# Tutorial - Pedoman Pengguna - Pengenalan

Tutorial ini menunjukan cara menggunakan ***FastAPI*** dengan semua fitur-fiturnya, tahap demi tahap.

Setiap bagian dibangun secara bertahap dari bagian sebelumnya, tetapi terstruktur untuk memisahkan banyak topik, sehingga kamu bisa secara langsung menuju ke topik spesifik untuk menyelesaikan kebutuhan API tertentu.

Ini juga dibangun untuk digunakan sebagai referensi yang akan datang.

Das kann nützlich sein, wenn Sie beispielsweise in einem Land leben, in dem bestimmte URLs eingeschränkt sind.

### Die automatischen Dokumentationen deaktivieren

Der erste Schritt besteht darin, die automatischen Dokumentationen zu deaktivieren, da diese standardmäßig das Standard-CDN verwenden.

Um diese zu deaktivieren, setzen Sie deren URLs beim Erstellen Ihrer `FastAPI`-App auf `None`:

```Python hl_lines="8"

  %0 = "tf.ReadVariableOp"(%arg0) {_output_shapes = ["tfshape$dim { size: 1 } dim { size: 3 }"], device = "/device:CPU:0", dtype = !tf_type.quint8} : (tensor<!tf_type.resource<tensor<1x3x!tf_type.quint8>>>) -> tensor<1x3x!tf_type.quint8>

  // CHECK: tf.ReadVariableOp
  // CHECK-SAME: dtype = !corert.quint16

  %2 = "tf.MatMul"(%arg0, %1) {T = f32, _output_shapes = ["tfshape$dim { size: 3 } dim { size: 3 }"], device = "/device:CPU:0", transpose_a = false, transpose_b = false} : (tensor<3x1xf32>, tensor<1x3xf32>) -> tensor<3x3xf32>
  // CHECK-NEXT: [[r1:%.*]] = tfrt_fallback_async.executeop {{.*}} "tf.BiasAdd"([[r0]], [[result]])

  op: "Placeholder"
  attr {
    key: "dtype"
    value {
      type: DT_FLOAT
    }
  }
  attr {
    key: "shape"
    value {
      shape {
        dim {
          size: 2
        }
        dim {
          size: 5
        }
        dim {
          size: 3
        }
      }
    }
  }
}
node {
  name: "Placeholder_1"
  op: "Placeholder"
  attr {
    key: "dtype"
    value {

  llvm::SmallVector<bool, 4> is_reduce_dim(rank, false);
  for (const APInt &index : indices.getValues<APInt>()) {
    int64_t dim = GetDimForAxis(index.getSExtValue(), rank);
    // Invalid input.
    if (dim < 0 || dim >= rank) return UnrankedTensorType::get(element_ty);

    if (!is_reduce_dim[dim]) {
      is_reduce_dim[dim] = true;
      num_reduce_dim++;
    }
  }

  ArrayRef<int64_t> shape = ranked_ty.getShape();

    // Collect non-unit dims and corresponding dim in the input shape.
    SmallVector<int64_t, 4> input_carryover_dims;
    SmallVector<int64_t, 4> non_unit_dims;

    for (int i = 0; i < input_shape_extended.size(); i++) {
      int64_t dim = broadcast_shape[i];
      if (dim != 1) {
        non_unit_dims.push_back(dim);
        input_carryover_dims.push_back(input_shape_extended[i]);
      }
    }

      -> (tensor<3x3xf32> {tf_saved_model.index_path = []}) {
  // CHECK: {{%.*}} = corert.get_op_handler %arg0 "/device:GPU:0"
  %2 = "tf.MatMul"(%arg0, %arg1) {T = f32, _output_shapes = ["tfshape$dim { size: 3 } dim { size: 3 }"], device = "/device:GPU:0", transpose_a = false, transpose_b = false} : (tensor<3x1xf32>, tensor<1x3xf32>) -> tensor<3x3xf32>
  func.return %2 : tensor<3x3xf32>

    }

    auto op_count_map = op_dtype_count_[op_with_dialect_name];
    if (!op_count_map.empty()) {
      std::string delim;
      *os_ << "  (";
      for (const auto &[dtype, cnt] : op_count_map) {
        *os_ << delim << absl::StrFormat("%s: %d", dtype, cnt);
        delim = ", ";
      }
      *os_ << ")";
    }
    *os_ << "\n";
  }
}

}  // namespace odml
}  // namespace mlir

template <typename ShapeContainerT>
void SetTensorShapeProto(ShapeContainerT shape, TensorShapeProto* proto) {
  if (shape.hasRank()) {
    for (int64_t dim : shape.getShape()) {
      proto->add_dim()->set_size(mlir::ShapedType::isDynamic(dim) ? -1 : dim);
    }
  } else {
    proto->set_unknown_rank(true);
  }
}

// Sets shape attribute with the given name. If the attribute already exists