Run AI Command with HARPA AI API on Task Completed (Instant) from Browse AI API

Pipedream makes it easy to connect APIs for HARPA AI, Browse AI and 2,700+ other apps remarkably fast.

Trigger workflow on

Task Completed (Instant) from the Browse AI API

Next, do this

Run AI Command with the HARPA AI API

No credit card required

▶

Watch us build a workflow

8 min

Watch now ➜

Trusted by 1,000,000+ developers from startups to Fortune 500 companies

Developers ♥ Pipedream

Getting Started#

This integration creates a workflow with a Browse AI trigger and HARPA AI action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the Task Completed (Instant) trigger
1. Connect your Browse AI account
2. Select a Robot ID
Configure the Run AI Command action
1. Connect your HARPA AI account
2. Configure URL
3. Optional- Configure Name
4. Optional- Configure Inputs
5. Optional- Configure Result Param
6. Optional- Configure Node
7. Optional- Configure Timeout
8. Optional- Configure Results Webhook
9. Optional- Configure Connection
Deploy the workflow
Send a test event to validate your setup
Turn on the trigger

Details#

This integration uses pre-built, source-available components from Pipedream's GitHub repo. These components are developed by Pipedream and the community, and verified and maintained by Pipedream.

To contribute an update to an existing component or create a new component, create a PR on GitHub. If you're new to Pipedream component development, you can start with quickstarts for trigger span and action development, and then review the component API reference.

Trigger#

Task Completed (Instant) on Browse AI

Description:Emits an event when a Browse AI task is completed. [See the documentation](https://www.browse.ai/docs/api/v2#tag/webhooks/operation/createNewWebhook)

Version:0.0.1

Key:browse_ai-task-completed

View on GitHub

Browse AI Overview#

The Browse AI API enables the automation of data extraction from websites, turning web pages into organized data. It's built for non-coders and coders alike, allowing for custom web scraping and monitoring tasks. Within Pipedream, you can harness Browse AI to create intricate workflows that trigger actions in other apps based on the data you extract. Think of automated competitive analysis, price tracking, or content changes detection, all streamlined through Pipedream's serverless platform.

Trigger Code#

import common from "../common/webhook.mjs";
import events from "../common/events.mjs";

export default {
  ...common,
  key: "browse_ai-task-completed",
  name: "Task Completed (Instant)",
  description: "Emits an event when a Browse AI task is completed. [See the documentation](https://www.browse.ai/docs/api/v2#tag/webhooks/operation/createNewWebhook)",
  version: "0.0.1",
  type: "source",
  dedupe: "unique",
  methods: {
    ...common.methods,
    getResourcesFn() {
      return this.app.getRobotTasks;
    },
    getResourcesFnArgs() {
      return {
        robotId: this.robotId,
        params: {
          status: "successful",
          sort: "-createdAt",
        },
      };
    },
    getResourcesName() {
      return "result.robotTasks.items";
    },
    getEventName() {
      return events.TASK_FINISHED_SUCCESSFULLY;
    },
    generateMeta(resource) {
      return {
        id: resource.id,
        summary: `New Task: ${resource.id}`,
        ts: resource.createdAt,
      };
    },
  },
};

Trigger Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI and CLI.

Label	Prop	Type	Description
Browse AI	`app`	`app`	This component uses the Browse AI app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
N/A	`http`	`$.interface.http`	This component uses `$.interface.http` to generate a unique URL when the component is first instantiated. Each request to the URL will trigger the `run()` method of the component.
Robot ID	`robotId`	`string`	Select a value from the drop down menu.

Trigger Authentication#

Browse AI uses API keys for authentication. When you connect your Browse AI account, Pipedream securely stores the keys so you can easily authenticate to Browse AI APIs in both code and no-code steps.

About Browse AI#

The easiest way to extract structured data from any website with no coding.

Action#

Run AI Command on HARPA AI

Description:Run an AI command. [See the documentation](https://harpa.ai/grid/grid-rest-api-reference#run-ai-command)

Version:0.0.1

Key:harpa_ai-run-ai-command

View on GitHub

Action Code#

import harpaAi from "../../harpa_ai.app.mjs";
import { parseObject } from "../../common/utils.mjs";

export default {
  key: "harpa_ai-run-ai-command",
  name: "Run AI Command",
  description: "Run an AI command. [See the documentation](https://harpa.ai/grid/grid-rest-api-reference#run-ai-command)",
  version: "0.0.1",
  type: "action",
  props: {
    harpaAi,
    url: {
      type: "string",
      label: "URL",
      description: "the page to run the AI command over",
    },
    name: {
      type: "string",
      label: "Name",
      description: "A command name to execute such as Summary",
      optional: true,
    },
    inputs: {
      type: "string[]",
      label: "Inputs",
      description: "An array of Strings, each one passed down into command in place of the user input. Inputs are used to bypass waiting for the user input in multi-step commands. For example [ \"REPORT\", \"DONE\" ] for the Summary command.",
      optional: true,
    },
    resultParam: {
      type: "string",
      label: "Result Param",
      description: "A HARPA {{parameter}} to interpret as the command result. By default is set to \"message\" to take the last chat message. Supports dot notation, e.g. \"g.data.email\". Refer to [AI Commands Guide](https://harpa.ai/chatml/overview) for more details.",
      optional: true,
    },
    node: {
      propDefinition: [
        harpaAi,
        "node",
      ],
    },
    timeout: {
      propDefinition: [
        harpaAi,
        "timeout",
      ],
    },
    resultsWebhook: {
      propDefinition: [
        harpaAi,
        "resultsWebhook",
      ],
    },
    connection: {
      type: "string",
      label: "Connection",
      description: "The title or ID of AI connection to use for AI actions. If not specified or connection not found, default connection is used.",
      optional: true,
    },
  },
  async run({ $ }) {
    const response = await this.harpaAi.sendAction({
      $,
      data: {
        action: "command",
        url: this.url,
        name: this.name,
        inputs: parseObject(this.inputs),
        resultParam: this.resultParam,
        node: this.node,
        timeout: this.timeout,
        resultsWebhook: this.resultsWebhook,
        connection: this.connection,
      },
    });
    $.export("$summary", `Ran AI command on ${this.url}`);
    return response;
  },
};

Action Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI.

Label	Prop	Type	Description
HARPA AI	`harpaAi`	`app`	This component uses the HARPA AI app.
URL	`url`	`string`	the page to run the AI command over
Name	`name`	`string`	A command name to execute such as Summary
Inputs	`inputs`	`string[]`	An array of Strings, each one passed down into command in place of the user input. Inputs are used to bypass waiting for the user input in multi-step commands. For example [ "REPORT", "DONE" ] for the Summary command.
Result Param	`resultParam`	`string`	A HARPA {{parameter}} to interpret as the command result. By default is set to "message" to take the last chat message. Supports dot notation, e.g. "g.data.email". Refer to AI Commands Guide for more details.
Node	`node`	`string`	A target Node ID which should run the command. If omitted, the first available Node will be used.
Timeout	`timeout`	`string`	Synchronous action execution timeout
Results Webhook	`resultsWebhook`	`string`	An asynchronous webhook URL to send the results to upon completion
Connection	`connection`	`string`	The title or ID of AI connection to use for AI actions. If not specified or connection not found, default connection is used.