BerriAI/litellm · error · Exception

\033[91m wandb not installed, try running 'pip install wandb

Error message

\033[91m wandb not installed, try running 'pip install wandb' to fix this error\033[0m

What it means

Error "\033[91m wandb not installed, try running 'pip install wandb' to fix this error\033[0m" thrown in BerriAI/litellm.

Source

Thrown at litellm/integrations/weights_biases.py:179

except Exception:
    imported_openAIResponse = False


#### What this does ####
#    On success, logs events to Langfuse
import traceback


class WeightsBiasesLogger:
    # Class variables or attributes
    def __init__(self):
        try:
            pass
        except Exception:
            raise Exception("\033[91m wandb not installed, try running 'pip install wandb' to fix this error\033[0m")
        if imported_openAIResponse is False:
            raise Exception("\033[91m wandb not installed, try running 'pip install wandb' to fix this error\033[0m")
        self.resolver = OpenAIRequestResponseResolver()

    def log_event(self, kwargs, response_obj, start_time, end_time, print_verbose):
        # Method definition
        import wandb

        try:
            print_verbose(f"W&B Logging - Enters logging function for model {kwargs}")
            run: Final = wandb.init()
            print_verbose(response_obj)

            trace: Final = self.resolver(kwargs, response_obj, (end_time - start_time).total_seconds())

            if trace is not None and run is not None:
                run.log({"trace": trace})

            if run is not None:
                run.finish()

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Install wandb: pip install wandb.

When it happens

Trigger: Thrown at litellm/integrations/weights_biases.py:179 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/1d4a450e2f9e410f. Report an issue: GitHub.