Generate Alt Text with AltText.ai API on New Bot Command Received (Instant) from Telegram API

Pipedream makes it easy to connect APIs for AltText.ai, Telegram and 2,700+ other apps remarkably fast.

Trigger workflow on

New Bot Command Received (Instant) from the Telegram API

Next, do this

Generate Alt Text with the AltText.ai 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 Telegram trigger and AltText.ai action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Bot Command Received (Instant) trigger
1. Connect your Telegram account
2. Select one or more Commands
Configure the Generate Alt Text action
1. Connect your AltText.ai account
2. Configure fileInfo
3. Optional- Configure Image Data
4. Optional- Configure Image File Path or URL
5. Optional- Configure Keywords
6. Optional- Configure Negative Keywords
7. Optional- Configure Keyword Source
8. Optional- Select a Language
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 Bot Command Received (Instant) on Telegram

Description:Emit new event each time a Telegram Bot command is received.

Version:0.0.5

Key:telegram_bot_api-new-bot-command-received

View on GitHub

New Bot Command Received (Instant) Overview#

Telegram Bots can respond to Slash commands. For instance, you can add a /hi or /help command to your Telegram bot to help users learn how to use your bot.

Trigger Code#

import base from "../common/webhooks.mjs";
import sampleEmit from "./test-event.mjs";

export default {
  ...base,
  key: "telegram_bot_api-new-bot-command-received",
  name: "New Bot Command Received (Instant)",
  description: "Emit new event each time a Telegram Bot command is received.",
  version: "0.0.5",
  type: "source",
  dedupe: "unique",
  props: {
    ...base.props,
    commands: {
      propDefinition: [
        base.props.telegramBotApi,
        "commands",
      ],
    },
  },
  methods: {
    ...base.methods,
    getMeta(event, message) {
      return {
        id: event.update_id,
        summary: message.text,
        ts: new Date(message.edit_date ?? message.date),
      };
    },
    getEventTypes() {
      return [
        "message",
        "edited_message",
      ];
    },
    processEvent(event) {
      const message = event.edited_message ?? event.message;

      if (!message?.text) {
        console.log("Skipping message that isn’t a bot command");

        return;
      }

      const command = message.text.split(" ")[0];

      if (typeof this.commands === "string") {
        this.commands = JSON.parse(this.commands);
      }

      const foundCmd = this.commands.some((cmd) => command.includes(cmd));
      if (!foundCmd) {
        return;
      }

      this.$emit(event, this.getMeta(event, message));
    },
  },
  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
Telegram	`telegramBotApi`	`app`	This component uses the Telegram 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.
Commands	`commands`	`string[]`	Select a value from the drop down menu.

Trigger Authentication#

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

About Telegram#

Telegram, is a cloud-based, cross-platform, encrypted instant messaging (IM) service.

Action#

Generate Alt Text on AltText.ai

Description:Generates a descriptive alt text for a given image. [See the documentation](https://alttext.ai/apidocs#tag/Images/operation/create-image)

Version:0.1.0

Key:alttext_ai-generate-alt-text

View on GitHub

AltText.ai Overview#

AltText.ai provides an API that leverages artificial intelligence to generate alternative text (alt text) for images, which is crucial for web accessibility and SEO. With AltText.ai, you can automate the process of creating descriptive, keyword-rich, and meaningful alt text for images on websites, blogs, or online stores. In Pipedream, you can create workflows that trigger on various events to send images to the AltText.ai API and receive alt text, which you can then store or apply to your content management system automatically.

Action Code#

import alttextAi from "../../alttext_ai.app.mjs";
import {
  ConfigurationError, getFileStream,
} from "@pipedream/platform";
import { LANGUAGE_OPTIONS } from "../../commons/constants.mjs";

export default {
  key: "alttext_ai-generate-alt-text",
  name: "Generate Alt Text",
  description:
    "Generates a descriptive alt text for a given image. [See the documentation](https://alttext.ai/apidocs#tag/Images/operation/create-image)",
  version: "0.1.0",
  type: "action",
  props: {
    alttextAi,
    fileInfo: {
      type: "alert",
      alertType: "warning",
      content: "Either `Image Data` or `Image File Path or URL` should be provided. If both are provided, `Image Data` will be used.",
    },
    imageData: {
      type: "string",
      label: "Image Data",
      description:
        "The image data in base64 format",
      optional: true,
    },
    imageFilePath: {
      type: "string",
      label: "Image File Path or URL",
      description:
        "The image to process. Provide either a file URL or a path to a file in the `/tmp` directory (for example, `/tmp/myImage.jpg`)",
      optional: true,
    },
    keywords: {
      type: "string[]",
      label: "Keywords",
      description:
        "Keywords / phrases to be considered when generating the alt text. Keywords must be in English, even if requesting alt text in another language. Max 6 items.",
      optional: true,
    },
    negativeKeywords: {
      type: "string[]",
      label: "Negative Keywords",
      description:
        "Negative keywords / phrases to be removed from any generated alt text. Negative keywords must be in English, even if requesting alt text in another language. Max 6 items.",
      optional: true,
    },
    keywordSource: {
      type: "string",
      label: "Keyword Source",
      description:
        "Text to use as the source of keywords for the alt text. Will only be used if `Keywords` is not provided. This text might be a product description, or a paragraph that describes the context of the images, etc. Max 1024 characters.",
      optional: true,
    },
    language: {
      type: "string",
      label: "Language",
      description: "The language for the generated alt text.",
      options: LANGUAGE_OPTIONS,
      default: "en",
      optional: true,
    },
  },
  async run({ $ }) {
    const {
      imageData, imageFilePath,
    } = this;
    if (!imageData && !imageFilePath) {
      throw new ConfigurationError("Either `Image Data` or `Image File Path or URL` should be specified.");
    }

    let rawData = imageData;
    if (!rawData) {
      const stream = await getFileStream(imageFilePath);
      const chunks = [];
      for await (const chunk of stream) {
        chunks.push(chunk);
      }
      const buffer = Buffer.concat(chunks);
      rawData = buffer.toString("base64");
    }

    const response = await this.alttextAi.generateAltText({
      $,
      data: {
        image: {
          raw: rawData,
        },
        keywords: this.keywords,
        negative_keywords: this.negativeKeywords,
        keyword_source: this.keywordSource,
        lang: this.language,
      },
    });

    $.export("$summary", "Generated alt text successfully");
    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
AltText.ai	`alttextAi`	`app`	This component uses the AltText.ai app.
Image Data	`imageData`	`string`	The image data in base64 format
Image File Path or URL	`imageFilePath`	`string`	The image to process. Provide either a file URL or a path to a file in the `/tmp` directory (for example, `/tmp/myImage.jpg`)
Keywords	`keywords`	`string[]`	Keywords / phrases to be considered when generating the alt text. Keywords must be in English, even if requesting alt text in another language. Max 6 items.
Negative Keywords	`negativeKeywords`	`string[]`	Negative keywords / phrases to be removed from any generated alt text. Negative keywords must be in English, even if requesting alt text in another language. Max 6 items.
Keyword Source	`keywordSource`	`string`	Text to use as the source of keywords for the alt text. Will only be used if `Keywords` is not provided. This text might be a product description, or a paragraph that describes the context of the images, etc. Max 1024 characters.
Language	`language`	`string`	Select a value from the drop down menu:`{ "label": "Afrikaans", "value": "af" }{ "label": "Albanian", "value": "sq" }{ "label": "Amharic", "value": "am" }{ "label": "Arabic", "value": "ar" }{ "label": "Armenian", "value": "hy" }{ "label": "Assamese", "value": "as" }{ "label": "Aymara", "value": "ay" }{ "label": "Azerbaijani", "value": "az" }{ "label": "Bambara", "value": "bm" }{ "label": "Basque", "value": "eu" }{ "label": "Belarusian", "value": "be" }{ "label": "Bengali", "value": "bn" }{ "label": "Bhojpuri", "value": "bho" }{ "label": "Bosnian", "value": "bs" }{ "label": "Bulgarian", "value": "bg" }{ "label": "Catalan", "value": "ca" }{ "label": "Cebuano", "value": "ceb" }{ "label": "Chinese (Simplified)", "value": "zh-CN" }{ "label": "Chinese (Traditional)", "value": "zh-TW" }{ "label": "Corsican", "value": "co" }{ "label": "Croatian", "value": "hr" }{ "label": "Czech", "value": "cs" }{ "label": "Danish", "value": "da" }{ "label": "Dhivehi", "value": "dv" }{ "label": "Dogri", "value": "doi" }{ "label": "Dutch", "value": "nl" }{ "label": "English", "value": "en" }{ "label": "Esperanto", "value": "eo" }{ "label": "Estonian", "value": "et" }{ "label": "Ewe", "value": "ee" }{ "label": "Filipino (Tagalog)", "value": "fil" }{ "label": "Finnish", "value": "fi" }{ "label": "French", "value": "fr" }{ "label": "Frisian", "value": "fy" }{ "label": "Galician", "value": "gl" }{ "label": "Georgian", "value": "ka" }{ "label": "German", "value": "de" }{ "label": "Greek", "value": "el" }{ "label": "Guarani", "value": "gn" }{ "label": "Gujarati", "value": "gu" }{ "label": "Haitian Creole", "value": "ht" }{ "label": "Hausa", "value": "ha" }{ "label": "Hawaiian", "value": "haw" }{ "label": "Hebrew", "value": "he" }{ "label": "Hindi", "value": "hi" }{ "label": "Hmong", "value": "hmn" }{ "label": "Hungarian", "value": "hu" }{ "label": "Icelandic", "value": "is" }{ "label": "Igbo", "value": "ig" }{ "label": "Ilocano", "value": "ilo" }{ "label": "Indonesian", "value": "id" }{ "label": "Irish", "value": "ga" }{ "label": "Italian", "value": "it" }{ "label": "Japanese", "value": "ja" }{ "label": "Javanese", "value": "jv" }{ "label": "Kannada", "value": "kn" }{ "label": "Kazakh", "value": "kk" }{ "label": "Khmer", "value": "km" }{ "label": "Kinyarwanda", "value": "rw" }{ "label": "Konkani", "value": "gom" }{ "label": "Korean", "value": "ko" }{ "label": "Krio", "value": "kri" }{ "label": "Kurdish", "value": "ku" }{ "label": "Kurdish (Sorani)", "value": "ckb" }{ "label": "Kyrgyz", "value": "ky" }{ "label": "Lao", "value": "lo" }{ "label": "Latin", "value": "la" }{ "label": "Latvian", "value": "lv" }{ "label": "Lingala", "value": "ln" }{ "label": "Lithuanian", "value": "lt" }{ "label": "Luganda", "value": "lg" }{ "label": "Luxembourgish", "value": "lb" }{ "label": "Macedonian", "value": "mk" }{ "label": "Maithili", "value": "mai" }{ "label": "Malagasy", "value": "mg" }{ "label": "Malay", "value": "ms" }{ "label": "Malayalam", "value": "ml" }{ "label": "Maltese", "value": "mt" }{ "label": "Maori", "value": "mi" }{ "label": "Marathi", "value": "mr" }{ "label": "Meiteilon (Manipuri)", "value": "mni-Mtei" }{ "label": "Mizo", "value": "lus" }{ "label": "Mongolian", "value": "mn" }{ "label": "Myanmar (Burmese)", "value": "my" }{ "label": "Nepali", "value": "ne" }{ "label": "Norwegian", "value": "no" }{ "label": "Nyanja (Chichewa)", "value": "ny" }{ "label": "Odia (Oriya)", "value": "or" }{ "label": "Oromo", "value": "om" }{ "label": "Pashto", "value": "ps" }{ "label": "Persian", "value": "fa" }{ "label": "Polish", "value": "pl" }{ "label": "Portuguese", "value": "pt" }{ "label": "Punjabi", "value": "pa" }{ "label": "Quechua", "value": "qu" }{ "label": "Romanian", "value": "ro" }{ "label": "Russian", "value": "ru" }{ "label": "Samoan", "value": "sm" }{ "label": "Sanskrit", "value": "sa" }{ "label": "ScotsGaelic", "value": "gd" }{ "label": "Sepedi", "value": "nso" }{ "label": "Serbian", "value": "sr" }{ "label": "Sesotho", "value": "st" }{ "label": "Shona", "value": "sn" }{ "label": "Sindhi", "value": "sd" }{ "label": "Sinhala (Sinhalese)", "value": "si" }{ "label": "Slovak", "value": "sk" }{ "label": "Slovenian", "value": "sl" }{ "label": "Somali", "value": "so" }{ "label": "Spanish", "value": "es" }{ "label": "Sundanese", "value": "su" }{ "label": "Swahili", "value": "sw" }{ "label": "Swedish", "value": "sv" }{ "label": "Tagalog (Filipino)", "value": "tl" }{ "label": "Tajik", "value": "tg" }{ "label": "Tamil", "value": "ta" }{ "label": "Tatar", "value": "tt" }{ "label": "Telugu", "value": "te" }{ "label": "Thai", "value": "th" }{ "label": "Tigrinya", "value": "ti" }{ "label": "Tsonga", "value": "ts" }{ "label": "Turkish", "value": "tr" }{ "label": "Turkmen", "value": "tk" }{ "label": "Twi (Akan)", "value": "ak" }{ "label": "Ukrainian", "value": "uk" }{ "label": "Urdu", "value": "ur" }{ "label": "Uyghur", "value": "ug" }{ "label": "Uzbek", "value": "uz" }{ "label": "Vietnamese", "value": "vi" }{ "label": "Welsh", "value": "cy" }{ "label": "Xhosa", "value": "xh" }{ "label": "Yiddish", "value": "yi" }{ "label": "Yoruba", "value": "yo" }{ "label": "Zulu", "value": "zu" }`