
+    GEN_AI_RESPONSE_ID = "gen_ai.response.id"
+    GEN_AI_RESPONSE_MODEL = "gen_ai.response.model"
+    GEN_AI_USAGE_INPUT_TOKENS = "gen_ai.usage.input_tokens"
+    GEN_AI_USAGE_OUTPUT_TOKENS = "gen_ai.usage.output_tokens"
+    GEN_AI_TOOL_CALL_ID = "gen_ai.tool.call.id"
+    GEN_AI_TOOL_NAME = "gen_ai.tool.name"
+
+    # GenAI Operation Types (OTel Semconv)
+    GEN_AI_OPERATION_TYPE_CHAT = "chat"
+    GEN_AI_OPERATION_TYPE_TOOLS = "execute_tool"
+    GEN_AI_OPERATION_TYPE_EMBEDDING = "embeddings"
+    GEN_AI_OPERATION_TYPE_IMAGE = "image"
+    GEN_AI_OPERATION_TYPE_AUDIO = "audio"
+    GEN_AI_OPERATION_TYPE_VECTORDB = "vectordb"
+    GEN_AI_OPERATION_TYPE_FRAMEWORK = "framework"
+    GEN_AI_OPERATION_TYPE_AGENT = "agent"
+    GEN_AI_OPERATION_TYPE_CREATE_AGENT = "create_agent"
+
+    # GenAI Output Types (OTel Semconv)
+    GEN_AI_OUTPUT_TYPE_IMAGE = "image"
+    GEN_AI_OUTPUT_TYPE_JSON = "json"
+    GEN_AI_OUTPUT_TYPE_SPEECH = "speech"
+    GEN_AI_OUTPUT_TYPE_TEXT = "text"
+
+    # GenAI System Names (OTel Semconv)
+    GEN_AI_SYSTEM_ANTHROPIC = "anthropic"
+    GEN_AI_SYSTEM_AWS_BEDROCK = "aws.bedrock"
+    GEN_AI_SYSTEM_AZURE_AI_INFERENCE = "az.ai.inference"
+    GEN_AI_SYSTEM_AZURE_OPENAI = "az.ai.openai"
+    GEN_AI_SYSTEM_COHERE = "cohere"
+    GEN_AI_SYSTEM_DEEPSEEK = "deepseek"
+    GEN_AI_SYSTEM_GEMINI = "gemini"
+    GEN_AI_SYSTEM_GROQ = "groq"
+    GEN_AI_SYSTEM_IBM_WATSON = "ibm.watson.ai"
+    GEN_AI_SYSTEM_MISTRAL = "mistral_ai"
+    GEN_AI_SYSTEM_OPENAI = "openai"
+    GEN_AI_SYSTEM_PERPLEXITY = "perplexity"
+    GEN_AI_SYSTEM_VERTEXAI = "vertex_ai"
+    GEN_AI_SYSTEM_XAI = "xai"
+
+    # GenAI OpenAI Attributes (OTel Semconv)
+    GEN_AI_REQUEST_SERVICE_TIER = "gen_ai.request.service_tier"
+    GEN_AI_RESPONSE_SERVICE_TIER = "gen_ai.response.service_tier"
+    GEN_AI_RESPONSE_SYSTEM_FINGERPRINT = "gen_ai.response.system_fingerprint"
+
+    # GenAI System Names (Extra)
+    GEN_AI_SYSTEM_HUGGING_FACE = "huggingface"
+    GEN_AI_SYSTEM_OLLAMA = "ollama"
+    GEN_AI_SYSTEM_GPT4ALL = "gpt4all"
+    GEN_AI_SYSTEM_ELEVENLABS = "elevenlabs"
+    GEN_AI_SYSTEM_VLLM = "vLLM"
+    GEN_AI_SYSTEM_GOOGLE_AI_STUDIO = "google.ai.studio"
+    GEN_AI_SYSTEM_REKAAI = "rekaai"
+    GEN_AI_SYSTEM_PREMAI = "premai"
+    GEN_AI_SYSTEM_LANGCHAIN = "langchain"
+    GEN_AI_SYSTEM_LLAMAINDEX = "llama_index"
+    GEN_AI_SYSTEM_HAYSTACK = "haystack"
+    GEN_AI_SYSTEM_EMBEDCHAIN = "embedchain"
+    GEN_AI_SYSTEM_MEM0 = "mem0"
+    GEN_AI_SYSTEM_LITELLM = "litellm"
+    GEN_AI_SYSTEM_CREWAI = "crewai"
+    GEN_AI_SYSTEM_AG2 = "ag2"
+    GEN_AI_SYSTEM_MULTION = "multion"
+    GEN_AI_SYSTEM_DYNAMIQ = "dynamiq"
+    GEN_AI_SYSTEM_PHIDATA = "phidata"
+    GEN_AI_SYSTEM_JULEP = "julep"
+    GEN_AI_SYSTEM_AI21 = "ai21"
+    GEN_AI_SYSTEM_CONTROLFLOW = "controlflow"
+    GEN_AI_SYSTEM_ASSEMBLYAI = "assemblyai"
+    GEN_AI_SYSTEM_CRAWL4AI = "crawl4ai"
+    GEN_AI_SYSTEM_FIRECRAWL = "firecrawl"
+    GEN_AI_SYSTEM_LETTA = "letta"
+    GEN_AI_SYSTEM_TOGETHER = "together"
+
+    # GenAI Request Attributes (Extra)
     GEN_AI_REQUEST_IS_STREAM = "gen_ai.request.is_stream"
     GEN_AI_REQUEST_USER = "gen_ai.request.user"
-    GEN_AI_REQUEST_SEED = "gen_ai.request.seed"
-    GEN_AI_REQUEST_FREQUENCY_PENALTY = "gen_ai.request.frequency_penalty"
-    GEN_AI_REQUEST_PRESENCE_PENALTY = "gen_ai.request.presence_penalty"
-    GEN_AI_REQUEST_EMBEDDING_FORMAT = "gen_ai.request.embedding_format"
     GEN_AI_REQUEST_EMBEDDING_DIMENSION = "gen_ai.request.embedding_dimension"
     GEN_AI_REQUEST_TOOL_CHOICE = "gen_ai.request.tool_choice"
     GEN_AI_REQUEST_AUDIO_VOICE = "gen_ai.request.audio_voice"
@@ -47,28 +131,23 @@ class SemanticConvetion:
     GEN_AI_REQUEST_AUDIO_SPEED = "gen_ai.request.audio_speed"
     GEN_AI_REQUEST_AUDIO_SETTINGS = "gen_ai.request.audio_settings"
     GEN_AI_REQUEST_AUDIO_DURATION = "gen_ai.request.audio_duration"
-    GEN_AI_REQUEST_FINETUNE_STATUS = "gen_ai.request.fine_tune_status"
-    GEN_AI_REQUEST_FINETUNE_MODEL_SUFFIX = "gen_ai.request.fine_tune_model_suffix"
-    GEN_AI_REQUEST_FINETUNE_MODEL_EPOCHS = "gen_ai.request.fine_tune_n_epochs"
-    GEN_AI_REQUEST_FINETUNE_MODEL_LRM = "gen_ai.request.learning_rate_multiplier"
-    GEN_AI_REQUEST_FINETUNE_BATCH_SIZE = "gen_ai.request.fine_tune_batch_size"
-    GEN_AI_REQUEST_VALIDATION_FILE = "gen_ai.request.validation_file"
-    GEN_AI_REQUEST_TRAINING_FILE = "gen_ai.request.training_file"
-
     GEN_AI_REQUEST_IMAGE_SIZE = "gen_ai.request.image_size"
     GEN_AI_REQUEST_IMAGE_QUALITY = "gen_ai.request.image_quality"
     GEN_AI_REQUEST_IMAGE_STYLE = "gen_ai.request.image_style"
+    GEN_AI_HUB_OWNER = "gen_ai.hub.owner"
+    GEN_AI_HUB_REPO = "gen_ai.hub.repo"
+    GEN_AI_RETRIEVAL_SOURCE = "gen_ai.retrieval.source"
+    GEN_AI_REQUESTS = "gen_ai.total.requests"
+    GEN_AI_DATA_SOURCES = "gen_ai.data_source_count"
+    GEN_AI_ENVIRONMENT = "gen_ai.environment"
+    GEN_AI_APPLICATION_NAME = "gen_ai.application_name"
+    GEN_AI_SDK_VERSION = "gen_ai.sdk.version"
 
-    # GenAI Usage
-    GEN_AI_USAGE_PROMPT_TOKENS = "gen_ai.usage.input_tokens"
-    GEN_AI_USAGE_COMPLETION_TOKENS = "gen_ai.usage.output_tokens"
+    # GenAI Response Attributes (Extra)
     GEN_AI_USAGE_TOTAL_TOKENS = "gen_ai.usage.total_tokens"
     GEN_AI_USAGE_COST = "gen_ai.usage.cost"
-
-    # GenAI Response
-    GEN_AI_RESPONSE_ID = "gen_ai.response.id"
-    GEN_AI_RESPONSE_FINISH_REASON = "gen_ai.response.finish_reasons"
-    GEN_AI_RESPONSE_IMAGE = "gen_ai.response.image"  # Not used directly in code yet
+    GEN_AI_RESPONSE_IMAGE = "gen_ai.response.image"
+    GEN_AI_TOOL_CALLS = "gen_ai.response.tool_calls"
 
     # GenAI Content
     GEN_AI_CONTENT_PROMPT_EVENT = "gen_ai.content.prompt"
@@ -90,52 +169,6 @@ class SemanticConvetion:
     GEN_AI_EVAL_ANSWER_RELEVANCY = "gen_ai.eval.answer_relevancy"
     GEN_AI_EVAL_GROUNDEDNESS = "gen_ai.eval.groundedness"
 
-    GEN_AI_TYPE_CHAT = "chat"
-    GEN_AI_TYPE_EMBEDDING = "embedding"
-    GEN_AI_TYPE_IMAGE = "image"
-    GEN_AI_TYPE_AUDIO = "audio"
-    GEN_AI_TYPE_FINETUNING = "fine_tuning"
-    GEN_AI_TYPE_VECTORDB = "vectordb"
-    GEN_AI_TYPE_FRAMEWORK = "framework"
-    GEN_AI_TYPE_AGENT = "agent"
-
-    GEN_AI_SYSTEM_HUGGING_FACE = "huggingface"
-    GEN_AI_SYSTEM_OPENAI = "openai"
-    GEN_AI_SYSTEM_AZURE_OPENAI = "azure_openai"
-    GEN_AI_SYSTEM_ANTHROPIC = "anthropic"
-    GEN_AI_SYSTEM_COHERE = "cohere"
-    GEN_AI_SYSTEM_MISTRAL = "mistral"
-    GEN_AI_SYSTEM_BEDROCK = "bedrock"
-    GEN_AI_SYSTEM_VERTEXAI = "vertex_ai"
-    GEN_AI_SYSTEM_GROQ = "groq"
-    GEN_AI_SYSTEM_OLLAMA = "ollama"
-    GEN_AI_SYSTEM_GPT4ALL = "gpt4all"
-    GEN_AI_SYSTEM_ELEVENLABS = "elevenlabs"
-    GEN_AI_SYSTEM_VLLM = "vLLM"
-    GEN_AI_SYSTEM_GOOGLE_AI_STUDIO = "google-ai-studio"
-    GEN_AI_SYSTEM_REKAAI = "rekaai"
-    GEN_AI_SYSTEM_PREMAI = "premai"
-    GEN_AI_SYSTEM_AZURE_AI_INFERENCE = "azure-ai-inference"
-    GEN_AI_SYSTEM_LANGCHAIN = "langchain"
-    GEN_AI_SYSTEM_LLAMAINDEX = "llama_index"
-    GEN_AI_SYSTEM_HAYSTACK = "haystack"
-    GEN_AI_SYSTEM_EMBEDCHAIN = "embedchain"
-    GEN_AI_SYSTEM_MEM0 = "mem0"
-    GEN_AI_SYSTEM_LITELLM = "litellm"
-    GEN_AI_SYSTEM_CREWAI = "crewai"
-    GEN_AI_SYSTEM_AG2 = "ag2"
-    GEN_AI_SYSTEM_MULTION = "multion"
-    GEN_AI_SYSTEM_DYNAMIQ = "dynamiq"
-    GEN_AI_SYSTEM_PHIDATA = "phidata"
-    GEN_AI_SYSTEM_JULEP = "julep"
-    GEN_AI_SYSTEM_AI21 = "ai21"
-    GEN_AI_SYSTEM_CONTROLFLOW = "controlflow"
-    GEN_AI_SYSTEM_ASSEMBLYAI = "assemblyai"
-    GEN_AI_SYSTEM_CRAWL4AI = "crawl4ai"
-    GEN_AI_SYSTEM_FIRECRAWL = "firecrawl"
-    GEN_AI_SYSTEM_LETTA = "letta"
-    GEN_AI_SYSTEM_TOGETHER = "together"
-
     # Vector DB
     DB_OPERATION_API_ENDPOINT = "db.operation.api_endpoint"
     DB_REQUESTS = "db.total.requests"

{openlit-1.33.8.dist-info → openlit-1.33.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: openlit
-Version: 1.33.8
+Version: 1.33.10
 Summary: OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications and GPUs, facilitating the integration of observability into your GenAI-driven projects
 License: Apache-2.0
 Keywords: OpenTelemetry,otel,otlp,llm,tracing,openai,anthropic,claude,cohere,llm monitoring,observability,monitoring,gpt,Generative AI,chatGPT,gpu

openlit-1.33.10.dist-info/RECORD

@@ -0,0 +1,122 @@
+openlit/__helpers.py,sha256=44dXhkRJ5K42qjNwC5PMphLj2N6CoXdO3m9ZmbxSFtQ,9840
+openlit/__init__.py,sha256=GKu_3fhw27IXODjUxTpTkX0JGO9yskuyxhX4w0y6Qx4,22446
+openlit/evals/__init__.py,sha256=nJe99nuLo1b5rf7pt9U9BCdSDedzbVi2Fj96cgl7msM,380
+openlit/evals/all.py,sha256=oWrue3PotE-rB5WePG3MRYSA-ro6WivkclSHjYlAqGs,7154
+openlit/evals/bias_detection.py,sha256=mCdsfK7x1vX7S3psC3g641IMlZ-7df3h-V6eiICj5N8,8154
+openlit/evals/hallucination.py,sha256=Yn5OfWVJKynAiImV_aAqCvc0zqYjdJ3XUppCnMTy1pg,7507
+openlit/evals/toxicity.py,sha256=Ii_kX2GToO9fDstDBuK4iN0tEQUkMoPWUBDMFFfeMC4,7000
+openlit/evals/utils.py,sha256=lXgxyh1OZHeQzlzTLBAEnIYVaUt0YqYA6Uaygjpbv0s,8472
+openlit/guard/__init__.py,sha256=B-D7iPadGFn5i7nEsQfVbS6feL1ViRht3zWTQ45Jgkg,417
+openlit/guard/all.py,sha256=VNHQERad-4qAMWsJJrpW9QNkhM7U8v_wy20KtDtQgzM,9755
+openlit/guard/prompt_injection.py,sha256=3e4DKxB7QDzM-xPCpwEuureiH_2s_OTJ9BSckknPpzY,5784
+openlit/guard/restrict_topic.py,sha256=KTuWa7XeMsV4oXxOrD1CYZV0wXWxTfA0H3p_6q_IOsk,6444
+openlit/guard/sensitive_topic.py,sha256=RgVw_laFERv0nNdzBsAd2_3yLomMOK-gVq-P7oj1bTk,5552
+openlit/guard/utils.py,sha256=x0-_hAtNa_ogYR2GfnwiBF1rlqaXtaJ-rJeGguTDe-Q,7663
+openlit/instrumentation/ag2/__init__.py,sha256=Nf9cDoXB16NYgZisvVQduFYJ5fpU90CNlMrIF4pSH-Y,1827
+openlit/instrumentation/ag2/ag2.py,sha256=Yo6WfuTLLk3yVValZGp7GC5lKb2Z3kOHAUWxlhhOyN4,4454
+openlit/instrumentation/ai21/__init__.py,sha256=Wk23syYEbHuKBzdIabD3dfjZJTW-qzu7LgJPbG8mNHY,2549
+openlit/instrumentation/ai21/ai21.py,sha256=-wzx6SMGJaMXXgfC4T31EBqi6TEC1JNy-fV5bOj4nY4,33615
+openlit/instrumentation/ai21/async_ai21.py,sha256=vay0klz43slfC9RhITQNC9iKAg3gzAqSahy9rPgqIiI,33719
+openlit/instrumentation/anthropic/__init__.py,sha256=IoWGApFQ72DQYp9jN-LRDr0uRW3OamDgHG-mO23OSzs,1887
+openlit/instrumentation/anthropic/anthropic.py,sha256=fj023njYA4nSvwuj5vrvOsGqyqKvxzzMdY7pWYKikM4,22332
+openlit/instrumentation/anthropic/async_anthropic.py,sha256=yxy5UlRaodyVfMTLK5UDujoCZ9ioHW__-YdBv1jTRMg,22418
+openlit/instrumentation/assemblyai/__init__.py,sha256=6uSNexxRJXIX-ZLitD3ow7ej3WK_N_W4ZxeIFb_eseY,1535
+openlit/instrumentation/assemblyai/assemblyai.py,sha256=dLCdL9SyfOocmzvT0iYG4UwM3giom_nKFlCoTQix5Bk,6262
+openlit/instrumentation/astra/__init__.py,sha256=G4alCOR6hXQvUQPDCS8lY1rj0Mz-KmrW5vVWk5loO78,8054
+openlit/instrumentation/astra/astra.py,sha256=19WweO3jGvUOC2fkij2ZKKaGbKfg1LaC-GSMoEsDmjU,12061
+openlit/instrumentation/astra/async_astra.py,sha256=8te62MqJBcdVqtG4iz9wFAn9bFaeESFvcqZVaVA9VnM,12073
+openlit/instrumentation/azure_ai_inference/__init__.py,sha256=xmDk8eK0VB6C1TsH5oIciVnxAhIrXiqDzyqHgy6u51Q,2621
+openlit/instrumentation/azure_ai_inference/async_azure_ai_inference.py,sha256=anQUO465P0ns9CrKAPFGFziA5qJvGuv69RB50cFAysk,29894
+openlit/instrumentation/azure_ai_inference/azure_ai_inference.py,sha256=b611q2NSIsT6KfgOogtfcHW-eliOK_bS8rSnOjU1D0A,29790
+openlit/instrumentation/bedrock/__init__.py,sha256=i32hjjdBu2JUGS1eytWjV2WX2_xvXw-iqrbXADSpHx0,1525
+openlit/instrumentation/bedrock/bedrock.py,sha256=IwV2y3e0yXcK11_6VJ6HjeaC9ic0Xc3rd4hqNyMBY6I,12234
+openlit/instrumentation/chroma/__init__.py,sha256=61lFpHlUEQUobsUJZHXdvOViKwsOH8AOvSfc4VgCmiM,3253
+openlit/instrumentation/chroma/chroma.py,sha256=hZgmGSWf22UqLyoyFTSh9uqrSiFNwMPrCZW9HckMJvo,10513
+openlit/instrumentation/cohere/__init__.py,sha256=P8w30qt_RoXeQ5VsdW0KB4G1-WaWS9DkhTqaoCZuDeI,2825
+openlit/instrumentation/cohere/async_cohere.py,sha256=_W7mcfShY0LlPc6S5WmIRlp9KVBqivBBSfZbThb1Wn4,30567
+openlit/instrumentation/cohere/cohere.py,sha256=egR629mOhSRdg1-x-rMwqNjBqIIxjuYNTS8_HQ3KfAg,30450
+openlit/instrumentation/controlflow/__init__.py,sha256=iKZ08IANfoN_n4o1TZJIK_C_t6RZQ6AS1H7kMfyBbYA,2118
+openlit/instrumentation/controlflow/controlflow.py,sha256=m9ZqO_9iQo1Hg9-9Endtw_biC0cZfzaFVLlpUiN9sXs,5538
+openlit/instrumentation/crawl4ai/__init__.py,sha256=CGkcbQijpKae_8GD_1ybDnCCk0MVu2AdV-ppFOg8mAA,1907
+openlit/instrumentation/crawl4ai/async_crawl4ai.py,sha256=R3S9iMkcetQhiag18oq29of7TDU5s6kmpGw9sWHxylQ,4859
+openlit/instrumentation/crawl4ai/crawl4ai.py,sha256=COTz6EWKK1iRGWMsPpuSC63P4jvZdyUyY_mMFSHqndE,4841
+openlit/instrumentation/crewai/__init__.py,sha256=cETkkwnKYEMAKlMrHbZ9-RvcRUPYaSNqNIhy2-vCDK8,1794
+openlit/instrumentation/crewai/crewai.py,sha256=JblvqWdZqC8H6geiQB35sHS0KBP_N0nGZzTG8DVHQpk,7181
+openlit/instrumentation/dynamiq/__init__.py,sha256=2uIHHxFWca0g2YLO2RBfi2Al6uWUYvVZBfDiPOHCdpQ,2331
+openlit/instrumentation/dynamiq/dynamiq.py,sha256=1Iga7NS4zw3LDFE_VMxT1PBGC4MAcfmCCKoyQRORojE,5260
+openlit/instrumentation/elevenlabs/__init__.py,sha256=BZjAe-kzFJpKxT0tKksXVfZgirvgEp8qM3SfegWU5co,2631
+openlit/instrumentation/elevenlabs/async_elevenlabs.py,sha256=H5svCDy_JGCsssi4IbF3HDF0ECgvR6_I_j1p0rVJe0o,6792
+openlit/instrumentation/elevenlabs/elevenlabs.py,sha256=khhkb7CHOMkQwhia___t0Iy9xMrQs3w-dEovvqdIeks,6775
+openlit/instrumentation/embedchain/__init__.py,sha256=8TYk1OEbz46yF19dr-gB_x80VZMagU3kJ8-QihPXTeA,1929
+openlit/instrumentation/embedchain/embedchain.py,sha256=-V4QAPtbE8mDE8FGzYQ2AUp8FpoYD2ygJWmXPEqwQKs,7874
+openlit/instrumentation/firecrawl/__init__.py,sha256=2QTcpPoaximsApdp68WD2iYR1_vZnKlkbAd4RHhgeOo,1836
+openlit/instrumentation/firecrawl/firecrawl.py,sha256=ZtYJsKcWuNOKihI76G7gZOlNSHs5ua8THj7FBWDukKY,3796
+openlit/instrumentation/google_ai_studio/__init__.py,sha256=n_vOdZeccUvw8W_NYEpiw468sywqnD5O_E1CjuElXYM,2009
+openlit/instrumentation/google_ai_studio/async_google_ai_studio.py,sha256=vYPfpwvHQh1vLgR2JMhpzXLJ4e7vPU5NhjjsAR7UNwM,11006
+openlit/instrumentation/google_ai_studio/google_ai_studio.py,sha256=4EfHmAQG9Auihs0DaaSx1wBmC8FV-1gDAGh5cnltMIE,10988
+openlit/instrumentation/gpt4all/__init__.py,sha256=QGk_uhpS9ac3jk_nk7yGAw9YBbGbbMrVv6OkAh4vvEM,1765
+openlit/instrumentation/gpt4all/gpt4all.py,sha256=ATbPMj1jzF-62iKTKMXnREvzM-eYndZB2nSIl2LNRt4,24037
+openlit/instrumentation/gpu/__init__.py,sha256=flcKWN18lqrSiuqsQAGM7x7gPUr5YuZNSPlrocC1zcE,11028
+openlit/instrumentation/groq/__init__.py,sha256=o_3StdM3VyMjL4XT-agYfZkQouVr1MqeQ-2fUPdpRyI,1861
+openlit/instrumentation/groq/async_groq.py,sha256=qGf5x7Ng4D_IfK2GMctWXe1Cq6uaT4sk-cAqWMdSnhM,24646
+openlit/instrumentation/groq/groq.py,sha256=CB8Dtgym7RaMkM8FBpHMoYlAy1BRoW7n9EFX3YdBsQc,24560
+openlit/instrumentation/haystack/__init__.py,sha256=QK6XxxZUHX8vMv2Crk7rNBOc64iOOBLhJGL_lPlAZ8s,1758
+openlit/instrumentation/haystack/haystack.py,sha256=qGBLRFRs5Z0nuAYf9oic3BrdQMx7eXT-g3S0rihHHtU,3901
+openlit/instrumentation/julep/__init__.py,sha256=oonEVK41P5g4SYRm0E_H4zCVH9NM4aJ-UswXzF3Oiv0,3136
+openlit/instrumentation/julep/async_julep.py,sha256=fMMa8_6r97ipDRo8_soQKSZ1tw9LRCjdgd_JTFEXjkM,5283
+openlit/instrumentation/julep/julep.py,sha256=tKjQN82PyKHNhfqwjjFGz5iCZRkFn1kLPuc2wIt8F0Y,5286
+openlit/instrumentation/langchain/__init__.py,sha256=thTGg9NCNlnVEUc_KsxR94AY2v5pwEk7uVnbLJ_Bl-4,3823
+openlit/instrumentation/langchain/async_langchain.py,sha256=s1LzZhT3Dxw2FD5wwK2hmDBSoxtp39yuqUB9ru5g9so,18155
+openlit/instrumentation/langchain/langchain.py,sha256=fk4nBc-wqJRE45PkXuOCIHUNoke1wlsNGEd3t1l_lis,18017
+openlit/instrumentation/letta/__init__.py,sha256=sjjOuMvZ1EPGEluNW0WTuSXYPhrb453cBIizt88Ta3g,2951
+openlit/instrumentation/letta/letta.py,sha256=WJYDmHQVeBsLBIlTHfZXiHBhjOkmr9dEj2HtkX-1OU0,8405
+openlit/instrumentation/litellm/__init__.py,sha256=dIFwJx45riHwolxBlUZUabO2TEnAR9MptwmSaFvaJfY,2314
+openlit/instrumentation/litellm/async_litellm.py,sha256=6Ljft-M80763dQvhgT_RPvt63EE33pWUY5G1rE6MciM,30328
+openlit/instrumentation/litellm/litellm.py,sha256=n5p0MnDFjNwYhYkcRfFRWRH_qtXbUR821X1GvHigYPc,30234
+openlit/instrumentation/llamaindex/__init__.py,sha256=vPtK65G6b-TwJERowVRUVl7f_nBSlFdwPBtpg8dOGos,1977
+openlit/instrumentation/llamaindex/llamaindex.py,sha256=reCkNucy-B4MC0ZsnlJ2lU68iN81KyDmWMqb180IaIc,4058
+openlit/instrumentation/mem0/__init__.py,sha256=guOkLoSKvHSVSmEWhCHMVRMUGEa5JzqI8CIluHtwirQ,2417
+openlit/instrumentation/mem0/mem0.py,sha256=AIddouvkTTjhyHrMOX7Z8z9fZ7jpD5PVlTYeHWatycI,5315
+openlit/instrumentation/milvus/__init__.py,sha256=qi1yfmMrvkDtnrN_6toW8qC9BRL78bq7ayWpObJ8Bq4,2961
+openlit/instrumentation/milvus/milvus.py,sha256=UOucpoOH0ay2jG9CRUsWtFXhceYJ3Z6ghWzhORCOF2E,9103
+openlit/instrumentation/mistral/__init__.py,sha256=u3e9ueG0-wJ1ZgRa8zknPj3bTWA0AFI-3-UxlothkLg,2980
+openlit/instrumentation/mistral/async_mistral.py,sha256=h_fd9oDX_AuFoK6023haxaYxr0PMd0M7PLs05uwFmA8,30999
+openlit/instrumentation/mistral/mistral.py,sha256=RnFedQO05jEWyhjtsxKRAIALf1iAkbTA82-vjDb-bcs,30895
+openlit/instrumentation/multion/__init__.py,sha256=DUt70uINLYi4xTxZ6D3bxKUBHYi1FpKbliQ6E7D_SeQ,3069
+openlit/instrumentation/multion/async_multion.py,sha256=2lSIP3HQa6XvWoA0pafQ1qnEIA1bBUxTlXwrGWZeOkc,6021
+openlit/instrumentation/multion/multion.py,sha256=LaUKx8XShi4Lv3IwnQR_NB0_Eb9s5Xq_VC-E0I17BlY,6003
+openlit/instrumentation/ollama/__init__.py,sha256=KDO0JxdfNiQiEpWxEk93m3LiM07zAmvnNznb1E3PtN4,2856
+openlit/instrumentation/ollama/async_ollama.py,sha256=k9ya3wSZfb8rQMqUqi3-fRcP2cw969-jf8TMjl47cyY,28301
+openlit/instrumentation/ollama/ollama.py,sha256=Y74fa0C4JrxN5m4c7_lFvEaamnGNqWlCc2Zmn2gIMUs,28197
+openlit/instrumentation/openai/__init__.py,sha256=54pwkndSO1IS78Qqx1A-QNkObx5eJnsvWeMtDZj2lD8,4773
+openlit/instrumentation/openai/async_openai.py,sha256=sm9ZbO5RYp69-4ak2kmQ8iWziE8qzG8fCc10jcfWYoE,50461
+openlit/instrumentation/openai/openai.py,sha256=y9ZS1NQmXzBTM0I5Nt0Ex5DK8x7EUiIW8t-coqfidMs,50290
+openlit/instrumentation/phidata/__init__.py,sha256=rfPCXYOIsJbxChee2p269UzkJ1Z-pvQbii7Fgrw1v2g,1527
+openlit/instrumentation/phidata/phidata.py,sha256=0qLqJ79A5-fVXDDDfFr0yLr1yiJQqaVa79l_9I5jwuQ,4799
+openlit/instrumentation/pinecone/__init__.py,sha256=Mv9bElqNs07_JQkYyNnO0wOM3hdbprmw7sttdMeKC7g,2526
+openlit/instrumentation/pinecone/pinecone.py,sha256=EV9PPri34c_OCGKqRuImshn0E1L5HsSNwgHWSr8v_DE,8747
+openlit/instrumentation/premai/__init__.py,sha256=VUrJaD59cpUDizobpkkIkWq-Kurq84Daj_SBwEMlMDE,1796
+openlit/instrumentation/premai/premai.py,sha256=grBsIc_5xt8XjtHeQymgD9zGPMZ9Jb55CPWOYd42i94,27890
+openlit/instrumentation/qdrant/__init__.py,sha256=GMlZgRBKoQMgrL4cFbAKwytfdTHLzJEIuTQMxp0uZO0,8940
+openlit/instrumentation/qdrant/async_qdrant.py,sha256=I_nchTueGLvb8OXID7MZyV1k97xnwGBDQWEzWla7vqo,15053
+openlit/instrumentation/qdrant/qdrant.py,sha256=WUrjYCgQZVWVyFxiA-lXB6LbLM1l8tFWG5FoojiShIg,15470
+openlit/instrumentation/reka/__init__.py,sha256=LIZt2K-GAXD69JAXIl_apf-IHIYMQSfRG2eHlAX-Zj0,1844
+openlit/instrumentation/reka/async_reka.py,sha256=MNSNy1SoaCcWgv-dAuKD7ylk4q6dLn10RFeKxc2IuiM,9383
+openlit/instrumentation/reka/reka.py,sha256=OU6Zv3FQ4f9Ewgd3ZlrLVRfuoawNFfKTmrU-_ZH7f9s,9365
+openlit/instrumentation/together/__init__.py,sha256=Kjj2Q2iy7e93Zsz4jPocOg8fb0DmNHMF1VzP90XieC4,2601
+openlit/instrumentation/together/async_together.py,sha256=ZGb_Gf9WZ7aDdM5L61_tF_PfOb1OOqkq8CMD77AV0UY,30464
+openlit/instrumentation/together/together.py,sha256=M6nysPLb2UM_yWGGRtJYf4YtNVSkM0bUZ__uAahSy_8,30360
+openlit/instrumentation/transformers/__init__.py,sha256=Fq2Nz1IsduF2GMIRSK3DK8KD0BYx6zk4zMASlkD9-cY,1437
+openlit/instrumentation/transformers/transformers.py,sha256=A6CPjMh9alqMmxs_ZIewlkT2WrPDOtw8VjRrYm99Qi0,9108
+openlit/instrumentation/vertexai/__init__.py,sha256=dgzzSOFFIw9TD8xyp8T2FTEMG-_15oyNycNN7MLjwsI,3645
+openlit/instrumentation/vertexai/async_vertexai.py,sha256=wNTJ42ZXAHrb727OT6XDOx8p3hmRD6uY_G4suSFPyTk,22982
+openlit/instrumentation/vertexai/vertexai.py,sha256=Jns15HksqqjRPpj_ogK7KXwMXW9OTQMnqZBdQjZXMAk,22896
+openlit/instrumentation/vllm/__init__.py,sha256=9rT_S7o28PLzoqjwW7bL7JZoBuigZZLRlctud6yZD_k,1478
+openlit/instrumentation/vllm/vllm.py,sha256=Momw7f94flqakXhi9PF1lz2xTp6L-Ddson8ymwpyprw,7724
+openlit/otel/metrics.py,sha256=URL7gzQbnxaNQJSX7oHRa15v6xi1GFmANn-5uFNL-aY,6378
+openlit/otel/tracing.py,sha256=fG3vl-flSZ30whCi7rrG25PlkIhhr8PhnfJYCkZzCD0,3895
+openlit/semcov/__init__.py,sha256=c9rHbQCFiGmbHp-8bIxY6x7z2HimSO-ANrXLXtpy1hE,12316
+openlit-1.33.10.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+openlit-1.33.10.dist-info/METADATA,sha256=-7lZ2D6sEjbDiMh_ZOf87_NKKi4EbrWfNUI7781feyw,23502
+openlit-1.33.10.dist-info/WHEEL,sha256=XbeZDeTWKc1w7CSIyre5aMDU_-PohRwTQceYnisIYYY,88
+openlit-1.33.10.dist-info/RECORD,,