Semantic Search with KodaGPT API on New Keyword Mention (Instant) from Slack API

Pipedream makes it easy to connect APIs for KodaGPT, Slack and 2,400+ other apps remarkably fast.

Trigger workflow on

New Keyword Mention (Instant) from the Slack API

Next, do this

Semantic Search with the KodaGPT 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 Slack trigger and KodaGPT action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Keyword Mention (Instant) trigger
1. Connect your Slack account
2. Optional- Select one or more Channels
3. Configure slackApphook
4. Configure Keyword
5. Optional- Configure Ignore Bots
Configure the Semantic Search action
1. Connect your KodaGPT account
2. Configure Question
3. Optional- Configure Chatbot ID
4. Configure alert
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 Keyword Mention (Instant) on Slack

Description:Emit new event when a specific keyword is mentioned in a channel

Version:0.0.5

Key:slack-new-keyword-mention

View on GitHub

Slack Overview#

The Pipedream Slack app enables you to build event-driven workflows that interact with the Slack API. Once you authorize the Pipedream app's access to your workspace, you can use Pipedream workflows to perform common Slack actions or write your own code against the Slack API.

The Pipedream Slack app is not a typical app. You don't interact with it directly as a bot, and it doesn't add custom functionality to your workspace out of the box. It makes it easier to automate anything you'd typically use the Slack API for, using Pipedream workflows.

Automate posting updates to your team channels
Create a bot to answer common questions
Integrate with your existing tools and services
And much more!

Trigger Code#

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

export default {
  ...common,
  key: "slack-new-keyword-mention",
  name: "New Keyword Mention (Instant)",
  version: "0.0.5",
  description: "Emit new event when a specific keyword is mentioned in a channel",
  type: "source",
  dedupe: "unique",
  props: {
    ...common.props,
    conversations: {
      propDefinition: [
        common.props.slack,
        "conversation",
      ],
      type: "string[]",
      label: "Channels",
      description: "Select one or more channels to monitor for new messages.",
      optional: true,
    },
    // eslint-disable-next-line pipedream/props-description,pipedream/props-label
    slackApphook: {
      type: "$.interface.apphook",
      appProp: "slack",
      async eventNames() {
        return this.conversations || [
          "message",
        ];
      },
    },
    keyword: {
      propDefinition: [
        common.props.slack,
        "keyword",
      ],
    },
    ignoreBot: {
      propDefinition: [
        common.props.slack,
        "ignoreBot",
      ],
    },
  },
  hooks: {
    ...common.hooks,
    async deploy() {
      // emit historical events
      const messages = await this.getMatches({
        query: this.keyword,
        sort: "timestamp",
      });
      const filteredMessages = this.conversations?.length > 0
        ? messages.filter((message) => this.conversations.includes(message.channel.id))
        : messages;
      await this.emitHistoricalEvents(filteredMessages.slice(-25).reverse());
    },
  },
  methods: {
    ...common.methods,
    async getMatches(params) {
      return (await this.slack.searchMessages(params)).messages.matches || [];
    },
    async emitHistoricalEvents(messages) {
      for (const message of messages) {
        const event = await this.processEvent({
          ...message,
          subtype: message.subtype || constants.SUBTYPE.PD_HISTORY_MESSAGE,
        });
        if (event) {
          if (!event.client_msg_id) {
            event.pipedream_msg_id = `pd_${Date.now()}_${Math.random().toString(36)
              .substr(2, 10)}`;
          }

          this.$emit(event, {
            id: event.client_msg_id || event.pipedream_msg_id,
            summary: this.getSummary(event),
            ts: event.event_ts || Date.now(),
          });
        }
      }
    },
    getSummary() {
      return "New keyword mention received";
    },
    async processEvent(event) {
      const {
        type: msgType,
        subtype,
        bot_id: botId,
        text,
      } = event;

      if (msgType !== "message") {
        console.log(`Ignoring event with unexpected type "${msgType}"`);
        return;
      }

      // This source is designed to just emit an event for each new message received.
      // Due to inconsistencies with the shape of message_changed and message_deleted
      // events, we are ignoring them for now. If you want to handle these types of
      // events, feel free to change this code!!
      if (subtype && !constants.ALLOWED_SUBTYPES.includes(subtype)) {
        console.log(`Ignoring message with subtype. "${subtype}"`);
        return;
      }

      if ((this.ignoreBot) && (subtype === constants.SUBTYPE.BOT_MESSAGE || botId)) {
        return;
      }

      let emitEvent = false;
      if (text.indexOf(this.keyword) !== -1) {
        emitEvent = true;
      } else if (subtype === constants.SUBTYPE.PD_HISTORY_MESSAGE) {
        emitEvent = true;
      }

      if (emitEvent) {
        return event;
      }
    },
  },
  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
Slack	`slack`	`app`	This component uses the Slack app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
Channels	`conversations`	`string[]`	Select a value from the drop down menu.
	`slackApphook`	`$.interface.apphook`
Keyword	`keyword`	`string`	Keyword to monitor
Ignore Bots	`ignoreBot`	`boolean`	Ignore messages from bots

Trigger Authentication#

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

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

channels:historychannels:readchannels:writeemoji:readgroups:historygroups:readgroups:writeim:historyim:readim:writelinks:readlinks:writempim:historympim:readmpim:writereactions:readreactions:writereminders:readreminders:writestars:readteam:readusergroups:readusergroups:writeusers:readusers:read.emailusers:writechat:write:botchat:write:userfiles:write:usercommandsusers.profile:writeusers.profile:read

About Slack#

Slack is a channel-based messaging platform. With Slack, people can work together more effectively, connect all their software tools and services, and find the information they need to do their best work — all within a secure, enterprise-grade environment.

Action#

Semantic Search on KodaGPT

Description:Perform a semantic search within chatbot data [See the documentation](https://kodagpt.readme.io/reference/buscas-semanticas)

Version:0.0.1

Key:kodagpt-semantic-search

View on GitHub

KodaGPT Overview#

The KodaGPT API offers a versatile platform for integrating advanced language processing into your applications, enabling the automation of text-based tasks and enhancing user interactions through natural language understanding. With its capabilities, developers can create dynamic content, automate responses, and analyze text on-the-fly. Leveraging Pipedream's robust integration platform, users can connect KodaGPT with other services to design complex workflows that simplify operations, improve efficiency, and deliver personalized experiences.

Action Code#

import app from "../../kodagpt.app.mjs";

export default {
  key: "kodagpt-semantic-search",
  name: "Semantic Search",
  description: "Perform a semantic search within chatbot data [See the documentation](https://kodagpt.readme.io/reference/buscas-semanticas)",
  version: "0.0.1",
  type: "action",
  props: {
    app,
    question: {
      propDefinition: [
        app,
        "question",
      ],
    },
    chatbotId: {
      propDefinition: [
        app,
        "chatbotId",
      ],
      optional: true,
    },
    alert: {
      type: "alert",
      alertType: "info",
      content: "Bot ID is required if you don't specify Bot ID on the connection popup",
    },
  },
  async run({ $ }) {
    const response = await this.app.semanticSearch({
      $,
      question: this.question,
      chatbotId: this.chatbotId,
    });

    $.export("$summary", `Successfully generated '${response.length}' answers`);

    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
KodaGPT	`app`	`app`	This component uses the KodaGPT app.
Question	`question`	`string`	The question to ask the chatbot
Chatbot ID	`chatbotId`	`string`	To get your Chatbot ID, sign in, go to "Integrations". Copy your Chatbot ID from "My Chatbots".

Semantic Search with KodaGPT API on New Keyword Mention (Instant) from Slack API

Pipedream makes it easy to connect APIs for KodaGPT, Slack 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