Skip to content

Add system_prompt param to GeneralLLM.invoke function #191

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
CodexVeritas merged 1 commit into from
Jan 20, 2026
Merged

Add system_prompt param to GeneralLLM.invoke function #191

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
10 changes: 6 additions & 4 deletions forecasting_tools/ai_models/general_llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -231,21 +231,23 @@ def __init__(

ModelTracker.give_cost_tracking_warning_if_needed(self._litellm_model)

async def invoke(self, prompt: ModelInputType) -> str:
async def invoke(self, prompt: ModelInputType, system_prompt: str | None = None) -> str:
response: TextTokenCostResponse = (
await self._invoke_with_request_cost_time_and_token_limits_and_retry(prompt)
await self._invoke_with_request_cost_time_and_token_limits_and_retry(prompt, system_prompt=system_prompt)
)
data = response.data
return data

@RetryableModel._retry_according_to_model_allowed_tries
async def _invoke_with_request_cost_time_and_token_limits_and_retry(
self, prompt: ModelInputType
self, prompt: ModelInputType, system_prompt: str | None = None
) -> Any:
logger.debug(f"Invoking model with prompt: {prompt}")

prompt = self.model_input_to_message(prompt, system_prompt)

with track_generation(
input=self.model_input_to_message(prompt),
input=prompt,
model=self.model,
) as span:
direct_call_response = await self._mockable_direct_call_to_model(prompt)
Expand Down
Loading