Input Schema

You have to define the input_schema.py in your GitHub/Gitlab repository this will help us create the Input parameters :

For each input, there are 3 fields required

  • datatype: “STRING”, “BOOL”, “INT8”, “INT16”, “INT32”, “FP16” “FP32”, “UINT8”, “UINT16”, “UINT32”, “UINT64”, “INT64” , “FP64” , “BYTES”, “BF16”

  • shape: The length of the array, If the shape is [1] you will get the variable, if the array > 1 you will get an array, If the length is variable you can put -1

  • required: If the parameter is required in all API calls

  • example( optional ): Sample value for calling the API

In code

def infer(self, inputs):
    prompt = inputs["prompt"] # "There is a fine house in the forest"
    shape = inputs["shape"] # [ 512,1 ]

In input_schema.py

Example
INPUT_SCHEMA = {
    "prompt": {
        'datatype': 'STRING',
        'required': True,
        'shape': [1],
        'example': ["There is a fine house in the forest"]
    },
    'shape': {
        'datatype': 'INT8',
        'required': False,
        'example': [ 512, 1 ],
        'shape': [2]
    },
}

Output Schema

You can return any dictionary in the return statement of app.py. You don’t need to provide any configuration.

Returning Dicts

# Example Return Statement 

return { "label_1" : 0.398 , "label_2" : 0.563, "label_3" : 0.434 }

Returning Variable Length Array

# Example Return Statement 
return { "generated_images_base64" : [ img_str1 , img_str2 , img_str3 ] }

Returning Dictionary with Variable keys

# Example Return Statement 
dict = {"label_x": 0.4554 , "label_y", 0.3232 }
return { "result": json.dumps(dict) }

Depreciated - Input / Output Json

Sample Input

The input JSON should contain the following fields:

  1. name - the name should match the name of the input/output that is specified in the model

  2. shape - the shape of the input array for the model. if the shape is variable use -1

  3. datatype - One of the formats is given below:

BOOL, UINT8, UINT16, UINT32, UINT64, INT8, INT16, INT32, INT64, FP16, FP32, FP64, BYTES, BF16.
For more details, you can view the matrix below the page

  1. data - An example of the data.

Note: Since an Array of Inputs and Outputs is expected, you may have to convert the dimension of your array with an additional dimension of no of requests.

An example of a model that takes attention_mask and input_ids Tensor Arrays of shape [10] for 1 Request will be

Sample of an inputjson
{ "inputs" : 
    [
        {
            "name": "attention_mask",
            "shape": [1,10],
            "datatype": "INT64",
            "data":  [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1]]
        },
        {
    	    "name": "input_ids",
    	    "shape": [1,10],
    	    "datatype": "INT64",
    	    "data":  [[3041, 5372, 502, 416, 597, 2420, 345, 1549, 588, 13]]
        }
    ]
}

Example of a Model that takes prompt (as string) as the input ( Stable Diffusion )

Sample of a inputjson

{ "inputs" : 
  [
      {
        "name": "prompt",
        "shape": [
          1
        ],
        "datatype": "BYTES",
        "data": [
          "Once upon a time"
        ]
      }
  ]
}

Example of Model using the Param

// Code to take the input var in the infer function. 
def infer(self, inputs):
    prompt = inputs["prompt"]

Sample Output

There is the output field that your model returns, Having a sample helps us validate that the name you are expecting in output is generated by the model.

Sample of Output json
{ "outputs" : 
  [
      {
        "name": "generated_text",
        "shape": [
          1
        ],
        "datatype": "BYTES",
        "data": [
          "Sample Output"
        ]
      }
  ]
}

Returning Dicts

# Example Return Statement 

return { "label_1" : 0.398 , "label_2" : 0.563, "label_3" : 0.434 }

Corresponding Output.json for the Python code

// Sample

{
  "outputs": [
    {
      "name": "label_1",
      "shape": [
        1
      ],
      "datatype": "FP64",
      "data": [
        "Sample Output"
      ]
    },
    {
      "name": "label_2",
      "shape": [
        1
      ],
      "datatype": "FP64",
      "data": [
        "Sample Output"
      ]
    },
    {
      "name": "label_3",
      "shape": [
        1
      ],
      "datatype": "FP64",
      "data": [
        "Sample Output"
      ]
    }
  ]
}

Returning Variable Length Array

# Example Return Statement 
return { "generated_images_base64" : [ img_str1 , img_str2 , img_str3 ] }

Corresponding Output.json for the Python code, Making the Shape parameter -1 will allow variable length items

// Sample
{
    "outputs": [
        {
            "data": [
                "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"
            ],
            "name": "generated_image_base64",
            "shape": [
                -1
            ],
            "datatype": "BYTES"
        }
    ]
}

Returning Dictionary with Variable keys

# Example Return Statement 
# dict = {"label_x": 0.4554 , "label_y", 0.3232 }
return { "result": json.dumps(dict) }

Corresponding Output.json for the Python code

// Sample
{
    "outputs": [
        {
            "data": [ "Sample" ],
            "name": "result",
            "shape": [
                1
            ],
            "datatype": "BYTES"
        }
    ]
}

Example

Below is a representation after giving the details during model import.