Skip to content

Add latency metrics #4472

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 3 commits into from
Apr 8, 2025
+13 −6
Merged

Add latency metrics #4472

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
8c42f46
k
pablonyx Apr 7, 2025
80c2c03
update
pablonyx Apr 8, 2025
6389b1f
Update chat_backend.py
evan-onyx Apr 8, 2025
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
4 changes: 4 additions & 0 deletions backend/onyx/auth/users.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,6 +105,7 @@
from onyx.utils.telemetry import create_milestone_and_report
from onyx.utils.telemetry import optional_telemetry
from onyx.utils.telemetry import RecordType
from onyx.utils.timing import log_function_time
from onyx.utils.url import add_url_params
from onyx.utils.variable_functionality import fetch_ee_implementation_or_noop
from onyx.utils.variable_functionality import fetch_versioned_implementation
Expand Down Expand Up @@ -363,6 +364,7 @@ async def validate_password(self, password: str, _: schemas.UC | models.UP) -> N
)
return

@log_function_time(print_only=True)
async def oauth_callback(
self,
oauth_name: str,
Expand Down Expand Up @@ -609,6 +611,7 @@ async def on_after_request_verify(
user.email, token, new_organization=user_count == 1
)

@log_function_time(print_only=True)
async def authenticate(
self, credentials: OAuth2PasswordRequestForm
) -> Optional[User]:
Expand Down Expand Up @@ -1235,6 +1238,7 @@ async def authorize(

return OAuth2AuthorizeResponse(authorization_url=authorization_url)

@log_function_time(print_only=True)
@router.get(
"/callback",
name=callback_route_name,
Expand Down
6 changes: 1 addition & 5 deletions backend/onyx/chat/process_message.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -914,6 +914,7 @@ def stream_chat_message_objects(
retrieval_options.filters.user_folder_ids = user_folder_ids

# Create override kwargs for the search tool

override_kwargs = SearchToolOverrideKwargs(
force_no_rerank=search_for_ordering_only, # Skip reranking for ordering-only
alternate_db_session=None,
Expand Down Expand Up @@ -1113,9 +1114,6 @@ def stream_chat_message_objects(
logger.info(
f"ORDERING: Processing search results for ordering {len(user_files)} user files"
)
import time

ordering_start = time.time()

# Extract document order from search results
doc_order = []
Expand Down Expand Up @@ -1151,8 +1149,6 @@ def stream_chat_message_objects(
if f_id in file_id_to_user_file
]

time.time() - ordering_start

yield UserKnowledgeFilePacket(
user_files=[
FileDescriptor(
Expand Down
5 changes: 5 additions & 0 deletions backend/onyx/server/query_and_chat/chat_backend.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -418,6 +418,7 @@ def handle_new_chat_message(
"""
tenant_id = get_current_tenant_id()
logger.debug(f"Received new chat message: {chat_message_req.message}")
start_time = time.time()

if (
not chat_message_req.message
Expand Down Expand Up @@ -448,6 +449,10 @@ def stream_generator() -> Generator[str, None, None]:
),
is_connected=is_connected_func,
):
if isinstance(packet, dict) and "top_documents" in packet:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this seems problematic, no? stream_chat_message yields strs not dicts?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes it does!

document_retrieval_latency = time.time() - start_time
logger.debug(f"First doc time: {document_retrieval_latency}")

yield json.dumps(packet) if isinstance(packet, dict) else packet

except Exception as e:
Expand Down