Create Thread (Assistants) with OpenAI (ChatGPT) API on New or Updated Document (Instant) from Google Docs API

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

Trigger workflow on

New or Updated Document (Instant) from the Google Docs API

Next, do this

Create Thread (Assistants) 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 Google Docs 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 or Updated Document (Instant) trigger
1. Connect your Google Docs account
2. Configure Push notification renewal schedule
3. Optional- Select one or more Folder
Configure the Create Thread (Assistants) action
1. Connect your OpenAI (ChatGPT) account
2. Optional- Configure Messages
3. Optional- Configure Metadata
4. Optional- Configure Run Thread
5. Optional- Select one or more Tool Types
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 or Updated Document (Instant) on Google Docs

Description:Emit new event when a document is created or updated in Google Docs. [See the documentation](https://developers.google.com/drive/api/reference/rest/v3/changes/watch)

Version:0.0.1

Key:google_docs-new-or-updated-document

View on GitHub

Google Docs Overview#

The Google Docs API allows you to create, read, and update Google Docs programmatically, enabling a wide range of automations and integrations with other apps and services. With Pipedream, you can harness this API to craft custom serverless workflows that trigger on various events, like form submissions, emails, or scheduled times, and perform actions like updating a document, extracting content, or even generating templated reports.

Trigger Code#

import common from "../common/base.mjs";
import {
  GOOGLE_DRIVE_NOTIFICATION_CHANGE,
  GOOGLE_DRIVE_NOTIFICATION_UPDATE,
} from "../../../google_drive/common/constants.mjs";

export default {
  ...common,
  key: "google_docs-new-or-updated-document",
  name: "New or Updated Document (Instant)",
  description: "Emit new event when a document is created or updated in Google Docs. [See the documentation](https://developers.google.com/drive/api/reference/rest/v3/changes/watch)",
  version: "0.0.1",
  type: "source",
  dedupe: "unique",
  methods: {
    ...common.methods,
    getUpdateTypes() {
      return [
        GOOGLE_DRIVE_NOTIFICATION_CHANGE,
        GOOGLE_DRIVE_NOTIFICATION_UPDATE,
      ];
    },
    generateMeta(doc) {
      return {
        id: doc.revisionId,
        summary: `Document Updated: ${doc.documentId}`,
        ts: Date.now(),
      };
    },
    async processChanges(changedFiles) {
      const filteredFiles = this.checkMinimumInterval(changedFiles);

      for (const file of filteredFiles) {
        file.parents = (await this.googleDrive.getFile(file.id, {
          fields: "parents",
        })).parents;

        console.log(file); // see what file was processed

        if (!this.shouldProcess(file)) {
          console.log(`Skipping file ${file.name}`);
          continue;
        }

        const doc = await this.googleDrive.getDocument(file.id);
        const meta = this.generateMeta(doc);
        this.$emit(doc, 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
Google Docs	`googleDrive`	`app`	This component uses the Google Docs 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.
Push notification renewal schedule	`timer`	`$.interface.timer`	The Google Drive API requires occasional renewal of push notification subscriptions. This runs in the background, so you should not need to modify this schedule.
Folder	`folders`	`string[]`	Select a value from the drop down menu.

Trigger Authentication#

Google Docs uses OAuth authentication. When you connect your Google Docs account, Pipedream will open a popup window where you can sign into Google Docs and grant Pipedream permission to connect to your account. Pipedream securely stores and automatically refreshes the OAuth tokens so you can easily authenticate any Google Docs API.

Pipedream requests the following authorization scopes when you connect your account:

https://www.googleapis.com/auth/drive

About Google Docs#

Use Google Docs to create, edit and collaborate on online documents.

Action#

Create Thread (Assistants) on OpenAI (ChatGPT)

Description:Creates a thread with optional messages and metadata, and optionally runs the thread using the specified assistant. [See the documentation](https://platform.openai.com/docs/api-reference/threads/createThread)

Version:0.0.11

Key:openai-create-thread

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-assistants.mjs";
import constants from "../../common/constants.mjs";

export default {
  key: "openai-create-thread",
  name: "Create Thread (Assistants)",
  description: "Creates a thread with optional messages and metadata, and optionally runs the thread using the specified assistant. [See the documentation](https://platform.openai.com/docs/api-reference/threads/createThread)",
  version: "0.0.11",
  type: "action",
  props: {
    openai,
    messages: {
      propDefinition: [
        openai,
        "messages",
      ],
      optional: true,
    },
    metadata: {
      propDefinition: [
        openai,
        "metadata",
      ],
      optional: true,
    },
    runThread: {
      type: "boolean",
      label: "Run Thread",
      description: "Set to `true` to run the thread after creation",
      optional: true,
      reloadProps: true,
    },
    toolTypes: {
      type: "string[]",
      label: "Tool Types",
      description: "The types of tools to enable on the assistant",
      options: constants.TOOL_TYPES.filter((type) => type !== "function"),
      optional: true,
      reloadProps: true,
    },
  },
  async additionalProps() {
    const props = {};
    if (this.runThread) {
      props.assistantId = {
        type: "string",
        label: "Assistant ID",
        description: "The unique identifier for the assistant.",
        options: async () => { return this.getAssistantPropOptions(); },
      };
      props.model = {
        type: "string",
        label: "Model",
        description: "The ID of the model to use for the assistant",
        options: async () => { return this.getAssistantModelPropOptions(); },
      };
      props.instructions = {
        type: "string",
        label: "Instructions",
        description: "The system instructions that the assistant uses.",
        optional: true,
      };
      props.waitForCompletion = {
        type: "boolean",
        label: "Wait For Completion",
        description: "Set to `true` to poll the API in 3-second intervals until the run is completed",
        optional: true,
      };
    }
    const toolProps = this.toolTypes?.length
      ? await this.getToolProps()
      : {};
    return {
      ...props,
      ...toolProps,
    };
  },
  methods: {
    ...common.methods,
    async getAssistantPropOptions() {
      const { data } = await this.openai.listAssistants();
      return data.map(({
        name, id,
      }) => ({
        label: name || id,
        value: id,
      }));
    },
    async getAssistantModelPropOptions() {
      const models = (await this.openai.models({})).filter(({ id }) => (id.includes("gpt-3.5-turbo") || id.includes("gpt-4-turbo")) && (id !== "gpt-3.5-turbo-0301"));
      return models.map(({ id }) => id);
    },
  },
  async run({ $ }) {
    const messages = this.messages?.length
      ? this.messages.map((message) => ({
        role: "user",
        content: message,
      }))
      : undefined;
    let response = !this.runThread
      ? await this.openai.createThread({
        $,
        data: {
          messages,
          metadata: this.metadata,
          tool_resources: this.buildToolResources(),
        },
      })
      : await this.openai.createThreadAndRun({
        $,
        data: {
          assistant_id: this.assistantId,
          thread: {
            messages,
            metadata: this.metadata,
          },
          model: this.model,
          instructions: this.instructions,
          tools: this.buildTools(),
          tool_resources: this.buildToolResources(),
          metadata: this.metadata,
        },
      });

    if (this.waitForCompletion) {
      const runId = response.id;
      const threadId = response.thread_id;
      response = await this.pollRunUntilCompleted(response, threadId, runId, $);
    }

    $.export("$summary", `Successfully created a thread ${this.runThread
      ? "and run"
      : ""} 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.
Messages	`messages`	`string[]`	An array of messages to start the thread with.
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.
Run Thread	`runThread`	`boolean`	Set to `true` to run the thread after creation
Tool Types	`toolTypes`	`string[]`	Select a value from the drop down menu:`code_interpreterfile_search`

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.

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 models like ChatGPT, DALL-E, and Whisper.

More Ways to Connect OpenAI (ChatGPT) + Google Docs#

Other Popular Integrations#

Create Run (Assistants) with OpenAI (ChatGPT) API on New Document Created (Instant) from Google Docs API

Google Docs + OpenAI (ChatGPT)

Create Thread (Assistants) with OpenAI (ChatGPT) API on New or Updated Document (Instant) from Google Docs API

Pipedream makes it easy to connect APIs for OpenAI (ChatGPT), Google Docs 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