Skip to content

fix(integrations): improve embeddings support for openai #5121

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
constantinius merged 1 commit into from
Nov 20, 2025
Merged

fix(integrations): improve embeddings support for openai #5121

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions sentry_sdk/consts.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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.
Expand Down
12 changes: 9 additions & 3 deletions sentry_sdk/integrations/openai.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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")
Expand Down
8 changes: 4 additions & 4 deletions tests/integrations/openai/test_openai.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down Expand Up @@ -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
Expand Down