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: OpenAI prompt details and completion tokens details missing from total usage #1105

Merged
merged 5 commits into from
Nov 8, 2024
Merged

fix: OpenAI prompt details and completion tokens details missing from total usage #1105

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
60d549a
prompt details and completion tokens details
ivanbelenky Oct 21, 2024
e3efd03
Merge branch 'main' into hf/1104
ivanbelenky Oct 21, 2024
df07c39
Merge branch 'main' into hf/1104
ivanbelenky Oct 23, 2024
821afdf
Merge branch 'main' into hf/1104
ivanbelenky Oct 28, 2024
9c3683a
Merge branch 'main' into hf/1104
ivanleomk Nov 8, 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
7 changes: 5 additions & 2 deletions instructor/retry.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@
from instructor.utils import update_total_usage
from instructor.validators import AsyncValidationError
from openai.types.chat import ChatCompletion
from openai.types.completion_usage import CompletionUsage
from openai.types.completion_usage import CompletionUsage, CompletionTokensDetails, PromptTokensDetails
from pydantic import BaseModel, ValidationError
from tenacity import (
AsyncRetrying,
Expand Down Expand Up @@ -71,7 +71,10 @@ def initialize_usage(mode: Mode) -> CompletionUsage | Any:
Returns:
CompletionUsage | Any: Initialized usage object.
"""
total_usage = CompletionUsage(completion_tokens=0, prompt_tokens=0, total_tokens=0)
total_usage = CompletionUsage(completion_tokens=0, prompt_tokens=0, total_tokens=0,
completion_tokens_details = CompletionTokensDetails(audio_tokens=0, reasoning_tokens=0),
prompt_token_details = PromptTokensDetails(audio_tokens=0, cached_tokens=0)
)
if mode in {Mode.ANTHROPIC_TOOLS, Mode.ANTHROPIC_JSON}:
from anthropic.types import Usage as AnthropicUsage

Expand Down
6 changes: 6 additions & 0 deletions instructor/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -140,6 +140,12 @@ def update_total_usage(
total_usage.completion_tokens += response_usage.completion_tokens or 0
total_usage.prompt_tokens += response_usage.prompt_tokens or 0
total_usage.total_tokens += response_usage.total_tokens or 0
if (rtd := response_usage.completion_tokens_details) and (ttd := total_usage.completion_tokens_details):
ttd.audio_tokens = (ttd.audio_tokens or 0) + (rtd.audio_tokens or 0)
ttd.reasoning_tokens = (ttd.reasoning_tokens or 0) + (rtd.reasoning_tokens or 0)
if (rpd := response_usage.prompt_tokens_details) and (tpd := total_usage.prompt_tokens_details):
tpd.audio_tokens = (tpd.audio_tokens or 0) + (rpd.audio_tokens or 0)
tpd.cached_tokens = (tpd.cached_tokens or 0) + (rpd.cached_tokens or 0)
response.usage = total_usage # Replace each response usage with the total usage
return response

Expand Down