Generate Chat Completion with Ollama API on New Message in Channel from Discord Bot API

Pipedream makes it easy to connect APIs for Ollama, Discord Bot and 2,900+ other apps remarkably fast.

Trigger workflow on

New Message in Channel from the Discord Bot API

Next, do this

Generate Chat Completion 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 Discord 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 Message in Channel trigger
1. Connect your Discord Bot account
2. Select a Guild
3. Select one or more Channels
4. Optional- Configure Emit messages as a single event
5. Optional- Configure Ignore Bot Messages
6. Configure timer
Configure the Generate Chat Completion action
1. Connect your Ollama account
2. Select a Model Name
3. Configure Messages
4. Optional- Configure Tools
5. Optional- Configure Advanced Options
6. Optional- Configure Stream
7. 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 Message in Channel on Discord Bot

Description:Emit new event for each message posted to one or more channels

Version:1.0.0

Key:discord_bot-new-message-in-channel

View on GitHub

Discord Bot Overview#

The Discord Bot API unlocks the power to interact with Discord users and channels programmatically, making it possible to automate messages, manage servers, and integrate with other services. With Pipedream's serverless platform, you can create complex workflows that respond to events in Discord, process data, and trigger actions in other apps. This opens up opportunities for community engagement, content moderation, analytics, and more, without the overhead of managing infrastructure.

Trigger Code#

import { DEFAULT_POLLING_SOURCE_TIMER_INTERVAL } from "@pipedream/platform";
import maxBy from "lodash.maxby";
import common from "../common/common.mjs";
import sampleEmit from "./test-event.mjs";

const { discord } = common.props;

export default {
  ...common,
  key: "discord_bot-new-message-in-channel",
  name: "New Message in Channel",
  description: "Emit new event for each message posted to one or more channels",
  type: "source",
  version: "1.0.0",

  dedupe: "unique", // Dedupe events based on the Discord message ID
  props: {
    ...common.props,
    db: "$.service.db",
    channels: {
      type: "string[]",
      label: "Channels",
      description: "The channels you'd like to watch for new messages",
      propDefinition: [
        discord,
        "channelId",
        ({ guildId }) => ({
          guildId,
        }),
      ],
    },
    emitEventsInBatch: {
      type: "boolean",
      label: "Emit messages as a single event",
      description:
        "If `true`, all messages are emitted as an array, within a single Pipedream event. Defaults to `false`, emitting each Discord message as its own event in Pipedream",
      optional: true,
      default: false,
    },
    ignoreBotMessages: {
      type: "boolean",
      label: "Ignore Bot Messages",
      description: "Set to `true` to only emit messages NOT from the configured Discord bot",
      optional: true,
    },
    timer: {
      type: "$.interface.timer",
      default: {
        intervalSeconds: DEFAULT_POLLING_SOURCE_TIMER_INTERVAL,
      },
    },
  },
  hooks: {
    async deploy() {
      if (this.ignoreBotMessages) {
        const { id } = await this.getBotProfile();
        this._setBotId(id);
      }
    },
  },
  async run({ $ }) {
    // We store a cursor to the last message ID
    let lastMessageIDs = this._getLastMessageIDs();
    const botId = this.ignoreBotMessages
      ? this._getBotId()
      : null;

    // If this is our first time running this source,
    // get the last N messages, emit them, and checkpoint
    for (const channelId of this.channels) {
      let lastMessageID;
      let messages = [];

      if (!lastMessageID) {
        messages = await this.discord.getMessages({
          $,
          channelId,
          params: {
            limit: 100,
          },
        });

        lastMessageID = messages.length
          ? maxBy(messages, (message) => message.id).id
          : 1;

      } else {
        let newMessages = [];

        do {
          newMessages = await this.discord.getMessages({
            $,
            channelId,
            params: {
              after: lastMessageIDs[channelId],
            },
          });

          messages = messages.concat(newMessages);

          lastMessageID = newMessages.length
            ? maxBy(newMessages, (message) => message.id).id
            : lastMessageIDs[channelId];

        } while (newMessages.length);
      }

      // Set the new high water mark for the last message ID
      // for this channel
      lastMessageIDs[channelId] = lastMessageID;

      if (!messages.length) {
        console.log(`No new messages in channel ${channelId}`);
        return;
      }

      if (botId) {
        messages = messages.filter((message) => message.author.id !== botId);
      }

      console.log(`${messages.length} new messages in channel ${channelId}`);

      // Batched emits do not take advantage of the built-in deduper
      if (this.emitEventsInBatch) {
        const suffixChar =
          messages.length > 1
            ? "s"
            : "";

        this.$emit(messages, {
          summary: `${messages.length} new message${suffixChar}`,
          id: lastMessageID,
        });

      } else {
        messages.forEach((message) => {
          this.$emit(message, {
            summary: message.content,
            id: message.id, // dedupes events based on this ID
          });
        });
      }
    }

    // Set the last message ID for the next run
    this._setLastMessageIDs(lastMessageIDs);
  },
  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
Discord Bot	`discord`	`app`	This component uses the Discord Bot app.
Guild	`guildId`	`string`	Select a value from the drop down menu.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
Channels	`channels`	`string[]`	Select a value from the drop down menu.
Emit messages as a single event	`emitEventsInBatch`	`boolean`	If `true`, all messages are emitted as an array, within a single Pipedream event. Defaults to `false`, emitting each Discord message as its own event in Pipedream
Ignore Bot Messages	`ignoreBotMessages`	`boolean`	Set to `true` to only emit messages NOT from the configured Discord bot
	`timer`	`$.interface.timer`

Trigger Authentication#

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

This app allows you to use the Discord API using your own Discord bot. If you don't want to use a custom bot, and you just need to use the Discord API, exit this screen and use the Discord app, instead.

If you want to use your own Discord bot, but haven't created one yet, see these instructions or watch this video. You'll need to add this bot to your server(s) to make successful API requests.

Once you've created your bot, you'll find the Bot token within the Bot section of your app. Enter that token below.

About Discord Bot#

Use this app to interact with the Discord API using a bot in your account

Action#

Generate Chat Completion on Ollama

Description:Generates the next message in a chat with a provided model. [See the documentation](https://github.com/ollama/ollama/blob/main/docs/api.md#generate-a-chat-completion).

Version:0.0.2

Key:ollama-generate-chat-completion

View on GitHub

Action Code#

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

export default {
  key: "ollama-generate-chat-completion",
  name: "Generate Chat Completion",
  description: "Generates the next message in a chat with a provided model. [See the documentation](https://github.com/ollama/ollama/blob/main/docs/api.md#generate-a-chat-completion).",
  version: "0.0.2",
  annotations: {
    destructiveHint: false,
    openWorldHint: true,
    readOnlyHint: false,
  },
  type: "action",
  props: {
    app,
    model: {
      propDefinition: [
        app,
        "model",
      ],
    },
    messages: {
      type: "string[]",
      label: "Messages",
      description: "The messages of the chat, this can be used to keep a chat memory. Each row should be set as a JSON format string. Eg. `{\"role\": \"user\", \"content\": \"Hello\"}`. The message object has the following fields:\n- `role`: the role of the message, either `system`, `user`, `assistant`, or `tool`.\n- `content`: The content of the message.\n- `images` (optional): a list of images to include in the message (for multimodal models such as `llava`).\n- `tool_calls`(optional): a list of tools the model wants to use.",
    },
    tools: {
      type: "string[]",
      label: "Tools",
      description: "A list of tools the model can use. Each row should be set as a JSON format string.",
      optional: true,
    },
    options: {
      propDefinition: [
        app,
        "options",
      ],
    },
    stream: {
      propDefinition: [
        app,
        "stream",
      ],
    },
    keepAlive: {
      propDefinition: [
        app,
        "keepAlive",
      ],
    },
  },
  methods: {
    generateChatCompletion(args = {}) {
      return this.app.post({
        path: "/chat",
        ...args,
      });
    },
  },
  async run({ $ }) {
    const {
      generateChatCompletion,
      model,
      messages,
      tools,
      options,
      stream,
      keepAlive,
    } = this;

    const response = await generateChatCompletion({
      $,
      data: {
        model,
        messages: utils.parseArray(messages),
        tools: utils.parseArray(tools),
        options: utils.parseOptions(options),
        stream,
        keep_alive: keepAlive,
      },
    });

    $.export("$summary", "Successfully generated chat completion.");
    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.
Messages	`messages`	`string[]`	The messages of the chat, this can be used to keep a chat memory. Each row should be set as a JSON format string. Eg. `{"role": "user", "content": "Hello"}`. The message object has the following fields: `role`: the role of the message, either `system`, `user`, `assistant`, or `tool`. `content`: The content of the message. `images` (optional): a list of images to include in the message (for multimodal models such as `llava`). `tool_calls`(optional): a list of tools the model wants to use.
Tools	`tools`	`string[]`	A list of tools the model can use. Each row should be set as a JSON format string.
Advanced Options	`options`	`object`	Additional model parameters listed in the documentation for the Modelfile such as `temperature`
Stream	`stream`	`boolean`	If `false` the response will be returned as a single response object, rather than a stream of objects.
Keep Alive	`keepAlive`	`string`	Controls how long the model will stay loaded into memory following the request (default: 5m).

Action Authentication#

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

About Ollama#

Get up and running with large language models.

More Ways to Connect Ollama + Discord Bot#

Other Popular Integrations#

Copy Model with Ollama API on New Forum Thread Message from Discord Bot API

Discord Bot + Ollama

Generate Chat Completion with Ollama API on New Message in Channel from Discord Bot API

Pipedream makes it easy to connect APIs for Ollama, Discord Bot and 2,900+ other apps remarkably fast.

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

Developers ♥ Pipedream

1-24of2,900+apps by most popular

1
-
24
of
2,900+
apps by most popular