Create Embeddings with OpenAI (ChatGPT) API on New Monitor Event (Instant) from Datadog API

Pipedream makes it easy to connect APIs for OpenAI (ChatGPT), Datadog and 1400+ other apps remarkably fast.

Trigger workflow on

New Monitor Event (Instant) from the Datadog API

Next, do this

Create Embeddings with the OpenAI (ChatGPT) API

No credit card required

▶

Watch us build a workflow

7 min

Watch now ➜

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

Developers ♥ Pipedream

Getting Started#

This integration creates a workflow with a Datadog trigger and OpenAI (ChatGPT) action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Monitor Event (Instant) trigger
1. Connect your Datadog account
2. Select a Region
3. Select one or more Monitors
Configure the Create Embeddings action
1. Connect your OpenAI (ChatGPT) account
2. Select a Model
3. Configure Input
4. Optional- Configure User
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 Monitor Event (Instant) on Datadog

Description:Emit new events captured by a Datadog monitor

Version:0.1.2

Key:datadog-new-monitor-event

View on GitHub

Datadog Overview#

With the Datadog API, you can build a variety of applications and tools to help
you monitor and optimize your Datadog account. Here are a few examples:

A tool to help you visualize your Datadog account data
A tool to help you manage your Datadog account settings
A tool to help you monitor and troubleshoot your Datadog account
A tool to help you migrate your data to Datadog

Trigger Code#

import datadog from "../../datadog.app.mjs";
import { payloadFormat } from "../common/payload-format.mjs";

export default {
  key: "datadog-new-monitor-event",
  name: "New Monitor Event (Instant)",
  description: "Emit new events captured by a Datadog monitor",
  dedupe: "unique",
  version: "0.1.2",
  type: "source",
  props: {
    datadog,
    db: "$.service.db",
    http: {
      type: "$.interface.http",
      customResponse: true,
    },
    region: {
      propDefinition: [
        datadog,
        "region",
      ],
    },
    monitors: {
      propDefinition: [
        datadog,
        "monitors",
        (c) => ({
          region: c.region,
        }),
      ],
    },
  },
  hooks: {
    async deploy() {
      // emit historical events
      const { events } = await this.datadog.getEvents({
        params: {
          start: Math.floor(this.datadog.daysAgo(7) / 1000), // one week ago
          end: Math.floor(Date.now() / 1000), // now
        },
        region: this.region,
      });
      const relevantEvents = events.filter((event) => this.monitors.includes(event.monitor_id));

      for (const event of relevantEvents.reverse().slice(-25)) {
        const payload = {
          alertTitle: event.eventTitle,
          alertType: event.alert_type,
          date: event.date_happened,
          eventMsg: event.text,
          eventTitle: event.title,
          hostname: event.host,
          id: event.id,
          lastUpdated: event.date_happened,
          link: `https://app.datadoghq.com${event.url}`,
          priority: event.priority,
          tags: event.tags.join(),
        };
        const meta = this.generateMeta(payload);
        this.$emit(payload, meta);
      }
    },
    async activate() {
      const {
        name: webhookName,
        secretKey: webhookSecretKey,
      } = await this.datadog.createWebhook(
        this.http.endpoint,
        payloadFormat,
        this.region,
      );

      console.log(`Created webhook "${webhookName}"`);
      this._setWebhookName(webhookName);
      this._setWebhookSecretKey(webhookSecretKey);

      await Promise.all(
        this.monitors.map((monitorId) =>
          this.datadog.addWebhookNotification(webhookName, monitorId, this.region)),
      );
    },
    async deactivate() {
      const webhookName = this._getWebhookName();
      await this.datadog.removeWebhookNotifications(webhookName, this.region);
      await this.datadog.deleteWebhook(webhookName, this.region);
    },
  },
  methods: {
    _getWebhookName() {
      return this.db.get("webhookName");
    },
    _setWebhookName(webhookName) {
      this.db.set("webhookName", webhookName);
    },
    _getWebhookSecretKey() {
      return this.db.get("webhookSecretKey");
    },
    _setWebhookSecretKey(webhookSecretKey) {
      this.db.set("webhookSecretKey", webhookSecretKey);
    },
    generateMeta(data) {
      const {
        id,
        eventTitle: summary,
        date: ts,
      } = data;
      return {
        id,
        summary,
        ts,
      };
    },
  },
  async run(event) {
    const webhookSecretKey = this._getWebhookSecretKey();
    if (!this.datadog.isValidSource(event, webhookSecretKey)) {
      console.log("Skipping event from unrecognized source");
      this.http.respond({
        status: 404,
      });
      return;
    }

    // Acknowledge the event back to Datadog.
    this.http.respond({
      status: 200,
    });

    const { body } = event;
    const meta = this.generateMeta(body);
    this.$emit(body, meta);
  },
};

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
Datadog	`datadog`	`app`	This component uses the Datadog 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.
Region	`region`	`string`	Select a value from the drop down menu:`{ "label": "US1 - East", "value": "datadoghq.com" }{ "label": "US3 - West", "value": "us3.datadoghq.com" }{ "label": "US5 - Central", "value": "us5.datadoghq.com" }{ "label": "EU1 - Europe", "value": "datadoghq.eu" }{ "label": "US1-FED (FedRamp)", "value": "ddog-gov.com" }`
Monitors	`monitors`	`integer[]`	Select a value from the drop down menu.

Trigger Authentication#

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

Manage your account’s API and applications keys in Datadog

About Datadog#

Cloud monitoring as a service

Action#

Create Embeddings on OpenAI (ChatGPT)

Description:Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms. [See the docs here](https://platform.openai.com/docs/api-reference/embeddings)

Version:0.0.2

Key:openai-create-embeddings

View on GitHub

OpenAI (ChatGPT) Overview#

The OpenAI API is a powerful tool that provides access to a range of
high-powered machine learning models. With the OpenAI API, developers can
create products, services, and tools that enable humanizing AI experiences, and
build applications that extend the power of human language.

Using the OpenAI API, developers can create language-driven applications such
as:

Natural language understanding and sentiment analysis
Text-based search
Question answering
Dialogue systems and conversation agents
Intelligent text completion
Text summarization
Text classification
Machine translation
Language generation
Multi-factor authentication
Anomaly detection
Text analysis

Action Code#

import openai from "../../app/openai.app.mjs";
import common from "../common/common.mjs";
import { ConfigurationError } from "@pipedream/platform";

export default {
  name: "Create Embeddings",
  version: "0.0.2",
  key: "openai-create-embeddings",
  description: "Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms. [See the docs here](https://platform.openai.com/docs/api-reference/embeddings)",
  type: "action",
  props: {
    openai,
    modelId: {
      propDefinition: [
        openai,
        "embeddingsModelId",
      ],
    },
    input: {
      label: "Input",
      description: "Input text to get embeddings for, encoded as a string or array of tokens. To get embeddings for multiple inputs in a single request, pass an array of strings or array of token arrays. Each input must not exceed 8192 tokens in length.",
      type: "string[]",
    },
    user: common.props.user,
  },
  async run({ $ }) {
    // Confirm no element is more than 8192 tokens in length
    for (const [
      i,
      element,
    ] of this.input.entries()) {
      if (element.length > 8192) {
        throw new ConfigurationError(`Element #${i} is more than 8192 tokens in length. Each input must not exceed 8192 tokens in length.`);
      }
    }

    const response = await this.openai.createEmbeddings({
      $,
      args: {
        model: this.modelId,
        input: this.input,
      },
    });

    if (response) {
      $.export("$summary", "Successfully created embeddings");
    }

    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
OpenAI (ChatGPT)	`openai`	`app`	This component uses the OpenAI (ChatGPT) app.
Model	`modelId`	`string`	Select a value from the drop down menu.
Input	`input`	`string[]`	Input text to get embeddings for, encoded as a string or array of tokens. To get embeddings for multiple inputs in a single request, pass an array of strings or array of token arrays. Each input must not exceed 8192 tokens in length.
User	`user`	`string`	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more here.

Action Authentication#

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

Create a new API key and enter it below.

About OpenAI (ChatGPT)#

OpenAI is an AI research and deployment company with the mission to ensure that artificial general intelligence benefits all of humanity. They are the makers of popular apps like ChatGPT and DALL·E 2.