name: "preprocessing"
backend: "python"
max_batch_size: 1

input [
    {
        name: "QUERY"
        data_type: TYPE_STRING
        dims: [ -1 ]
    },
    {
        name: "BAD_WORDS_DICT"
        data_type: TYPE_STRING
        dims: [ -1 ]
        optional: true
    },
    {
        name: "STOP_WORDS_DICT"
        data_type: TYPE_STRING
        dims: [ -1 ]
        optional: true
    },
    {
        name: "REQUEST_OUTPUT_LEN"
        data_type: TYPE_UINT32
        dims: [ -1 ]
    }
]
output [
    {
        name: "INPUT_ID"
        data_type: TYPE_UINT32
        dims: [ -1 ]
    },
    {
        name: "REQUEST_INPUT_LEN"
        data_type: TYPE_UINT32
        dims: [ 1 ]
    },
    {
        name: "BAD_WORDS_IDS"
        data_type: TYPE_INT32
        dims: [ 2, -1 ]
    },
    {
        name: "STOP_WORDS_IDS"
        data_type: TYPE_INT32
        dims: [ 2, -1 ]
    },
    {
        name: "REQUEST_OUTPUT_LEN"
        data_type: TYPE_UINT32
        dims: [ -1 ]
    },
    {
        name: "PROMPT_LEARNING_TASK_NAME_IDS"
        data_type: TYPE_UINT32
        dims: [ 1 ]
    }
]

instance_group [
    {
        count: 4
        kind: KIND_CPU
    }
]

parameters {
  key: "tokenizer_path"
  value: {
    string_value: "tokenizer/tokenizer.model"
  }
}