Create Completion (Send Prompt) with OpenAI (ChatGPT) API on New Error Occurred from Airbrake API

Pipedream makes it easy to connect APIs for OpenAI (ChatGPT), Airbrake and 2,400+ other apps remarkably fast.

Trigger workflow on

New Error Occurred from the Airbrake API

Next, do this

Create Completion (Send Prompt) with the OpenAI (ChatGPT) 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 Airbrake 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 Error Occurred trigger
1. Connect your Airbrake account
2. Configure timer
3. Select a Project ID
Configure the Create Completion (Send Prompt) action
1. Connect your OpenAI (ChatGPT) account
2. Configure alert
3. Select a Model
4. Configure Prompt
5. Optional- Configure Suffix
6. Optional- Configure Max Tokens
7. Optional- Configure Temperature
8. Optional- Configure Top P
9. Optional- Configure N
10. Optional- Configure Stop
11. Optional- Configure Presence Penalty
12. Optional- Configure Frequency Penalty
13. Optional- Configure User
14. Optional- Configure Best Of
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 Error Occurred on Airbrake

Description:Emit new event for each error occurred. [See docs here](https://docs.airbrake.io/docs/devops-tools/api/#list-notices-v4)

Version:0.0.3

Key:airbrake-new-error-occurred

View on GitHub

Airbrake Overview#

The Airbrake API facilitates real-time error monitoring and automatic exception reporting for your web applications, giving you instant insight into issues as they arise. With this API, you can create custom notifications, analyze and aggregate error data, and manage your project's error trends. Leveraging Pipedream's capabilities, you can automate workflows that respond to these errors, connect with other services for enhanced issue resolution, and maintain a smooth operation within your development and production environments.

Trigger Code#

import airbrake from "../../airbrake.app.mjs";
import { DEFAULT_POLLING_SOURCE_TIMER_INTERVAL } from "@pipedream/platform";

export default {
  name: "New Error Occurred",
  version: "0.0.3",
  key: "airbrake-new-error-occurred",
  description: "Emit new event for each error occurred. [See docs here](https://docs.airbrake.io/docs/devops-tools/api/#list-notices-v4)",
  type: "source",
  dedupe: "unique",
  props: {
    airbrake,
    db: "$.service.db",
    timer: {
      type: "$.interface.timer",
      static: {
        intervalSeconds: DEFAULT_POLLING_SOURCE_TIMER_INTERVAL,
      },
    },
    projectId: {
      propDefinition: [
        airbrake,
        "projectId",
      ],
    },
  },
  methods: {
    emitEvent(data) {
      this._setLastNoticeId(data.id);

      this.$emit(data, {
        id: data.id,
        summary: `New error with id ${data.id}`,
        ts: Date.parse(data.created_at),
      });
    },
    _setLastNoticeId(id) {
      this.db.set("lastNoticeId", id);
    },
    _getLastNoticeId() {
      return this.db.get("lastNoticeId");
    },
  },
  hooks: {
    async deploy() {
      const { notices } = await this.airbrake.getProjectNotices({
        projectId: this.projectId,
        params: {
          page: 1,
        },
      });

      notices.slice(-10).reverse()
        .forEach(this.emitEvent);
    },
  },
  async run() {
    const lastNoticeId = this._getLastNoticeId();

    let page = 1;

    while (page >= 0) {
      const { notices } = await this.airbrake.getProjectNotices({
        projectId: this.projectId,
        params: {
          page,
        },
      });

      notices.reverse().forEach(this.emitEvent);

      if (notices.filter((notice) => notice.id === lastNoticeId)) {
        return;
      }

      page++;
    }
  },
};

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
Airbrake	`airbrake`	`app`	This component uses the Airbrake app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
	`timer`	`$.interface.timer`
Project ID	`projectId`	`integer`	Select a value from the drop down menu.

Trigger Authentication#

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

To access a user-based API Key, sign in to your Airbrake account and go to Profile > Profile & Notifications.
To access a Project-based API Key, open a project on your Dashboard, and click Settings on the top right.
Alternatively, you can generate time-expiring user API Tokens here: https://airbrake.io/docs/api/#create-user-token-v4.

About Airbrake#

Airbrake collects errors generated by other applications, and aggregates the results for review.

Action#

Create Completion (Send Prompt) on OpenAI (ChatGPT)

Description:OpenAI recommends using the **Chat** action for the latest `gpt-3.5-turbo` API, since it's faster and 10x cheaper. This action creates a completion for the provided prompt and parameters using the older `/completions` API. [See the documentation](https://beta.openai.com/docs/api-reference/completions/create)

Version:0.1.14

Key:openai-send-prompt

View on GitHub

OpenAI (ChatGPT) Overview#

OpenAI provides a suite of powerful AI models through its API, enabling developers to integrate advanced natural language processing and generative capabilities into their applications. Here’s an overview of the services offered by OpenAI's API:

Use Python or Node.js code to make fully authenticated API requests with your OpenAI account:

Action Code#

import openai from "../../openai.app.mjs";
import common from "../common/common.mjs";

export default {
  ...common,
  name: "Create Completion (Send Prompt)",
  version: "0.1.14",
  key: "openai-send-prompt",
  description: "OpenAI recommends using the **Chat** action for the latest `gpt-3.5-turbo` API, since it's faster and 10x cheaper. This action creates a completion for the provided prompt and parameters using the older `/completions` API. [See the documentation](https://beta.openai.com/docs/api-reference/completions/create)",
  type: "action",
  props: {
    openai,
    alert: {
      type: "alert",
      alertType: "warning",
      content: "We recommend using the Pipedream **Chat** action instead of this one. It supports the latest `gpt-3.5-turbo` API, which is faster and 10x cheaper. This action, **Create Completion (Send Prompt)**, creates a completion for the provided prompt and parameters using the older `/completions` API.",
    },
    modelId: {
      propDefinition: [
        openai,
        "completionModelId",
      ],
    },
    prompt: {
      label: "Prompt",
      description: "The prompt to generate completions for",
      type: "string",
    },
    suffix: {
      label: "Suffix",
      description: "The suffix that comes after a completion of inserted text",
      type: "string",
      optional: true,
    },
    ...common.props,
    bestOf: {
      label: "Best Of",
      description: "Generates best_of completions server-side and returns the \"best\" (the one with the highest log probability per token). If set, results cannot be streamed.",
      type: "integer",
      optional: true,
    },
  },
  async run({ $ }) {
    const response = await this.openai.createCompletion({
      $,
      data: this._getCommonArgs(),
    });

    if (response) {
      $.export("$summary", `Successfully sent prompt 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
OpenAI (ChatGPT)	`openai`	`app`	This component uses the OpenAI (ChatGPT) app.
Model	`modelId`	`string`	Select a value from the drop down menu.
Prompt	`prompt`	`string`	The prompt to generate completions for
Suffix	`suffix`	`string`	The suffix that comes after a completion of inserted text
Max Tokens	`maxTokens`	`integer`	The maximum number of tokens to generate in the completion.
Temperature	`temperature`	`string`	Optional. What sampling temperature to use. Higher values means the model will take more risks. Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer.
Top P	`topP`	`string`	An alternative to sampling with temperature, called 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.
N	`n`	`integer`	How many completions to generate for each prompt
Stop	`stop`	`string[]`	Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
Presence Penalty	`presencePenalty`	`string`	Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
Frequency Penalty	`frequencyPenalty`	`string`	Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
User	`user`	`string`	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more here.
Best Of	`bestOf`	`integer`	Generates best_of completions server-side and returns the "best" (the one with the highest log probability per token). If set, results cannot be streamed.

Create Completion (Send Prompt) with OpenAI (ChatGPT) API on New Error Occurred from Airbrake API

Pipedream makes it easy to connect APIs for OpenAI (ChatGPT), Airbrake and 2,400+ other apps remarkably fast.

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

Developers ♥ Pipedream

1-24of2,400+apps by most popular

1
-
24
of
2,400+
apps by most popular