Analyze Text Sentiment with Google Vertex AI API on New Message Sent from SnatchBot API

Pipedream makes it easy to connect APIs for Google Vertex AI, SnatchBot and 2,500+ other apps remarkably fast.

Trigger workflow on

New Message Sent from the SnatchBot API

Next, do this

Analyze Text Sentiment with the Google Vertex 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 SnatchBot trigger and Google Vertex 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 Message Sent trigger
1. Connect your SnatchBot account
2. Configure timer
3. Configure User ID
Configure the Analyze Text Sentiment action
1. Connect your Google Vertex AI account
2. Select a Project ID
3. Configure Text
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 Sent on SnatchBot

Description:Emit new event when a new bot message is sent. [See the documentation](https://support.snatchbot.me/reference/get-message)

Version:0.0.1

Key:snatchbot-new-message-sent

View on GitHub

SnatchBot Overview#

The SnatchBot API provides a programmatic window to SnatchBot's chatbot platform, allowing you to manage and interact with your bots outside of the SnatchBot interface. With this API, you can execute tasks like sending messages, retrieving chat history, and managing your bot's structure and behavior. When integrated into Pipedream workflows, the SnatchBot API shines in automating interactions, syncing chat data with other systems, and reacting to events with custom logic and third-party services.

Trigger Code#

import snatchbot from "../../snatchbot.app.mjs";
import { DEFAULT_POLLING_SOURCE_TIMER_INTERVAL } from "@pipedream/platform";

export default {
  key: "snatchbot-new-message-sent",
  name: "New Message Sent",
  description: "Emit new event when a new bot message is sent. [See the documentation](https://support.snatchbot.me/reference/get-message)",
  version: "0.0.1",
  type: "source",
  dedupe: "unique",
  props: {
    snatchbot,
    db: "$.service.db",
    timer: {
      type: "$.interface.timer",
      default: {
        intervalSeconds: DEFAULT_POLLING_SOURCE_TIMER_INTERVAL,
      },
    },
    userId: {
      propDefinition: [
        snatchbot,
        "userId",
      ],
    },
  },
  hooks: {
    async deploy() {
      const messages = await this.getMessages();
      if (!messages.length) {
        return;
      }
      this.processMessages(messages.slice(0, 25));
    },
  },
  methods: {
    _getLastTs() {
      return this.db.get("lastTs") || 0;
    },
    _setLastTs(lastTs) {
      this.db.set("lastTs", lastTs);
    },
    generateMeta(message) {
      return {
        id: message.id,
        summary: message.message,
        ts: Date.parse(message.date),
      };
    },
    async getMessages() {
      const { messages } = await this.snatchbot.listMessages({
        params: {
          user_id: this.userId,
          message_id: 0,
        },
      });
      return messages;
    },
    processMessages(messages) {
      const lastTs = this._getLastTs();
      let maxLastTs = lastTs;

      for (const message of messages) {
        const ts = Date.parse(message.date);
        if (ts > lastTs) {
          const meta = this.generateMeta(message);
          this.$emit(message, meta);
          if (ts > maxLastTs) {
            maxLastTs = ts;
          }
        } else {
          break;
        }
      }

      this._setLastTs(maxLastTs);
    },
  },
  async run() {
    const messages = await this.getMessages();
    if (!messages.length) {
      return;
    }
    this.processMessages(messages);
  },
};

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
SnatchBot	`snatchbot`	`app`	This component uses the SnatchBot app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
	`timer`	`$.interface.timer`
User ID	`userId`	`string`	The user ID in your application

Trigger Authentication#

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

To retrieve your App ID and Secret,

Navigate to your SnatchBot account and sign in
Click on one of your Bots, then click on “Channels”
Go to “Other” > “API”

In the steps above when you click one of your bots, your Bot ID is 1234 if your Bot URL is https://account.snatchbot.me/edit/1234

About SnatchBot#

A revolutionary bot builder platform to add multi-channel messaging to your system.

Action#

Analyze Text Sentiment on Google Vertex AI

Description:Analyzes a specified text for its underlying sentiment. [See the documentation](https://cloud.google.com/vertex-ai/docs/reference/rest/v1/projects.locations.publishers.models/generateContent)

Version:0.0.1

Key:google_vertex_ai-analyze-text-sentiment

View on GitHub

Google Vertex AI Overview#

With the Google Vertex AI API, you can tap into a robust suite of AI tools offered by Google Cloud to build, deploy, and scale machine learning models. Whether you're processing data, training custom models, or using pre-trained ones, Vertex AI provides a unified platform for AI development. In Pipedream, you can create serverless workflows that interact with Vertex AI, allowing you to automate tasks like model training, prediction, and resource management without provisioning your own infrastructure.

Action Code#

import vertexAi from "../../google_vertex_ai.app.mjs";

export default {
  key: "google_vertex_ai-analyze-text-sentiment",
  name: "Analyze Text Sentiment",
  description: "Analyzes a specified text for its underlying sentiment. [See the documentation](https://cloud.google.com/vertex-ai/docs/reference/rest/v1/projects.locations.publishers.models/generateContent)",
  version: "0.0.1",
  type: "action",
  props: {
    vertexAi,
    projectId: {
      propDefinition: [
        vertexAi,
        "projectId",
      ],
    },
    text: {
      type: "string",
      label: "Text",
      description: "The content to analyze for sentiment",
    },
  },
  async run({ $ }) {
    const response = await this.vertexAi.generateContent({
      $,
      projectId: this.projectId,
      model: "gemini-1.0-pro",
      data: {
        contents: [
          {
            role: "user",
            parts: [
              {
                text: `${this.text}\nClassify the sentiment of the message:\n`,
              },
            ],
          },
        ],
      },
    });
    $.export("$summary", "Successfully analyzed text sentiment");
    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 Vertex AI	`vertexAi`	`app`	This component uses the Google Vertex AI app.
Project ID	`projectId`	`string`	Select a value from the drop down menu.
Text	`text`	`string`	The content to analyze for sentiment

Action Authentication#

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

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

emailprofilehttps://www.googleapis.com/auth/cloud-platform