Classify Items into Categories with OpenAI (ChatGPT) API on New Email from IMAP API

Pipedream makes it easy to connect APIs for OpenAI (ChatGPT), IMAP and 2,400+ other apps remarkably fast.

Trigger workflow on

New Email from the IMAP API

Next, do this

Classify Items into Categories with the OpenAI (ChatGPT) 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 IMAP 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 Email trigger
1. Connect your IMAP account
2. Configure Polling interval
3. Select a Mailbox
Configure the Classify Items into Categories action
1. Connect your OpenAI (ChatGPT) account
2. Select a Model
3. Optional- Configure Max Tokens
4. Optional- Configure Temperature
5. Optional- Configure Top P
6. Optional- Configure N
7. Optional- Configure Stop
8. Optional- Configure Presence Penalty
9. Optional- Configure Frequency Penalty
10. Optional- Configure User
11. Configure info
12. Configure Items
13. 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 Email on IMAP

Description:Emit new event for each new email in a mailbox

Version:0.0.4

Key:imap-new-email

View on GitHub

IMAP Overview#

Using Pipedream's IMAP API, developers can automate interactions with their email inbox, enabling serverless workflows that perform actions based on incoming emails. This could include parsing email contents, triggering events upon receiving emails from specific senders, attaching labels, and much more. By leveraging IMAP, Pipedream can act as a bridge between your email and other services, streamlining processes that would otherwise require manual intervention.

Trigger Code#

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

/**
 * Creates an IMAP server connection and emits emails added to a mailbox after the last emitted
 * email.
 */
export default {
  key: "imap-new-email",
  name: "New Email",
  description: "Emit new event for each new email in a mailbox",
  version: "0.0.4",
  type: "source",
  dedupe: "unique",
  props: {
    imap,
    db: "$.service.db",
    timer: {
      label: "Polling interval",
      description:
        "Pipedream will poll the IMAP server for new emails at this interval",
      type: "$.interface.timer",
      default: {
        intervalSeconds: DEFAULT_POLLING_SOURCE_TIMER_INTERVAL,
      },
    },
    mailbox: {
      propDefinition: [
        imap,
        "mailbox",
      ],
    },
  },
  methods: {
    _getLastUid(mailbox) {
      return this.db.get(`lastUid-${mailbox}`);
    },
    _setLastUid(mailbox, lastUid) {
      this.db.set(`lastUid-${mailbox}`, lastUid);
    },
    _getUidValidity(mailbox) {
      return this.db.get(`uidValidity-${mailbox}`);
    },
    _setUidValidity(mailbox, uidValidity) {
      this.db.set(`uidValidity-${mailbox}`, uidValidity);
    },
    _handleUidValidityChange(mailbox, uidValidity) {
      this._setUidValidity(mailbox, uidValidity);
      this._setLastUid(mailbox, null);
    },
    hasNewMessages(box) {
      const lastUid = this._getLastUid(box.name);
      return !lastUid || box.uidnext > lastUid + 1;
    },
    generateMeta(message) {
      const date = message.attributes?.date ?? new Date();
      const ts = Date.parse(date);
      return {
        id: `${message.attributes?.uid}-${ts}`,
        ts,
        summary: message.mail?.subject,
      };
    },
    processMessage(message) {
      const lastUid = message.attributes?.uid ?? lastUid;
      this._setLastUid(this.mailbox, lastUid);
      this.$emit(message.mail, this.generateMeta(message));
    },
    async processMessageStream(stream) {
      for await (const message of stream) {
        this.processMessage(message);
      }
    },
    async getHistoricalEvents() {
      const { mailbox } = this;
      const connection = await this.imap.getConnection();
      try {
        const box = await this.imap.openMailbox(connection, mailbox);
        const startSeqno = box.messages.total > 25
          ? box.messages.total - 24
          : 1;
        const messageStream = this.imap.fetchMessages(connection, {
          startSeqno,
        });
        await this.processMessageStream(messageStream);
      } finally {
        await this.imap.closeConnection(connection);
      }
    },
  },
  hooks: {
    async deploy() {
      await this.getHistoricalEvents();
    },
  },
  async run() {
    const { mailbox } = this;
    const connection = await this.imap.getConnection();

    try {
      const box = await this.imap.openMailbox(connection, mailbox);

      const uidValidity = this._getUidValidity(box.name);
      if (uidValidity !== box.uidvalidity) {
        this._handleUidValidityChange(box.name, box.uidvalidity);
      }

      if (!this.hasNewMessages(box)) {
        console.log("No new messages since last run");
        return;
      }

      const lastUid = this._getLastUid(box.name);

      // Fetch messages after lastUid if it exists, or most recent message otherwise
      const messageStream = this.imap.fetchMessages(connection, {
        startUid: lastUid && lastUid + 1,
        startSeqno: box.messages.total,
      });
      await this.processMessageStream(messageStream);
    } finally {
      await this.imap.closeConnection(connection);
    }
  },
};

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
IMAP	`imap`	`app`	This component uses the IMAP app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
Polling interval	`timer`	`$.interface.timer`	Pipedream will poll the IMAP server for new emails at this interval
Mailbox	`mailbox`	`string`	Select a value from the drop down menu.

Trigger Authentication#

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

Below are the required fields to connect your IMAP account to Pipedream:

host: Enter the host Pipedream should connect to. Refer to your email provider's IMAP instructions if you aren't sure what to enter.
email: Enter the email address you use to sign in to the account you'd like to connect.
password: This is the password you use to sign in to your email account. Note: in order to connect a Gmail account, you must use an App Password.
port: Specify the port number, either 143 (default) or 993. Refer to your email provider's IMAP instructions if you aren't sure which to use.

For Gmail accounts, refer to these instructions.

About IMAP#

Connect Pipedream to any IMAP email provider to trigger custom workflows.

Action#

Classify Items into Categories on OpenAI (ChatGPT)

Description:Classify items into specific categories using the Chat API. [See the documentation](https://platform.openai.com/docs/api-reference/chat)

Version:0.1.2

Key:openai-classify-items-into-categories

View on GitHub

OpenAI (ChatGPT) Overview#

OpenAI provides a suite of powerful AI models through its API, enabling developers to integrate advanced natural language processing and generative capabilities into their applications. Here’s an overview of the services offered by OpenAI's API:

Use Python or Node.js code to make fully authenticated API requests with your OpenAI account:

Action Code#

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

export default {
  ...common,
  name: "Classify Items into Categories",
  version: "0.1.2",
  key: "openai-classify-items-into-categories",
  description: "Classify items into specific categories using the Chat API. [See the documentation](https://platform.openai.com/docs/api-reference/chat)",
  type: "action",
  props: {
    ...common.props,
    info: {
      type: "alert",
      alertType: "info",
      content: `Provide a list of **items** and a list of **categories**. The output will contain an array of objects, each with properties \`item\` and \`category\`
        \nExample:
        \nIf **Categories** is \`["people", "pets"]\`, and **Items** is \`["dog", "George Washington"]\`
        \n The output will contain the following categorizations:
        \n \`[{"item":"dog","category":"pets"},{"item":"George Washington","category":"people"}]\`
      `,
    },
    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 responses = response.choices?.map(({ message }) => message.content);
      const categorizations = [];
      for (const response of responses) {
        try {
          categorizations.push(JSON.parse(response));
        } catch (err) {
          console.log("Failed to parse output, assistant returned malformed JSON");
        }
      }
      const output = {
        messages,
      };
      if (this.n > 1) {
        output.categorizations = categorizations;
      } else {
        output.categorizations = categorizations[0];
      }
      return output;
    },
  },
};

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.
Model	`modelId`	`string`	Select a value from the drop down menu.
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

Classify Items into Categories with OpenAI (ChatGPT) API on New Email from IMAP API

Pipedream makes it easy to connect APIs for OpenAI (ChatGPT), IMAP 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