Skip to content

openai: apply instrumentation to beta.chat.Completions.parse #65

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 5 commits into from
Mar 17, 2025
Merged

openai: apply instrumentation to beta.chat.Completions.parse #65

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
27432ae
openai: apply instrumentation to beta.chat.Completions.parse
anuraaga Mar 14, 2025
576a123
Accidental
anuraaga Mar 14, 2025
4e7d994
Set min version
anuraaga Mar 14, 2025
4f6727b
Check version before patching
anuraaga Mar 14, 2025
39861f2
Check version before unwrap
anuraaga Mar 14, 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
20 changes: 18 additions & 2 deletions ...opentelemetry-instrumentation-openai/src/opentelemetry/instrumentation/openai/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,7 +99,9 @@ def _instrument(self, **kwargs):

register_post_import_hook(self._patch, "openai")

def _patch(self, _module):
def _patch(self, module):
version = tuple([int(x) for x in getattr(getattr(module, "version"), "VERSION").split(".")])
Copy link
Contributor Author

@anuraaga anuraaga Mar 14, 2025

Choose a reason for hiding this comment

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

Let me know if this is the sensible pattern for patching newer modules

Copy link
Member

@xrmx xrmx Mar 18, 2025 •
edited
Loading

Choose a reason for hiding this comment

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

You can use module.version.VERSION directly since you are not adding any default to getattr though.

Problem with this approach is when these would be promoted out of beta, I expect the version check will pass but the patching will fail. I think a more robust approach would be to try to wrap anyway and catch the ModuleNotFoundError and AttributeError exceptions and set the beta_chat_available boolean accordingly.

self.beta_chat_available = version >= (1, 40, 0)
wrap_function_wrapper(
"openai.resources.chat.completions",
"Completions.create",
Expand All @@ -110,6 +112,17 @@ def _patch(self, _module):
"AsyncCompletions.create",
self._async_chat_completion_wrapper,
)
if self.beta_chat_available:
wrap_function_wrapper(
"openai.resources.beta.chat.completions",
"Completions.parse",
self._chat_completion_wrapper,
)
wrap_function_wrapper(
"openai.resources.beta.chat.completions",
"AsyncCompletions.parse",
self._async_chat_completion_wrapper,
)
wrap_function_wrapper(
"openai.resources.embeddings",
"Embeddings.create",
Expand All @@ -128,11 +141,14 @@ def _uninstrument(self, **kwargs):

unwrap(openai.resources.chat.completions.Completions, "create")
unwrap(openai.resources.chat.completions.AsyncCompletions, "create")
if self.beta_chat_available:
unwrap(openai.resources.beta.chat.completions.Completions, "parse")
unwrap(openai.resources.beta.chat.completions.AsyncCompletions, "parse")
unwrap(openai.resources.embeddings.Embeddings, "create")
unwrap(openai.resources.embeddings.AsyncEmbeddings, "create")

def _chat_completion_wrapper(self, wrapped, instance, args, kwargs):
logger.debug(f"openai.resources.chat.completions.Completions.create kwargs: {kwargs}")
logger.debug(f"{wrapped} kwargs: {kwargs}")

span_attributes = _get_attributes_from_wrapper(instance, kwargs)
event_attributes = _get_event_attributes()
Expand Down
Loading