Generate Content from Text and Image with Google Gemini API on New Modified or Deleted Records (Instant) from Airtable API

Pipedream makes it easy to connect APIs for Google Gemini, Airtable and 2,200+ other apps remarkably fast.

Trigger workflow on

New Modified or Deleted Records (Instant) from the Airtable API

Next, do this

Generate Content from Text and Image with the Google Gemini 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 Airtable trigger and Google Gemini action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Modified or Deleted Records (Instant) trigger
1. Connect your Airtable account
2. Select a Base
3. Select one or more Data Types
4. Optional- Select a Table
5. Optional- Select a View
6. Optional- Select one or more Change Types
7. Optional- Select one or more From Sources
8. Optional- Select one or more Watch Data In Field Ids
9. Optional- Select one or more Watch Schemas of Field Ids
10. Optional- Select one or more Include Cell Values in Field Ids
11. Optional- Configure Include Previous Cell Values
12. Optional- Configure Include Previous Field Definitions
Configure the Generate Content from Text and Image action
1. Connect your Google Gemini account
2. Select a Model
3. Configure Prompt Text
4. Select a MIME Type
5. Configure Image File Paths
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 Modified or Deleted Records (Instant) on Airtable

Description:Emit new event each time a record is added, updated, or deleted in an Airtable table. [See the documentation](https://airtable.com/developers/web/api/create-a-webhook)

Version:0.0.1

Key:airtable_oauth-new-modified-or-deleted-records-instant

View on GitHub

Airtable Overview#

Airtable (OAuth) API on Pipedream allows you to manipulate and leverage your Airtable data in a myriad of powerful ways. Sync data between Airtable and other apps, trigger workflows on updates, or process bulk data operations asynchronously. By using Airtable's structured databases with Pipedream's serverless platform, you can craft custom automation solutions, integrate with other services seamlessly, and streamline complex data processes.

Trigger Code#

import airtable from "../../airtable_oauth.app.mjs";
import constants from "../common/constants.mjs";
import sampleEmit from "./test-event.mjs";

export default {
  name: "New Modified or Deleted Records (Instant)",
  description: "Emit new event each time a record is added, updated, or deleted in an Airtable table. [See the documentation](https://airtable.com/developers/web/api/create-a-webhook)",
  key: "airtable_oauth-new-modified-or-deleted-records-instant",
  version: "0.0.1",
  type: "source",
  dedupe: "unique",
  props: {
    airtable,
    db: "$.service.db",
    http: {
      type: "$.interface.http",
      customResponse: true,
    },
    baseId: {
      propDefinition: [
        airtable,
        "baseId",
      ],
    },
    dataTypes: {
      type: "string[]",
      label: "Data Types",
      description: "Only generate payloads that contain changes affecting objects of these types",
      options: constants.DATA_TYPES,
    },
    tableId: {
      propDefinition: [
        airtable,
        "tableId",
        (c) => ({
          baseId: c.baseId,
        }),
      ],
      description: "Only generate payloads for changes in the specified TableId",
      optional: true,
    },
    viewId: {
      propDefinition: [
        airtable,
        "viewId",
        (c) => ({
          baseId: c.baseId,
          tableId: c.tableId,
        }),
      ],
      description: "Only generate payloads for changes in the specified ViewId",
      optional: true,
    },
    changeTypes: {
      type: "string[]",
      label: "Change Types",
      description: "Only generate payloads that contain changes of these types",
      options: constants.CHANGE_TYPES,
      optional: true,
    },
    fromSouces: {
      type: "string[]",
      label: "From Sources",
      description: "Only generate payloads for changes from these sources. If omitted, changes from all sources are reported",
      options: constants.FROM_SOURCES,
      optional: true,
    },
    watchDataInFieldIds: {
      propDefinition: [
        airtable,
        "sortFieldId",
        (c) => ({
          baseId: c.baseId,
          tableId: c.tableId,
        }),
      ],
      type: "string[]",
      label: "Watch Data In Field Ids",
      description: "Only generate payloads for changes that modify values in cells in these fields. If omitted, all fields within the table/view/base are watched",
    },
    watchSchemasOfFieldIds: {
      propDefinition: [
        airtable,
        "sortFieldId",
        (c) => ({
          baseId: c.baseId,
          tableId: c.tableId,
        }),
      ],
      type: "string[]",
      label: "Watch Schemas of Field Ids",
      description: "Only generate payloads for changes that modify the schemas of these fields. If omitted, schemas of all fields within the table/view/base are watched",
    },
    includeCellValuesInFieldIds: {
      propDefinition: [
        airtable,
        "sortFieldId",
        (c) => ({
          baseId: c.baseId,
          tableId: c.tableId,
        }),
      ],
      type: "string[]",
      label: "Include Cell Values in Field Ids",
      description: "A list of fields to include in the payload regardless of whether or not they changed",
    },
    includePreviousCellValues: {
      type: "boolean",
      label: "Include Previous Cell Values",
      description: "If true, include the previous cell value in the payload",
      optional: true,
    },
    includePreviousFieldDefinitions: {
      type: "boolean",
      label: "Include Previous Field Definitions",
      description: "If true, include the previous field definition in the payload",
      optional: true,
    },
  },
  hooks: {
    async activate() {
      const { id } = await this.airtable.createWebhook({
        baseId: this.baseId,
        data: {
          notificationUrl: `${this.http.endpoint}/`,
          specification: {
            options: {
              filters: {
                recordChangeScope: this.viewId
                  ? this.viewId
                  : this.tableId
                    ? this.tableId
                    : undefined,
                dataTypes: this.dataTypes,
                changeTypes: this.changeTypes,
                fromSources: this.fromSources,
                watchDataInFieldIds: this.watchDataInFieldIds,
                watchSchemasOfFieldIds: this.watchSchemasOfFieldIds,
              },
              includes: {
                includeCellValuesInFieldIds: this.includeCellValuesInFieldIds,
                includePreviousCellValues: this.includePreviousCellValues,
                includePreviousFieldDefinitions: this.includePreviousFieldDefinitions,
              },
            },
          },
        },
      });
      this._setHookId(id);
    },
    async deactivate() {
      const webhookId = this._getHookId();
      if (webhookId) {
        await this.airtable.deleteWebhook({
          baseId: this.baseId,
          webhookId,
        });
      }
    },
  },
  methods: {
    _getHookId() {
      return this.db.get("hookId");
    },
    _setHookId(hookId) {
      this.db.set("hookId", hookId);
    },
    getSpecificationOptions() {
      throw new Error("getSpecificationOptions is not implemented");
    },
    generateMeta(payload) {
      return {
        id: payload.baseTransactionNumber,
        summary: `New Event ${payload.baseTransactionNumber}`,
        ts: Date.parse(payload.timestamp),
      };
    },
  },
  async run() {
    this.http.respond({
      status: 200,
    });
    // webhook pings source, we then fetch webhook events to emit
    const webhookId = this._getHookId();
    let hasMore = false;
    const params = {};
    do {
      const {
        cursor, mightHaveMore, payloads,
      } = await this.airtable.listWebhookPayloads({
        baseId: this.baseId,
        webhookId,
        params,
      });
      for (const payload of payloads) {
        const meta = this.generateMeta(payload);
        this.$emit(payload, meta);
      }
      params.cursor = cursor;
      hasMore = mightHaveMore;
    } while (hasMore);
  },
  sampleEmit,
};

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
Airtable	`airtable`	`app`	This component uses the Airtable 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.
Base	`baseId`	`string`	Select a value from the drop down menu.
Data Types	`dataTypes`	`string[]`	Select a value from the drop down menu:`{ "value": "tableData", "label": "Record and cell value changes" }{ "value": "tableFields", "label": "Field changes" }{ "value": "tableMetadata", "label": "Table name and description changes" }`
Table	`tableId`	`string`	Select a value from the drop down menu.
View	`viewId`	`string`	Select a value from the drop down menu.
Change Types	`changeTypes`	`string[]`	Select a value from the drop down menu:`addremoveupdate`
From Sources	`fromSouces`	`string[]`	Select a value from the drop down menu:`{ "value": "client", "label": "Changes generated by a user through the web or mobile clients" }{ "value": "publicApi", "label": "Changes generated through the Airtable API" }{ "value": "formSubmission", "label": "Changes generated when a form view is submitted" }{ "value": "formPageSubmission", "label": "Changes generated when an interface form builder page, form layout page, or record creation button page is submitted" }{ "value": "automation", "label": "Changes generated through an automation action" }{ "value": "system", "label": "Changes generated by system events, such as processing time function formulas" }{ "value": "sync", "label": "Changes generated through Airtable Sync" }{ "value": "anonymousUser", "label": "Changes generated by an anonymous user" }{ "value": "unknown", "label": "Unknown" }`
Watch Data In Field Ids	`watchDataInFieldIds`	`string[]`	Select a value from the drop down menu.
Watch Schemas of Field Ids	`watchSchemasOfFieldIds`	`string[]`	Select a value from the drop down menu.
Include Cell Values in Field Ids	`includeCellValuesInFieldIds`	`string[]`	Select a value from the drop down menu.
Include Previous Cell Values	`includePreviousCellValues`	`boolean`	If true, include the previous cell value in the payload
Include Previous Field Definitions	`includePreviousFieldDefinitions`	`boolean`	If true, include the previous field definition in the payload

Trigger Authentication#

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

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

data.records:readdata.records:writedata.recordComments:readdata.recordComments:writeschema.bases:readschema.bases:writewebhook:manageuser.email:read

About Airtable#

Airtable is a low-code platform to build next-gen apps. Move beyond rigid tools, operationalize your critical data, and reimagine workflows with AI.

Action#

Generate Content from Text and Image on Google Gemini

Description:Generates content from both text and image input using the Gemini API. [See the documentation](https://ai.google.dev/tutorials/rest_quickstart#text-and-image_input)

Version:0.1.0

Key:google_gemini-generate-content-from-text-and-image

View on GitHub

Google Gemini Overview#

The Google Gemini API is a cutting-edge tool from Google that enables developers to leverage AI models like Imagen and MusicLM to create and manipulate images and music based on textual descriptions. With Pipedream, you can harness this API to automate workflows that integrate AI-generated content into a variety of applications, from generating visuals for social media posts to composing background music for videos. Pipedream's serverless platform allows you to connect Google Gemini API with other apps to create complex, event-driven workflows without managing infrastructure.

Action Code#

import fs from "fs";
import { ConfigurationError } from "@pipedream/platform";
import app from "../../google_gemini.app.mjs";

export default {
  key: "google_gemini-generate-content-from-text-and-image",
  name: "Generate Content from Text and Image",
  description: "Generates content from both text and image input using the Gemini API. [See the documentation](https://ai.google.dev/tutorials/rest_quickstart#text-and-image_input)",
  version: "0.1.0",
  type: "action",
  props: {
    app,
    model: {
      propDefinition: [
        app,
        "model",
      ],
    },
    text: {
      propDefinition: [
        app,
        "text",
      ],
    },
    mimeType: {
      propDefinition: [
        app,
        "mimeType",
      ],
    },
    imagePaths: {
      propDefinition: [
        app,
        "imagePaths",
      ],
    },
  },
  methods: {
    fileToGenerativePart(path, mimeType) {
      if (!path) {
        return;
      }
      return {
        inline_data: {
          mime_type: mimeType,
          data: Buffer.from(fs.readFileSync(path)).toString("base64"),
        },
      };
    },
  },
  async run({ $ }) {
    const {
      app,
      model,
      text,
      imagePaths,
      mimeType,
    } = this;

    if (!Array.isArray(imagePaths)) {
      throw new ConfigurationError("Image paths must be an array.");
    }

    if (!imagePaths.length) {
      throw new ConfigurationError("At least one image path must be provided.");
    }

    const response = await app.generateContent({
      $,
      model,
      data: {
        contents: [
          {
            parts: [
              {
                text,
              },
              ...imagePaths.map((path) => this.fileToGenerativePart(path, mimeType)),
            ],
          },
        ],
      },
    });

    $.export("$summary", "Successfully generated content from text and image.");

    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
Google Gemini	`app`	`app`	This component uses the Google Gemini app.
Model	`model`	`string`	Select a value from the drop down menu.
Prompt Text	`text`	`string`	The text to use as the prompt for content generation
MIME Type	`mimeType`	`string`	Select a value from the drop down menu:`{ "label": "PNG", "value": "image/png" }{ "label": "JPEG", "value": "image/jpeg" }`
Image File Paths	`imagePaths`	`string[]`	The local file paths of the images to use in the content generation. The path to the image file saved to the `/tmp` directory (e.g. `/tmp/example.pdf`). See the documentation.

Action Authentication#

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

About Google Gemini#

Google Gemini is a multimodal AI by DeepMind that processes text, audio, images, and more.

More Ways to Connect Google Gemini + Airtable#

Other Popular Integrations#

Generate Content from Text with Google Gemini API on New Field from Airtable API

Airtable + Google Gemini

Generate Content from Text and Image with Google Gemini API on New Modified or Deleted Records (Instant) from Airtable API

Pipedream makes it easy to connect APIs for Google Gemini, Airtable and 2,200+ other apps remarkably fast.

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

Developers ♥ Pipedream

1-24of2,200+apps by most popular

1
-
24
of
2,200+
apps by most popular