Skip to content

feat: backend changes to support EAP-based LLM monitoring #77749

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
merged 1 commit into from
Sep 19, 2024
Merged

feat: backend changes to support EAP-based LLM monitoring #77749

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
7 changes: 6 additions & 1 deletion src/sentry/search/events/fields.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1113,7 +1113,12 @@ def _normalize(self, value: str) -> str:
# this even in child classes where `normalize` have been overridden.
# Shortcutting this for now
# TODO: handle different datasets better here
if self.spans and value in ["span.duration", "span.self_time"]:
if self.spans and value in [
"span.duration",
"span.self_time",
"ai.total_tokens.used",
"ai.total_cost",
]:
return value
snuba_column = SEARCH_MAP.get(value)
if not snuba_column and is_measurement(value):
Expand Down
7 changes: 5 additions & 2 deletions src/sentry/utils/snuba.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -188,8 +188,8 @@ def log_snuba_info(content):
# message also maps to span description but gets special handling
# to support wild card searching by default
"message": "name",
"span.domain": "domain",
"span.group": "group",
"span.domain": "attr_str[domain]",
"span.group": "attr_str[group]",
"span.op": "attr_str[op]",
"span.category": "attr_str[category]",
"span.self_time": "exclusive_time_ms",
Expand All @@ -204,6 +204,9 @@ def log_snuba_info(content):
"origin.transaction": "segment_name",
"span.status_code": "attr_str[status_code]",
"replay.id": "attr_str[replay_id]",
"span.ai.pipeline.group": "attr_str[ai_pipeline_group]",
"ai.total_tokens.used": "attr_num[ai_total_tokens_used]",
"ai.total_cost": "attr_num[ai_total_cost]",
}

METRICS_SUMMARIES_COLUMN_MAP = {
Expand Down
Loading