Generate Embeddings with Ollama API on New Channel Updates (Instant) from Telegram Bot API

Pipedream makes it easy to connect APIs for Ollama, Telegram Bot and 2,400+ other apps remarkably fast.

Trigger workflow on

New Channel Updates (Instant) from the Telegram Bot API

Next, do this

Generate Embeddings with the Ollama 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 Bot trigger and Ollama action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Channel Updates (Instant) trigger
1. Connect your Telegram Bot account
Configure the Generate Embeddings action
1. Connect your Ollama account
2. Select a Model Name
3. Configure Input
4. Optional- Configure Truncate
5. Optional- Configure Advanced Options
6. Optional- Configure Keep Alive
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 Channel Updates (Instant) on Telegram Bot

Description:Emit new event each time a channel post is created or updated.

Version:0.1.5

Key:telegram_bot_api-channel-updates

View on GitHub

Telegram Bot Overview#

The Telegram Bot API allows you to build bots that can interact with users on the Telegram platform. Using Pipedream, you can automate messaging, handle commands, and trigger actions based on conversations or alerts. Pipedream's serverless execution model enables you to create complex workflows involving Telegram messages without managing any infrastructure. With Pipedream's integration, you can process inbound messages, send outbound notifications, and connect the Telegram Bot API with numerous other services to create powerful automation solutions.

Trigger Code#

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

export default {
  ...base,
  key: "telegram_bot_api-channel-updates",
  name: "New Channel Updates (Instant)",
  description: "Emit new event each time a channel post is created or updated.",
  version: "0.1.5",

  type: "source",
  dedupe: "unique",
  methods: {
    ...base.methods,
    getEventTypes() {
      return [
        "channel_post",
        "edited_channel_post",
      ];
    },
    getMeta(event, channelPost) {
      return {
        id: event.update_id,
        summary: `${channelPost.chat.title} - ${channelPost.text}`,
        ts: new Date(channelPost.edit_date ?? channelPost.date),
      };
    },
    processEvent(event) {
      const channelPost = event.edited_channel_post ?? event.channel_post;

      if (!channelPost?.chat) {
        throw new Error(`Expected event to contain a chat, but received: ${JSON.stringify(event)}`);
      }

      this.$emit(event, this.getMeta(event, channelPost));
    },
  },
  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 Bot	`telegramBotApi`	`app`	This component uses the Telegram Bot 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.

Trigger Authentication#

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

To use the Telegram Bot API, you must first create a new bot by chatting with the BotFather.

After you create your bot, copy the bot token and add it below.

About Telegram Bot#

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

Action#

Generate Embeddings on Ollama

Description:Generate embeddings from a model. [See the documentation](https://github.com/ollama/ollama/blob/main/docs/api.md#generate-embeddings).

Version:0.0.1

Key:ollama-generate-embeddings

View on GitHub

Action Code#

import utils from "../../common/utils.mjs";
import app from "../../ollama.app.mjs";

export default {
  key: "ollama-generate-embeddings",
  name: "Generate Embeddings",
  description: "Generate embeddings from a model. [See the documentation](https://github.com/ollama/ollama/blob/main/docs/api.md#generate-embeddings).",
  version: "0.0.1",
  type: "action",
  props: {
    app,
    model: {
      propDefinition: [
        app,
        "model",
      ],
    },
    input: {
      type: "string[]",
      label: "Input",
      description: "The list of texts to generate embeddings for.",
    },
    truncate: {
      type: "boolean",
      label: "Truncate",
      description: "Truncates the end of each input to fit within context length. Returns error if `false` and context length is exceeded. Defaults to `true`.",
      optional: true,
    },
    options: {
      propDefinition: [
        app,
        "options",
      ],
    },
    keepAlive: {
      propDefinition: [
        app,
        "keepAlive",
      ],
    },
  },
  methods: {
    generateEmbeddings(args = {}) {
      return this.app.post({
        path: "/embed",
        ...args,
      });
    },
  },
  async run({ $ }) {
    const {
      generateEmbeddings,
      model,
      input,
      truncate,
      options,
      keepAlive,
    } = this;

    const response = await generateEmbeddings({
      $,
      data: {
        model,
        input,
        truncate,
        options: utils.parseOptions(options),
        keep_alive: keepAlive,
      },
    });
    $.export("$summary", "Successfully generated embeddings.");
    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
Ollama	`app`	`app`	This component uses the Ollama app.
Model Name	`model`	`string`	Select a value from the drop down menu.
Input	`input`	`string[]`	The list of texts to generate embeddings for.
Truncate	`truncate`	`boolean`	Truncates the end of each input to fit within context length. Returns error if `false` and context length is exceeded. Defaults to `true`.
Advanced Options	`options`	`object`	Additional model parameters listed in the documentation for the Modelfile such as `temperature`
Keep Alive	`keepAlive`	`string`	Controls how long the model will stay loaded into memory following the request (default: 5m).