Generate Text with Mistral AI API on New Worker Duty (Instant) from Onfleet API

Pipedream makes it easy to connect APIs for Mistral AI, Onfleet and 2,800+ other apps remarkably fast.

Trigger workflow on

New Worker Duty (Instant) from the Onfleet API

Next, do this

Generate Text with the Mistral 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 Onfleet trigger and Mistral AI action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Worker Duty (Instant) trigger
1. Connect your Onfleet account
2. Configure Name
Configure the Generate Text action
1. Connect your Mistral AI account
2. Configure Message
3. Select a Model ID
4. Optional- Configure Temperature
5. Optional- Configure Top P
6. Optional- Configure Max Tokens
7. Optional- Configure Random Seed
8. Optional- Configure N
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#

New Worker Duty (Instant) on Onfleet

Description:Emit new event when a worker status is changed.

Version:0.0.1

Key:onfleet-new-worker-duty

View on GitHub

Onfleet Overview#

The Onfleet API integrates with Pipedream to power logistics and delivery operations, offering real-time tracking, optimized routes, automatic dispatch, analytics, and communication with drivers. With Pipedream's serverless platform, one can automate complex workflows involving Onfleet and other apps, triggering actions based on events, scheduling tasks, or processing data to enhance delivery services.

Trigger Code#

import moment from "moment";
import base from "../common/base.mjs";
export default {
    ...base,
    key: "onfleet-new-worker-duty",
    name: "New Worker Duty (Instant)",
    description: "Emit new event when a worker status is changed.",
    version: "0.0.1",
    dedupe: "unique",
    type: "source",
    methods: {
        ...base.methods,
        getTrigger() {
            return 3;
        },
        generateMeta({ id, workerId, time, timeCreated, }) {
            return {
                id: `${workerId || id}${time || timeCreated}`,
                summary: `New worker status changed: ${workerId || id}`,
                ts: moment(time || timeCreated).format(),
            };
        },
        async startDeploy() {
            //It doesn't have pagination and sorting.
            return;
        },
    },
};

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
Onfleet	`onfleet`	`app`	This component uses the Onfleet 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.
Name	`webhookName`	`string`	A name for the webhook for identification.

Trigger Authentication#

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

To retrieve your API key,

Navigate to your Onfleet account and sign in
Go to Settings > API & Webhooks

About Onfleet#

Onfleet is the world's most advanced last mile delivery platform.

Action#

Generate Text on Mistral AI

Description:Generate text using Mistral AI models. [See the Documentation](https://docs.mistral.ai/api/#tag/chat/operation/chat_completion_v1_chat_completions_post)

Version:0.0.1

Key:mistral_ai-generate-text

View on GitHub

Action Code#

import mistralAI from "../../mistral_ai.app.mjs";

export default {
  key: "mistral_ai-generate-text",
  name: "Generate Text",
  description: "Generate text using Mistral AI models. [See the Documentation](https://docs.mistral.ai/api/#tag/chat/operation/chat_completion_v1_chat_completions_post)",
  version: "0.0.1",
  type: "action",
  props: {
    mistralAI,
    message: {
      type: "string",
      label: "Message",
      description: "The prompt message to send",
    },
    modelId: {
      propDefinition: [
        mistralAI,
        "modelId",
      ],
    },
    temperature: {
      type: "string",
      label: "Temperature",
      description: "The sampling temperature to use, we recommend between 0.0 and 0.7. Higher values like 0.7 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both. The default value varies depending on the model you are targeting.",
      optional: true,
    },
    topP: {
      type: "string",
      label: "Top P",
      description: "Nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.",
      optional: true,
    },
    maxTokens: {
      type: "integer",
      label: "Max Tokens",
      description: "The maximum number of tokens to generate in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length.",
      optional: true,
    },
    randomSeed: {
      type: "integer",
      label: "Random Seed",
      description: "The seed to use for random sampling. If set, different calls will generate deterministic results.",
      optional: true,
    },
    n: {
      type: "integer",
      label: "N",
      description: "Number of completions to return for each request, input tokens are only billed once.",
      optional: true,
    },
  },
  async run({ $ }) {
    const response = await this.mistralAI.sendPrompt({
      $,
      data: {
        model: this.modelId,
        messages: [
          {
            content: this.message,
            role: "user",
          },
        ],
        temperature: this.temperature && +this.temperature,
        top_p: this.topP && +this.topP,
        max_tokens: this.maxTokens,
        random_seed: this.randomSeed,
        n: this.n,
      },
    });
    if (response?.id) {
      $.export("$summary", `Successfully retrieved response with ID: ${response.id}`);
    }
    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
Mistral AI	`mistralAI`	`app`	This component uses the Mistral AI app.
Message	`message`	`string`	The prompt message to send
Model ID	`modelId`	`string`	Select a value from the drop down menu.
Temperature	`temperature`	`string`	The sampling temperature to use, we recommend between 0.0 and 0.7. Higher values like 0.7 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both. The default value varies depending on the model you are targeting.
Top P	`topP`	`string`	Nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
Max Tokens	`maxTokens`	`integer`	The maximum number of tokens to generate in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length.
Random Seed	`randomSeed`	`integer`	The seed to use for random sampling. If set, different calls will generate deterministic results.
N	`n`	`integer`	Number of completions to return for each request, input tokens are only billed once.

Generate Text with Mistral AI API on New Worker Duty (Instant) from Onfleet API

Pipedream makes it easy to connect APIs for Mistral AI, Onfleet and 2,800+ other apps remarkably fast.

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

Developers ♥ Pipedream

1-24of2,800+apps by most popular

1
-
24
of
2,800+
apps by most popular