# ONNXRuntime **`class ONNXRuntime(config)`** Bases: [`Runtime`](squirro.lib.nlp.steps.runtimes.Runtime.md#squirro.lib.nlp.steps.runtimes.Runtime) Step that process data using models in the ONNX format ([https://onnx.ai/](https://onnx.ai/)). **Input** - the input fields need to be of type that is expected by the provided model. **Output** - the output fields depend on the provided model and the data it returns. Parameters - `type` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)) – onnx - `model` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)) – Model location - `input_mapping` ([`dict`](https://docs.python.org/3.11/library/stdtypes.html#dict)) – dictionary of input fields mapping: name of the model input to the document input field - `output_mapping` ([`dict`](https://docs.python.org/3.11/library/stdtypes.html#dict)) – dictionary of output fields mapping: name of the model output to the document output field **Example** ```json { "step": "runtime", "type": "onnx", "model": "/models/test-model.onnx", "input_mapping": { "input": "query" }, "output_mapping": { "output_label": "query_class", "output_probability": "query_probability" } } ``` Methods SummaryMethods Documentation **`pre_session_hook()`** Pre-session hook that is executed before creating an inference session. It can be overwritten by subclasses to perform custom operations e.g. downloading model. Return type [`None`](https://docs.python.org/3.11/library/constants.html#None) **`process_batch(batch)`** Process a batch of documents. If not defined will default to using self.process_doc for each document in the batch. Parameters `batch` ([`list`](https://docs.python.org/3.11/library/stdtypes.html#list)`(`[`Document`](../technical/libnlp/base.md#squirro.lib.nlp.document.Document)`)`) – List of documents Returns List of processed documents Return type [list](https://docs.python.org/3.11/library/stdtypes.html#list)([Document](../technical/libnlp/base.md#squirro.lib.nlp.document.Document))