Skip to content
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

Fix BaseOpenAIChatCompletionClient token usage #4770

Merged
merged 6 commits into from
Dec 30, 2024
+4 −4
Merged

Fix BaseOpenAIChatCompletionClient token usage #4770

Changes from 1 commit
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
f9cf23a
Fix openai client token usage (#4769)
gziz Dec 20, 2024
0136055
Include actual_usage in add_usage function
gziz Dec 26, 2024
813029c
Merge branch 'main' into fix_client_token_track
gziz Dec 26, 2024
50c2618
Merge branch 'main' into fix_client_token_track
jackgerrits Dec 30, 2024
a940f73
Make sure result is assigned
jackgerrits Dec 30, 2024
ef95ece
remove method
jackgerrits Dec 30, 2024
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
19 changes: 8 additions & 11 deletions python/packages/autogen-ext/src/autogen_ext/models/openai/_openai_client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -285,13 +285,6 @@ def calculate_vision_tokens(image: Image, detail: str = "auto") -> int:
return total_tokens


def _add_usage(usage1: RequestUsage, usage2: RequestUsage) -> RequestUsage:
return RequestUsage(
prompt_tokens=usage1.prompt_tokens + usage2.prompt_tokens,
completion_tokens=usage1.completion_tokens + usage2.completion_tokens,
)


def convert_tools(
tools: Sequence[Tool | ToolSchema],
) -> List[ChatCompletionToolParam]:
Expand Down Expand Up @@ -561,8 +554,7 @@ async def create(
logprobs=logprobs,
)

_add_usage(self._actual_usage, usage)
jackgerrits marked this conversation as resolved.
Show resolved Hide resolved
_add_usage(self._total_usage, usage)
self.add_usage(usage)

# TODO - why is this cast needed?
return response
Expand Down Expand Up @@ -778,8 +770,7 @@ async def create_stream(
logprobs=logprobs,
)

_add_usage(self._actual_usage, usage)
_add_usage(self._total_usage, usage)
self.add_usage(usage)

yield result

Expand Down Expand Up @@ -886,6 +877,12 @@ def remaining_tokens(self, messages: Sequence[LLMMessage], tools: Sequence[Tool
def capabilities(self) -> ModelCapabilities:
return self._model_capabilities

def add_usage(self, usage: RequestUsage) -> None:
self._total_usage = RequestUsage(
prompt_tokens=self._total_usage.prompt_tokens + usage.prompt_tokens,
completion_tokens=self._total_usage.completion_tokens + usage.completion_tokens,
)


class OpenAIChatCompletionClient(BaseOpenAIChatCompletionClient):
"""Chat completion client for OpenAI hosted models.
Expand Down
Loading