Input Data Mapping

Input data mapping allows explicit mapping of values for the inputs of the next step. These values can come from a number of sources:

The outputs of a previous step
The runtime context
A constant value
The initial input of the workflow

Map

In this example the output from cityCoordinatesStep is transformed to match the inputSchema required for the locationDetailsStep. The values from the cityCoordinatesStep are available using the inputData parameter of the .map function.

src/mastra/workflows/test-workflow.ts


const cityCoordinatesStep = createStep({
  id: "city-step",
  description: "Gets details about a city",
  inputSchema: z.object({
    city: z.string()
  }),
  outputSchema: z.object({
    city_name: z.string(),
    country_name: z.string(),
    country_timezone: z.string()
  }),
  execute: async ({ inputData }) => {
    const { city } = inputData;
    const geocodingResponse = await fetch(`https://geocoding-api.open-meteo.com/v1/search?name=${city}`);
    const geocodingData = await geocodingResponse.json();
 
    const { name, country, timezone } = geocodingData.results[0];
 
    return {
      city_name: name,
      country_name: country,
      country_timezone: timezone
    };
  }
});
 
const locationDetailsStep = createStep({
  id: "location-step",
  description: "Display location details",
  inputSchema: z.object({
    details: z.string()
  }),
  outputSchema: z.object({
    outcome: z.string()
  }),
  execute: async ({ inputData }) => {
    const { details } = inputData;
    return {
      outcome: details
    };
  }
});
 
export const testWorkflow = createWorkflow({
  id: "test-workflow",
  description: 'Test workflow',
  inputSchema: z.object({
    city: z.string()
  }),
  outputSchema: z.object({
    outcome: z.string()
  })
})
  .then(cityCoordinatesStep)
  .map(({ inputData }) => {
    const { city_name, country_name, country_timezone } = inputData;
    return {
      details: `${city_name}, ${country_name}, ${country_timezone}`
    };
  })
  .then(locationDetailsStep)
  .commit();

inputData

Use inputData to access the full output of the previous step:


  .map(({ inputData }) => {
    const { city_name, country_name, country_timezone } = inputData;
    ...
  })

getStepResult

Use getStepResult to access the full output of a specific step by referencing the step’s instance:


  .then(cityCoordinatesStep)
  .map(({ getStepResult }) => {
    console.log(getStepResult(cityCoordinatesStep));
    ...
  })

The above log would produce an output similar to the below:


{
  city_name: 'London',
  country_name: 'United Kingdom',
  country_timezone: 'Europe/London'
}

getInitData

Use getInitData to access the initial input data provided to the workflow:


  .then(cityCoordinatesStep)
  .map(({ getInitData }) => {
      console.log(getInitData());
    ...
  })

The above log would produce an output similar to the below:


{ city: 'London' }

Renaming Outputs

Step Outputs

You can rename step outputs using the object syntax in .map(). In the example below, the city_name output from cityCoordinatesStep is renamed to details:


  .then(cityCoordinatesStep)
  .map({
    details: {
      step: cityCoordinatesStep,
      path: "city_name"
    }
  })

The output would be similar to the below:


{ details: 'London' }

Workflow Outputs

You can rename workflow outputs by using referential composition. This involves passing the workflow instance as the initData.


export const testWorkflow = createWorkflow({
  id: "test-workflow",
  description: 'Test workflow',
  inputSchema: z.object({
    city: z.string()
  }),
  outputSchema: z.object({
    outcome: z.string()
  })
});
 
testWorkflow
  .then(cityCoordinatesStep)
  .map({
    details: {
      initData: testWorkflow,
      path: "city"
    }
  })

The output would be similar to the below:


{ details: 'London' }