8000 Add support for response_cost for LiteLLM model for non streaming response by thetushargoyal · Pull Request #198 · google/adk-python · GitHub
[go: up one dir, main page]
Skip to content

Add support for response_cost for LiteLLM model for non streaming response #198

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
wants to merge 4 commits into from
Closed

Add support for response_cost for LiteLLM model for non streaming response #198

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
4fc79af
added support for response_cost for LiteLLM model for non streaming r…
thetushargoyal Apr 14, 2025
0104e57
Merge branch 'main' into main
thetushargoyal Apr 15, 2025
c699d20
Update lite_llm.py
thetushargoyal Apr 15, 2025
a781446
Merge branch 'google:main' into main
thetushargoyal Apr 24, 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
Next Next commit
added support for response_cost for LiteLLM model for non streaming r… 
…esponses
  • Loading branch information
@thetushargoyal
thetushargoyal committed Apr 14, 2025
commit 4fc79af2fb89f635e64372992c74c4d2c7aef913
16 changes: 12 additions & 4 deletions src/google/adk/models/lite_llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -391,11 +391,17 @@ def _model_response_to_generate_content_response(

if not message:
raise ValueError("No message in response")
return _message_to_generate_content_response(message)

response_cost = None
if hasattr(response, "_hidden_params") and isinstance(response._hidden_params, dict):
response_cost = response._hidden_params.get("response_cost")
response_cost = response_cost*86

return _message_to_generate_content_response(message, response_cost=response_cost)


def _message_to_generate_content_response(
message: Message, is_partial: bool = False
message: Message, is_partial: bool = False, response_cost: float = None
) -> LlmResponse:
"""Converts a litellm message to LlmResponse.

Expand All @@ -422,7 +428,9 @@ def _message_to_generate_content_response(
parts.append(part)

return LlmResponse(
content=types.Content(role="model", parts=parts), partial=is_partial
content=types.Content(role="model", parts=parts),
partial=is_partial,
response_cost=response_cost
)


Expand Down Expand Up @@ -596,7 +604,7 @@ async def generate_content_async(
LlmResponse: The model response.
"""

logger.info(_build_request_log(llm_request))
# logger.info(_build_request_log(llm_request))

messages, tools = _get_completion_inputs(llm_request)

Expand Down
1 change: 1 addition & 0 deletions src/google/adk/models/llm_response.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,6 +70,7 @@ class LlmResponse(BaseModel):
"""Flag indicating that LLM was interrupted when generating the content.
Usually it's due to user interruption during a bidi streaming.
"""
response_cost: Optional[float] = None

@staticmethod
def create(
Expand Down
0