elastic-opentelemetry-instrumentation-openai: match proposed upstream semconv (elastic#36)

Update attributes to match
open-telemetry/semantic-conventions#1603

Author: xrmx

instrumentation/elastic-opentelemetry-instrumentation-openai/README.md

@@ -2,13 +2,14 @@
 
 An OpenTelemetry instrumentation for the `openai` client library.
 
-This instrumentation currently only supports instrumenting the Chat completions APIs.
+This instrumentation currently supports instrumenting the chat completions and the embeddings APIs.
 
 We currently support the following features:
 - `sync` and `async` chat completions
-- Streaming support
-- Functions calling with tools
+- Streaming support for chat completions
+- Functions calling with tools for chat completions
 - Client side metrics
+- Embeddings API calls
 - Following 1.28.0 Gen AI Semantic Conventions
 
 ## Installation
@@ -60,7 +61,7 @@ log events instead of span events.
 ### Elastic specific semantic conventions
 
 - New `embeddings` value for `gen_ai.operation.name`
-- New `gen_ai.request.encoding_format` attribute with openai specific values `[float, base64]`
+- New `gen_ai.request.encoding_formats` attribute with openai specific values `[[float], [base64]]`
 
 ## Development
 

instrumentation/elastic-opentelemetry-instrumentation-openai/src/opentelemetry/instrumentation/openai/helpers.py

@@ -48,8 +48,8 @@
 EVENT_GEN_AI_SYSTEM_MESSAGE = "gen_ai.system.message"
 EVENT_GEN_AI_TOOL_MESSAGE = "gen_ai.tool.message"
 
-# elastic specific attributes
-GEN_AI_REQUEST_ENCODING_FORMAT = "gen_ai.request.encoding_format"
+# not yet released attributes
+GEN_AI_REQUEST_ENCODING_FORMATS = "gen_ai.request.encoding_formats"
 
 # As this is only used for a type annotation, only import from openai module
 # when running type checker like pyright since we otherwise don't want to import
@@ -204,7 +204,7 @@ def _get_embeddings_span_attributes_from_wrapper(instance, kwargs) -> Attributes
         span_attributes.update(_attributes_from_client(client))
 
     if (encoding_format := kwargs.get("encoding_format")) is not None:
-        span_attributes[GEN_AI_REQUEST_ENCODING_FORMAT] = encoding_format
+        span_attributes[GEN_AI_REQUEST_ENCODING_FORMATS] = [encoding_format]
 
     return span_attributes
 

instrumentation/elastic-opentelemetry-instrumentation-openai/tests/test_embeddings.py

@@ -18,7 +18,7 @@
 
 import openai
 import pytest
-from opentelemetry.instrumentation.openai.helpers import GEN_AI_REQUEST_ENCODING_FORMAT
+from opentelemetry.instrumentation.openai.helpers import GEN_AI_REQUEST_ENCODING_FORMATS
 from opentelemetry.trace import SpanKind, StatusCode
 from opentelemetry.semconv._incubating.attributes.gen_ai_attributes import (
     GEN_AI_OPERATION_NAME,
@@ -117,7 +117,7 @@ def test_all_the_client_options(provider_str, model, input_tokens, duration, tra
         GEN_AI_REQUEST_MODEL: model,
         GEN_AI_SYSTEM: "openai",
         GEN_AI_RESPONSE_MODEL: model,
-        GEN_AI_REQUEST_ENCODING_FORMAT: "float",
+        GEN_AI_REQUEST_ENCODING_FORMATS: ("float",),
         GEN_AI_USAGE_INPUT_TOKENS: input_tokens,
         SERVER_ADDRESS: provider.server_address,
         SERVER_PORT: provider.server_port,
@@ -159,7 +159,7 @@ def test_all_the_client_options_integration(provider_str, model, trace_exporter,
         GEN_AI_REQUEST_MODEL: model,
         GEN_AI_SYSTEM: "openai",
         GEN_AI_RESPONSE_MODEL: model,
-        GEN_AI_REQUEST_ENCODING_FORMAT: "float",
+        GEN_AI_REQUEST_ENCODING_FORMATS: ("float",),
         GEN_AI_USAGE_INPUT_TOKENS: response.usage.prompt_tokens,
         SERVER_ADDRESS: provider.server_address,
         SERVER_PORT: provider.server_port,
@@ -312,7 +312,7 @@ async def test_async_all_the_client_options(
         GEN_AI_REQUEST_MODEL: model,
         GEN_AI_SYSTEM: "openai",
         GEN_AI_RESPONSE_MODEL: model,
-        GEN_AI_REQUEST_ENCODING_FORMAT: "float",
+        GEN_AI_REQUEST_ENCODING_FORMATS: ("float",),
         GEN_AI_USAGE_INPUT_TOKENS: input_tokens,
         SERVER_ADDRESS: provider.server_address,
         SERVER_PORT: provider.server_port,
@@ -355,7 +355,7 @@ async def test_async_all_the_client_options_integration(provider_str, model, tra
         GEN_AI_REQUEST_MODEL: model,
         GEN_AI_SYSTEM: "openai",
         GEN_AI_RESPONSE_MODEL: model,
-        GEN_AI_REQUEST_ENCODING_FORMAT: "float",
+        GEN_AI_REQUEST_ENCODING_FORMATS: ("float",),
         GEN_AI_USAGE_INPUT_TOKENS: response.usage.prompt_tokens,
         SERVER_ADDRESS: provider.server_address,
         SERVER_PORT: provider.server_port,