Skip to content

fix: process Vertex AI response properly for usage #1173

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

Closed
t-miyak wants to merge 7 commits into from
Closed

fix: process Vertex AI response properly for usage #1173

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
47f0706
chore: upgrade langchain-google-vertexai
t-miyak Apr 24, 2025
9b97509
feat: remove unnecessary fields of response from VertexAI for usage
t-miyak Apr 24, 2025
7270a42
chore: remove langchain-google-vertexai from deps
t-miyak Apr 24, 2025
c1cf0da
chore: revert langchain-google-vertexai
t-miyak Apr 24, 2025
31c2bbb
chore: restore pyproject and poetry.lock
t-miyak Apr 24, 2025
1015813
feat: determine if the model is gemini more strictly
t-miyak Apr 26, 2025
653774a
test: fix test for VertexAI
t-miyak Apr 26, 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
12 changes: 12 additions & 0 deletions langfuse/callback/langchain.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1066,6 +1066,7 @@ def _parse_usage_model(usage: typing.Union[pydantic.BaseModel, dict]):
# https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/get-token-count
("prompt_token_count", "input"),
("candidates_token_count", "output"),
("total_token_count", "total"),
# Bedrock: https://docs.aws.amazon.com/bedrock/latest/userguide/monitoring-cw.html#runtime-cloudwatch-metrics
("inputTokenCount", "input"),
("outputTokenCount", "output"),
Expand Down Expand Up @@ -1114,6 +1115,17 @@ def _parse_usage_model(usage: typing.Union[pydantic.BaseModel, dict]):
if "output" in usage_model:
usage_model["output"] = max(0, usage_model["output"] - value)

# For VertexAI, the usage model has non integer values that are not necessary for the usage, so remove them.
# ref. https://cloud.google.com/vertex-ai/generative-ai/docs/reference/rpc/google.cloud.aiplatform.v1#google.cloud.aiplatform.v1.GenerateContentResponse.UsageMetadata
for key in [
"prompt_tokens_details",
"candidates_tokens_details",
"cache_tokens_details",
]:
if key in usage_model:
if isinstance(usage_model[key], list):
del usage_model[key]

return usage_model if usage_model else None


Expand Down
Loading