Classify Items into Categories with OpenAI (ChatGPT) API on New NPS Ratings from UserVoice API

Pipedream makes it easy to connect APIs for OpenAI (ChatGPT), UserVoice and 1400+ other apps remarkably fast.

Trigger workflow on

New NPS Ratings from the UserVoice API

Next, do this

Classify Items into Categories with the OpenAI (ChatGPT) API

No credit card required

▶

Watch us build a workflow

7 min

Watch now ➜

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

Developers ♥ Pipedream

Getting Started#

This integration creates a workflow with a UserVoice trigger and OpenAI (ChatGPT) action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New NPS Ratings trigger
1. Connect your UserVoice account
2. Configure Polling schedule
Configure the Classify Items into Categories action
1. Connect your OpenAI (ChatGPT) account
2. Optional- Configure Max Tokens
3. Optional- Configure Temperature
4. Optional- Configure Top P
5. Optional- Configure N
6. Optional- Configure Stop
7. Optional- Configure Presence Penalty
8. Optional- Configure Frequency Penalty
9. Optional- Configure User
10. Configure Items
11. Configure Categories
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 NPS Ratings on UserVoice

Description:Emits new NPS ratings submitted through the UserVoice NPS widget. On first run, emits up to 10 sample NPS ratings users have previously submitted.

Version:0.0.4

Key:uservoice-new-nps-ratings

View on GitHub

UserVoice Overview#

Using the UserVoice API, developers can build powerful customer service tools
to improve the service your organization provides to its customers. Here are
just a few of the possibilities:

Create a custom portal, allowing your customers to submit and manage their
requests, as well as track their progress, all within your own branded
domain.
Integrate UserVoice with your existing customer service software, enabling
customers to better track their inquiries and quickly provide feedback on
their experiences.
Design branded surveys to gather feedback from customers and gain insight
about how to improve your customer service.
Automate customer service processes to ensure each customer's inquiries are
handled quickly and efficiently.
Use data from the UserVoice API to gain valuable insights into your customer
service performance.

These are just a few of the possibilities that can be accomplished through the
UserVoice API. With its comprehensive suite of features, your organization will
be able to provide exceptional customer service experiences and better serve
your customers.

Trigger Code#

const uservoice = require("../../uservoice.app.js");
const { DEFAULT_POLLING_SOURCE_TIMER_INTERVAL } = require("@pipedream/platform");

const NUM_SAMPLE_RESULTS = 10;

module.exports = {
  name: "New NPS Ratings",
  version: "0.0.4",
  key: "uservoice-new-nps-ratings",
  description: `Emits new NPS ratings submitted through the UserVoice NPS widget. On first run, emits up to ${NUM_SAMPLE_RESULTS} sample NPS ratings users have previously submitted.`,
  dedupe: "unique",
  type: "source",
  props: {
    uservoice,
    timer: {
      label: "Polling schedule",
      description:
        "Pipedream will poll the UserVoice API for new NPS ratings on this schedule",
      type: "$.interface.timer",
      default: {
        intervalSeconds: DEFAULT_POLLING_SOURCE_TIMER_INTERVAL,
      },
    },
    db: "$.service.db",
  },
  hooks: {
    async deploy() {
      // Emit sample records on the first run
      const { npsRatings } = await this.uservoice.listNPSRatings({
        numSampleResults: NUM_SAMPLE_RESULTS,
      });
      this.emitWithMetadata(npsRatings);
    },
  },
  methods: {
    emitWithMetadata(ratings) {
      for (const rating of ratings) {
        const {
          id, rating: score, body, created_at,
        } = rating;
        const summary = body && body.length
          ? `${score} - ${body}`
          : `${score}`;
        this.$emit(rating, {
          summary,
          id,
          ts: +new Date(created_at),
        });
      }
    },
  },
  async run() {
    let updated_after =
      this.db.get("updated_after") || new Date().toISOString();
    const {
      npsRatings, maxUpdatedAt,
    } = await this.uservoice.listNPSRatings({
      updated_after,
    });
    this.emitWithMetadata(npsRatings);

    if (maxUpdatedAt) {
      updated_after = maxUpdatedAt;
    }
    this.db.set("updated_after", updated_after);
  },
};

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
UserVoice	`uservoice`	`app`	This component uses the UserVoice app.
Polling schedule	`timer`	`$.interface.timer`	Pipedream will poll the UserVoice API for new NPS ratings on this schedule
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.

Trigger Authentication#

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

To connect to the UserVoice API, create a trusted API client. In your UserVoice Admin Console, navigate to Settings → Integrations → UserVoice API keys and click the button to Add API Key. Add a name and check the Trusted box at the bottom of the modal that appears:

Then, generate an access token by clicking the Create button near the right of the details of the API key:

Enter that access token below.

Finally, enter your UserVoice subdomain, which can be found in the URL of your instance: https://SUBDOMAIN.uservoice.com/

About UserVoice#

User feedback made easy and actionable

Action#

Classify Items into Categories on OpenAI (ChatGPT)

Description:Classify items into specific categories using the Chat API

Version:0.0.4

Key:openai-classify-items-into-categories

View on GitHub

OpenAI (ChatGPT) Overview#

The OpenAI API is a powerful tool that provides access to a range of
high-powered machine learning models. With the OpenAI API, developers can
create products, services, and tools that enable humanizing AI experiences, and
build applications that extend the power of human language.

Using the OpenAI API, developers can create language-driven applications such
as:

Natural language understanding and sentiment analysis
Text-based search
Question answering
Dialogue systems and conversation agents
Intelligent text completion
Text summarization
Text classification
Machine translation
Language generation
Multi-factor authentication
Anomaly detection
Text analysis

Action Code#

import common from "../common/common-helper.mjs";

export default {
  ...common,
  name: "Classify Items into Categories",
  version: "0.0.4",
  key: "openai-classify-items-into-categories",
  description: "Classify items into specific categories using the Chat API",
  type: "action",
  props: {
    ...common.props,
    items: {
      label: "Items",
      description: "Items to categorize",
      type: "string[]",
    },
    categories: {
      label: "Categories",
      description: "Categories to classify items into",
      type: "string[]",
    },
  },
  methods: {
    ...common.methods,
    systemInstructions() {
      return "Your goal is to categorize items into specific categories and produce ONLY JSON. The user will provide both the items and categories. Please only categorize items into the specific categories, and no others, and output ONLY JSON.";
    },
    outputFormat() {
      return "Please only categorize items into the specific categories, and no others. Output a valid JSON string — an array of objects, where each object has the following properties: item, category. Do not return any English text other than the JSON, either before or after the JSON. I need to parse the response as JSON, and parsing will fail if you return any English before or after the JSON";
    },
    userMessage() {
      return `Categorize each of the following items:\n\n${this.items.join("\n")}\n\ninto one of the following categories:\n\n${this.categories.join("\n")}\n\n${this.outputFormat()}}`;
    },
    summary() {
      return `Categorized ${this.items.length} items into ${this.categories.length} categories`;
    },
    formatOutput({
      messages, response,
    }) {
      if (!messages || !response) {
        throw new Error("Invalid API output, please reach out to https://pipedream.com/support");
      }
      const assistantResponse = response.choices?.[0]?.message?.content;
      let categorizations = assistantResponse;
      try {
        categorizations = JSON.parse(assistantResponse);
      } catch (err) {
        console.log("Failed to parse output, assistant returned malformed JSON");
      }
      return {
        categorizations,
        messages,
      };
    },
  },
};

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
OpenAI (ChatGPT)	`openai`	`app`	This component uses the OpenAI (ChatGPT) app.
Max Tokens	`maxTokens`	`integer`	The maximum number of tokens to generate in the completion.
Temperature	`temperature`	`string`	Optional. What sampling temperature to use. Higher values means the model will take more risks. Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer.
Top P	`topP`	`string`	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.
N	`n`	`integer`	How many completions to generate for each prompt
Stop	`stop`	`string[]`	Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
Presence Penalty	`presencePenalty`	`string`	Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
Frequency Penalty	`frequencyPenalty`	`string`	Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
User	`user`	`string`	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more here.
Items	`items`	`string[]`	Items to categorize
Categories	`categories`	`string[]`	Categories to classify items into