```json
{
    "detail": [
        {
            "type": "extra_forbidden",
            "loc": ["body", "extra"],
            "msg": "Extra inputs are not permitted",
            "input": "Mr. Poopybutthole"
        }
    ]
}
```

## Summary

// capture some inputs and then add a node in the graph. The output tensors are
// returned through the provided TF_OutputList.
// Any active tape will observe the effects of this execution.
void TF_ExecuteOperation(TF_AbstractOp* op, int num_inputs,
                         TF_AbstractTensor* const* inputs, TF_OutputList* o,
                         TF_Status* s);

      TF_GraphToFunction(
          /* fn_body */ body.get(), /* fn_name */ function_name,
          /* append_hash_to_fn_name */ 0, /* num_opers */ 2,
          /* opers */ operations, /* ninputs */ 1, /* inputs */ &x,
          /* noutputs */ 1, /* outputs */ &y, /* output_names */ &output_name,
          /* opts */ nullptr, /* description */ "", /* status */ status),
      TF_DeleteFunction);

                "detail": [
                    {
                        "type": "extra_forbidden",
                        "loc": ["cookie", "extra"],
                        "msg": "Extra inputs are not permitted",
                        "input": "track-me-here-too",
                    }
                ]
            }
        )
        | IsDict(
            # TODO: remove when deprecating Pydantic v1
            {

// TPUReplicatedInput and TPUReplicatedOutput respectively. For example, with
// two component devices, running `x = TPUReplicatedInput(inputs=[a, b])` on the
// parallel device creates a parallel tensor `x` with `a` on the first of
// `underlying_devices` and `b` on the second. Running `a_unpacked, b_unpacked =
// TPUReplicatedOutput(input=x, num_replicas=2)` un-packs the parallel tensor
// into its components.
//

                IsDict(
                    {
                        "type": "extra_forbidden",
                        "loc": ["header", "tool"],
                        "msg": "Extra inputs are not permitted",
                        "input": "plumbus",
                    }
                )
                | IsDict(
                    # TODO: remove when deprecating Pydantic v1
                    {

@ElementTypesAreNonnullByDefault
public interface Interner<E> {
  /**
   * Chooses and returns the representative instance for any of a collection of instances that are
   * equal to each other. If two {@linkplain Object#equals equal} inputs are given to this method,
   * both calls will return the same instance. That is, {@code intern(a).equals(a)} always holds,
   * and {@code intern(a) == intern(b)} if and only if {@code a.equals(b)}. Note that {@code

    TFE_TensorHandle* input = TFE_OpGetFlatInput(original_op, j, s);
    if (TF_GetCode(s) != TF_OK) return;
    const char* input_device = TFE_TensorHandleDeviceName(input, s);
    if (TF_GetCode(s) != TF_OK) return;
    if (dev->device_name == input_device) {
      LoggedTensor* t = reinterpret_cast<LoggedTensor*>(
          TFE_TensorHandleDevicePointer(input, s));
      if (TF_GetCode(s) != TF_OK) return;

					Signature: [4]byte{2, 1, 1, 1},
					Type:      ObjectType,
					Flags:     0,
				}},
			},
		},
	}
	inputSerialized := make([]metaCacheEntry, len(inputs))
	for i, xl := range inputs {
		xl.sortByModTime()
		var err error
		entry := metaCacheEntry{
			name: "testobject",
		}
		entry.metadata, err = xl.AppendTo(nil)
		if err != nil {
			t.Fatal(err)
		}

```json
{
    "detail": [
        {
            "type": "extra_forbidden",
            "loc": ["query", "tool"],
            "msg": "Extra inputs are not permitted",
            "input": "plumbus"
        }
    ]
}
```

## Resumo

Você pode utilizar **modelos Pydantic** para declarar **parâmetros de consulta** no **FastAPI**. 😎

/// tip | Dica