Lightning-AI/pytorch-lightning · error · Exception

Your provided payload {payload} should have a field named "b

Error message

Your provided payload {payload} should have a field named "body".

What it means

After the server is up, the validator calls model.configure_payload() and POSTs it to /serve. The serving protocol requires the payload to contain a top-level "body" field; if it is missing, a generic Exception is raised before the request is sent.

Source

Thrown at src/lightning/pytorch/serve/servable_module_validator.py:117

        process.start()

        servable_module.trainer = trainer

        ready = False
        t0 = time.time()
        while not ready:
            with contextlib.suppress(requests.exceptions.ConnectionError):
                resp = requests.get(f"http://{self.host}:{self.port}/ping")
                ready = resp.status_code == 200
            if time.time() - t0 > self.timeout:
                process.kill()
                raise Exception(f"The server didn't start within {self.timeout} seconds.")
            time.sleep(0.1)

        payload = servable_module.configure_payload()

        if "body" not in payload:
            raise Exception(f'Your provided payload {payload} should have a field named "body".')

        self.resp = requests.post(f"http://{self.host}:{self.port}/serve", json=payload)
        process.kill()

        if is_overridden("configure_response", servable_module, ServableModule):
            response = servable_module.configure_response()
            if self.resp.json() != response:
                raise Exception(f"The expected response {response} doesn't match the generated one {self.resp.json()}.")

        if self.exit_on_failure and not self.successful:
            raise MisconfigurationException("The model isn't servable. Investigate the traceback and try again.")

        if self.successful:
            _logger.info(f"Your model is servable and the received payload was {self.resp.json()}.")

    @property
    def successful(self) -> Optional[bool]:
        """Returns whether the model was successfully served."""

View on GitHub (pinned to 9fed5c27d2)

Solutions

1. Wrap your inputs under a "body" key in configure_payload: return {"body": {...}}
2. Make sure keys inside "body" match the input deserializer names from configure_serialization

Example fix

// before
def configure_payload(self):
    return {"x": [1.0, 2.0]}
// after
def configure_payload(self):
    return {"body": {"x": [1.0, 2.0]}}

payload = model.configure_payload()
assert isinstance(payload, dict) and "body" in payload, \
    f'configure_payload must return {{"body": ...}}, got {payload}'

def valid_payload(p) -> bool:
    return isinstance(p, dict) and "body" in p and isinstance(p["body"], dict)

When it happens

Trigger: configure_payload returns a flat dict like {"x": ...} instead of {"body": {"x": ...}}, or returns the raw tensor/list payload without wrapping.

Common situations: Writing the payload by trial without reading the ServableModule contract; changing payload shape after adding new inputs and dropping the wrapper.

Related errors

• The `configure_payload` method needs to be overridden.
• The `configure_serialization` method needs to be overridden.
• The `serve_step` method needs to be overridden.
• The server didn't start within {self.timeout} seconds.
• The expected response {response} doesn't match the generated

AI-assisted analysis of Lightning-AI/pytorch-lightning@9fed5c27d2 (2026-08-28). Data as JSON: /api/errors/2ee6104319909e05. Report an issue: GitHub.