Skip to content

feat(openai): Gate embeddings input collection on data_collection #6977

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

Open
ericapisani wants to merge 3 commits into from
+343 −16
Open

feat(openai): Gate embeddings input collection on data_collection #6977

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
0aa794e
feat(openai): Gate embeddings input collection on data_collection
ericapisani Jul 31, 2026
c41a9ce
lint
ericapisani Jul 31, 2026
c75e763
Merge branch 'master' into py-2588-openai-embeddings-input-data
ericapisani Jul 31, 2026
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
33 changes: 17 additions & 16 deletions sentry_sdk/integrations/openai.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -610,31 +610,36 @@ def _set_embeddings_input_data(
kwargs: "dict[str, Any]",
integration: "OpenAIIntegration",
) -> None:
messages: "Union[str, SequenceNotStr[str], Iterable[int], Iterable[Iterable[int]]]" = kwargs.get(
"input"
)

set_data_normalized(span, SPANDATA.GEN_AI_OPERATION_NAME, "embeddings")

set_on_span = (
span.set_attribute if isinstance(span, StreamedSpan) else span.set_data
)

model = kwargs.get("model")
if model is not None:
set_on_span(SPANDATA.GEN_AI_REQUEST_MODEL, model)

if (
not should_send_default_pii()
or not integration.include_prompts
or messages is None
):
set_data_normalized(span, SPANDATA.GEN_AI_OPERATION_NAME, "embeddings")
messages: "Union[str, SequenceNotStr[str], Iterable[int], Iterable[Iterable[int]]]" = kwargs.get(
"input"
)

client = sentry_sdk.get_client()
if has_data_collection_enabled(client.options):
# This takes precedence over the global data collection settings
if not integration.include_prompts:
return
if not client.options["data_collection"]["gen_ai"]["inputs"]:
return
elif not should_send_default_pii() or not integration.include_prompts:
return

if isinstance(messages, str):
set_data_normalized(span, SPANDATA.GEN_AI_OPERATION_NAME, "embeddings")
if messages is None:
return

if isinstance(messages, str):
normalized_messages = normalize_message_roles([messages]) # type: ignore
client = sentry_sdk.get_client()
scope = sentry_sdk.get_current_scope()
messages_data = (
truncate_and_annotate_embedding_inputs(normalized_messages, span, scope)
Expand All @@ -650,15 +655,13 @@ def _set_embeddings_input_data(

# dict special case following https://github.com/openai/openai-python/blob/3e0c05b84a2056870abf3bd6a5e7849020209cc3/src/openai/_utils/_transform.py#L194-L197
if not isinstance(messages, Iterable) or isinstance(messages, dict):
set_data_normalized(span, SPANDATA.GEN_AI_OPERATION_NAME, "embeddings")
return

messages = list(messages)
kwargs["input"] = messages

if len(messages) > 0:
normalized_messages = normalize_message_roles(messages)
client = sentry_sdk.get_client()
scope = sentry_sdk.get_current_scope()
messages_data = (
truncate_and_annotate_embedding_inputs(normalized_messages, span, scope)
Expand All @@ -670,8 +673,6 @@ def _set_embeddings_input_data(
span, SPANDATA.GEN_AI_EMBEDDINGS_INPUT, messages_data, unpack=False
)

set_data_normalized(span, SPANDATA.GEN_AI_OPERATION_NAME, "embeddings")


def _set_common_output_data(
span: "Union[Span, StreamedSpan]",
Expand Down
Loading
Loading