Nils Lindemann <******@****.***> 1711821718 +0100

So, a Python class is also a **callable**.

Then, in **FastAPI**, you could use a Python class as a dependency.

What FastAPI actually checks is that it is a "callable" (function, class or anything else) and the parameters defined.

If you pass a "callable" as a dependency in **FastAPI**, it will analyze the parameters for that "callable", and process them in the same way as the parameters for a *path operation function*. Including sub-dependencies.

# RUN: tf-mlir-translate -graphdef-to-mlir -tf-enable-shape-inference-on-import=false %s -tf-graph-as-function -tf-xla-compile-device-type="GPU" -tf-enable-soft-placement-on-import=true -o - | FileCheck %s

# Verify main graph was converted to a function, args/rets are mapped correctly,
# and ops in the main graph are retained. In addition, check if subsequent
# functions are converted.

// RUN: tf-mlir-translate -mlir-to-graphdef %s -tf-graph-as-function -o - | FileCheck %s

func.func @main(%arg0: tensor<*x!tf_type.resource>, %arg1: tensor<*x!tf_type.resource<tensor<3x3x1x32xf32>>>, %arg2: tensor<*xf32>, %arg3: tensor<2x4x6x8xi32>) -> (tensor<f32>, tensor<f32>)
attributes {tf.entry_function = {inputs = "args_0,args_1,args_2,args_3", outputs = "rets_0_RetVal,rets_1_RetVal"}} {
  %graph:2 = tf_executor.graph {

Aleksandr Andrukhov <******@****.***> 1705057939 +0300

LeeeeT <******@****.***> 1680341164 +0300

Kani Kim <******@****.***> 1707659311 +0900

SwftAlpc <******@****.***> 1705334896 +0900

A. Unique TensorFlower <******@****.***> 1621903882 -0700

Andy Ly <******@****.***> 1591818565 -0700