But it's still part of the same **FastAPI** application/web API (it's part of the same "Python Package").

You can create the *path operations* for that module using `APIRouter`.

### Import `APIRouter`

You import it and create an "instance" the same way you would with the class `FastAPI`:

```Python hl_lines="1  3" title="app/routers/users.py"

// CHECK: func.func @main(%[[ARG:.*]]: tensor<?x!tf_type.string>
// CHECK-SAME: tf_saved_model.index_path = ["serving_default_input_vocabs:0"]
// CHECK-SAME: -> (tensor<*xi64> {tf_saved_model.index_path = ["StatefulPartitionedCall:0"]})
// CHECK-SAME: tf.entry_function = {inputs = "serving_default_input_vocabs:0", outputs = "StatefulPartitionedCall:0"}
// CHECK-SAME: tf_saved_model.exported_names = ["main"]

			emon, epool, eimage := existingVolume.RBD.CephMonitors, existingVolume.RBD.RBDPool, existingVolume.RBD.RBDImage
			// two RBDs images are the same if they share the same Ceph monitor, are in the same RADOS Pool, and have the same image name
			// only one read-write mount is permitted for the same RBD image.
			// same RBD image mounted by multiple Pods conflicts unless all Pods mount the image read-only

  // CHECK: tfrt.while [[pred_0]]#1 @"while_body_add2/tfrt_body_10"
  // CHECK-SAME: parallel_iterations(10)
  // CHECK: [[pred_1:%.*]]:2 = tfrt.call @"while_cond_lt9/tfrt_predicate"
  // CHECK: tfrt.while [[pred_1]]#1 @"while_body_add2/tfrt_body_1"
  // CHECK-SAME: parallel_iterations(1)

   (IsConstTensor $input_zp),
   (IsConstTensor $filter),
   (IsInt32ElementType $conv),
   (HasStaticShapeConstraint $filter),
   (HasStaticShapeAtDimsConstraint<"3"> $input)],
  [], (addBenefit 10)>;

// Same as ConvertTFConv2DToXLAConvOp but handles the case where input zero
// point is dynaically calculated so not a constant.
def ConvertTFConv2DToXLAConvOpDynamicRange : Pat<
  (TF_Conv2DOp:$conv

  func.return
}

// -----

// Tests last resource assign is returned even when the original function
// returns the same value prior.

// CHECK-LABEL: func @main
// CHECK-SAME: %{{[a-z0-9]+}}: tensor<f32> {tf.aliasing_output = 1 : i64}
// CHECK-SAME: %arg1: tensor<i1>
// CHECK-SAME: -> (tensor<f32>, tensor<f32>)
func.func @main(%arg0: tensor<!tf_type.resource<tensor<f32>>>, %arg1: tensor<i1>) -> tensor<f32> {

  // CHECK: %[[VAL_1:.*]] = "tf.Identity"(%[[VAL_0]]) : (tensor<*xf32>) -> tensor<*xf32>

  func.return %2 : tensor<1x128x128x8xf32>

  // CHECK-LABEL: testDilatedConvWithNonZeroBasePadding
  // CHECK-SAME: ([[INPUT:%.*]]: tensor<1x128x128x3xf32>, [[FILTER:%.*]]: tensor<5x5x3x8xf32>)
  // CHECK-NEXT: [[RESULT:%.*]] = "tf.Conv2D"([[INPUT]], [[FILTER]]) <{dilations = [1, 2, 2, 1], padding = "SAME", strides = [1, 1, 1, 1]}> : (tensor<1x128x128x3xf32>, tensor<5x5x3x8xf32>) -> tensor<1x128x128x8xf32>

// CHECK:      %[[SHAPE:[0-9]*]] = "tf.Shape"(%[[ARG_0]])
// CHECK-NEXT: %[[LAUNCH_A:[0-9]*]] = "tf_device.launch"
// CHECK-SAME: device = "a"
// CHECK-NEXT:   %[[OP_A:[0-9]*]] = "tf.opA"(%[[SHAPE]])
// CHECK-NEXT:   tf_device.return %[[OP_A]]
// CHECK:      %[[LAUNCH_B:[0-9]*]] = "tf_device.launch"
// CHECK-SAME: device = "b"
// CHECK-NEXT:   %[[OP_B:[0-9]*]] = "tf.opB"(%[[SHAPE]], %[[LAUNCH_A]])
// CHECK-NEXT:   tf_device.return %[[OP_B]]

                verify(programHost).compileSecondStageOf(
                    same(program),
                    same(scriptHost),
                    argThat { this.sourceHash == sourceHash && this.templateId == scriptTemplateId },
                    same(ProgramKind.TopLevel),
                    same(programTarget),
                    same(accessorsClassPath)
                )

                verifyNoMoreInteractions()