fix(integrations): improve embeddings support for openai

Author: constantinius

sentry_sdk/consts.py

@@ -465,6 +465,12 @@ class SPANDATA:
     Example: "The weather in Paris is rainy and overcast, with temperatures around 57°F"
     """
 
+    GEN_AI_EMBEDDINGS_INPUT = "gen_ai.embeddings.input"
+    """
+    The input to the embeddings operation.
+    Example: "Hello!"
+    """
+
     GEN_AI_OPERATION_NAME = "gen_ai.operation.name"
     """
     The name of the operation being performed.

sentry_sdk/integrations/openai.py

@@ -195,9 +195,15 @@ def _set_input_data(span, kwargs, operation, integration):
         scope = sentry_sdk.get_current_scope()
         messages_data = truncate_and_annotate_messages(normalized_messages, span, scope)
         if messages_data is not None:
-            set_data_normalized(
-                span, SPANDATA.GEN_AI_REQUEST_MESSAGES, messages_data, unpack=False
-            )
+            # Use appropriate field based on operation type
+            if operation == "embeddings":
+                set_data_normalized(
+                    span, SPANDATA.GEN_AI_EMBEDDINGS_INPUT, messages_data, unpack=False
+                )
+            else:
+                set_data_normalized(
+                    span, SPANDATA.GEN_AI_REQUEST_MESSAGES, messages_data, unpack=False
+                )
 
     # Input attributes: Common
     set_data_normalized(span, SPANDATA.GEN_AI_SYSTEM, "openai")

tests/integrations/openai/test_openai.py

@@ -501,9 +501,9 @@ def test_embeddings_create(
     span = tx["spans"][0]
     assert span["op"] == "gen_ai.embeddings"
     if send_default_pii and include_prompts:
-        assert "hello" in span["data"][SPANDATA.GEN_AI_REQUEST_MESSAGES]
+        assert "hello" in span["data"][SPANDATA.GEN_AI_EMBEDDINGS_INPUT]
     else:
-        assert SPANDATA.GEN_AI_REQUEST_MESSAGES not in span["data"]
+        assert SPANDATA.GEN_AI_EMBEDDINGS_INPUT not in span["data"]
 
     assert span["data"]["gen_ai.usage.input_tokens"] == 20
     assert span["data"]["gen_ai.usage.total_tokens"] == 30
@@ -549,9 +549,9 @@ async def test_embeddings_create_async(
     span = tx["spans"][0]
     assert span["op"] == "gen_ai.embeddings"
     if send_default_pii and include_prompts:
-        assert "hello" in span["data"][SPANDATA.GEN_AI_REQUEST_MESSAGES]
+        assert "hello" in span["data"][SPANDATA.GEN_AI_EMBEDDINGS_INPUT]
     else:
-        assert SPANDATA.GEN_AI_REQUEST_MESSAGES not in span["data"]
+        assert SPANDATA.GEN_AI_EMBEDDINGS_INPUT not in span["data"]
 
     assert span["data"]["gen_ai.usage.input_tokens"] == 20
     assert span["data"]["gen_ai.usage.total_tokens"] == 30