Skip to content

feat: use Gemini response metadata for token counting #11743

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
Dec 17, 2024
Merged

feat: use Gemini response metadata for token counting #11743

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
2a8b931
feat: use Gemini response metadata for token counting
totsukash Dec 17, 2024
76445b8
fix: add attribute check
totsukash Dec 17, 2024
9d904a3
refactor: replace single quotes with double quotes
totsukash Dec 17, 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
8 changes: 6 additions & 2 deletions api/core/model_runtime/model_providers/google/llm/llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -317,8 +317,12 @@ def _handle_generate_stream_response(
)
else:
# calculate num tokens
prompt_tokens = self.get_num_tokens(model, credentials, prompt_messages)
completion_tokens = self.get_num_tokens(model, credentials, [assistant_prompt_message])
if hasattr(response, "usage_metadata") and response.usage_metadata:
prompt_tokens = response.usage_metadata.prompt_token_count
completion_tokens = response.usage_metadata.candidates_token_count
else:
prompt_tokens = self.get_num_tokens(model, credentials, prompt_messages)
completion_tokens = self.get_num_tokens(model, credentials, [assistant_prompt_message])

# transform usage
usage = self._calc_response_usage(model, credentials, prompt_tokens, completion_tokens)
Expand Down
Loading