Skip to content

fix(vertex-ai-langchain): token count parsing #1181

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
hassiebp merged 2 commits into from
May 6, 2025
Merged

fix(vertex-ai-langchain): token count parsing #1181

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1065560
fix(vertex-ai-langchain): token count parsing
hassiebp May 6, 2025
afd0896
Merge branch 'main' into fix-vertexai-token-usage
hassiebp May 6, 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
48 changes: 48 additions & 0 deletions langfuse/callback/langchain.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1125,6 +1125,54 @@ def _parse_usage_model(usage: typing.Union[pydantic.BaseModel, dict]):
if "output" in usage_model:
usage_model["output"] = max(0, usage_model["output"] - value)

# Vertex AI
if "prompt_tokens_details" in usage_model and isinstance(
usage_model["prompt_tokens_details"], list
):
prompt_tokens_details = usage_model.pop("prompt_tokens_details")

for item in prompt_tokens_details:
if (
isinstance(item, dict)
and "modality" in item
and "token_count" in item
):
usage_model[f"input_modality_{item['modality']}"] = item[
"token_count"
]

# Vertex AI
if "candidates_tokens_details" in usage_model and isinstance(
usage_model["candidates_tokens_details"], list
):
candidates_tokens_details = usage_model.pop("candidates_tokens_details")

for item in candidates_tokens_details:
if (
isinstance(item, dict)
and "modality" in item
and "token_count" in item
):
usage_model[f"output_modality_{item['modality']}"] = item[
"token_count"
]

# Vertex AI
if "cache_tokens_details" in usage_model and isinstance(
usage_model["cache_tokens_details"], list
):
cache_tokens_details = usage_model.pop("cache_tokens_details")

for item in cache_tokens_details:
if (
isinstance(item, dict)
and "modality" in item
and "token_count" in item
):
usage_model[f"cached_modality_{item['modality']}"] = item[
"token_count"
]

return usage_model if usage_model else None


Expand Down
Loading