Create Batch with OpenAI (ChatGPT) API

Pipedream makes it easy to connect APIs for OpenAI (ChatGPT) and 2,700+ other apps remarkably fast.

Trigger workflow on

HTTP requests, schedules and app events

Next, do this

Create Batch 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#

Create a workflow to Create Batch with the OpenAI (ChatGPT) API. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Configure the Create Batch action
1. Connect your OpenAI (ChatGPT) account
2. Select a Endpoint
3. Optional- Select a File ID
4. Optional- Configure File Path or URL
5. Optional- Configure Metadata
Select a trigger to run your workflow on HTTP requests, schedules or app events
Deploy the workflow
Send a test event to validate your setup
Turn on the trigger

Integrations#

Create Batch with OpenAI (ChatGPT) API on New Requests (Payload Only) from HTTP / Webhook API

HTTP / Webhook + OpenAI (ChatGPT)

Try it

Create Batch with OpenAI (ChatGPT) API on New Submission from Typeform API

Typeform + OpenAI (ChatGPT)

Try it

Create Batch with OpenAI (ChatGPT) API on New Submission (Instant) from Jotform API

Jotform + OpenAI (ChatGPT)

Try it

Create Batch with OpenAI (ChatGPT) API on New Scheduled Tasks from Pipedream API

Pipedream + OpenAI (ChatGPT)

Try it

Create Batch with OpenAI (ChatGPT) API on npm Download Counts from npm API

npm + OpenAI (ChatGPT)

Try it

Details#

This is a pre-built, source-available component from Pipedream's GitHub repo. The component is 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.

Create Batch on OpenAI (ChatGPT)

Description:Creates and executes a batch from an uploaded file of requests. [See the documentation](https://platform.openai.com/docs/api-reference/batch/create)

Version:0.1.0

Key:openai-create-batch

View on GitHub

Code#

import openai from "../../openai.app.mjs";
import constants from "../../common/constants.mjs";
import {
  ConfigurationError, getFileStreamAndMetadata,
} from "@pipedream/platform";
import FormData from "form-data";

export default {
  key: "openai-create-batch",
  name: "Create Batch",
  description: "Creates and executes a batch from an uploaded file of requests. [See the documentation](https://platform.openai.com/docs/api-reference/batch/create)",
  version: "0.1.0",
  type: "action",
  props: {
    openai,
    endpoint: {
      type: "string",
      label: "Endpoint",
      description: "The endpoint to be used for all requests in the batch",
      options: constants.BATCH_ENDPOINTS,
    },
    fileId: {
      propDefinition: [
        openai,
        "fileId",
        () => ({
          purpose: "batch",
        }),
      ],
      optional: true,
    },
    filePath: {
      type: "string",
      label: "File Path or URL",
      description: "The .jsonl file to process. Provide either a file URL or a path to a file in the `/tmp` directory (for example, `/tmp/myFile.jpg`)",
      optional: true,
    },
    metadata: {
      propDefinition: [
        openai,
        "metadata",
      ],
    },
  },
  async run({ $ }) {
    if (!this.fileId && !this.filePath) {
      throw new ConfigurationError("Must provide one of File ID or File Path");
    }

    let fileId = this.fileId;
    if (this.filePath) {
      const fileData = new FormData();
      const {
        stream, metadata,
      } = await getFileStreamAndMetadata(this.filePath);
      fileData.append("purpose", "batch");
      fileData.append("file", stream, {
        contentType: metadata.contentType,
        knownLength: metadata.size,
        filename: metadata.name,
      });

      const { id } = await this.openai.uploadFile({
        $,
        data: fileData,
        headers: fileData.getHeaders(),
      });
      fileId = id;
    }

    const response = await this.openai.createBatch({
      $,
      data: {
        input_file_id: fileId,
        endpoint: this.endpoint,
        completion_window: "24h",
        metadata: this.metadata,
      },
    });
    $.export("$summary", `Successfully created batch with ID ${response.id}`);
    return response;
  },
};

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
OpenAI (ChatGPT)	`openai`	`app`	This component uses the OpenAI (ChatGPT) app.
Endpoint	`endpoint`	`string`	Select a value from the drop down menu:`/v1/chat/completions/v1/embeddings/v1/completions`
File ID	`fileId`	`string`	Select a value from the drop down menu.
File Path or URL	`filePath`	`string`	The .jsonl file to process. Provide either a file URL or a path to a file in the `/tmp` directory (for example, `/tmp/myFile.jpg`)
Metadata	`metadata`	`object`	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.