← Gmail + OpenAI (ChatGPT) integrations

Chat with OpenAI (ChatGPT) API on New Email Received from Gmail API

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

Trigger workflow on
New Email Received from the Gmail API
Next, do this
Chat with the OpenAI (ChatGPT) API
No credit card required
Intro to Pipedream
Watch us build a workflow
Watch us build a workflow
8 min
Watch now ➜

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

Adyen logo
Appcues logo
Bandwidth logo
Checkr logo
ChartMogul logo
Dataminr logo
Gopuff logo
Gorgias logo
LinkedIn logo
Logitech logo
Replicated logo
Rudderstack logo
SAS logo
Scale AI logo
Webflow logo
Warner Bros. logo
Adyen logo
Appcues logo
Bandwidth logo
Checkr logo
ChartMogul logo
Dataminr logo
Gopuff logo
Gorgias logo
LinkedIn logo
Logitech logo
Replicated logo
Rudderstack logo
SAS logo
Scale AI logo
Webflow logo
Warner Bros. logo

Developers Pipedream

Getting Started

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

  1. Select this integration
  2. Configure the New Email Received trigger
    1. Connect your Gmail account
    2. Select a Trigger Type
    3. Optional- Configure Service Account Key JSON
    4. Configure serviceAccountKeyJsonInstructions
    5. Optional- Select a Pub/Sub Topic
    6. Optional- Select a Pub/Sub Topic Name
    7. Optional- Select a Label
    8. Configure permissionAlert
    9. Configure latencyWarningAlert
  3. Configure the Chat action
    1. Connect your OpenAI (ChatGPT) account
    2. Select a Model
    3. Configure User Message
    4. Optional- Configure Max Tokens
    5. Optional- Configure Temperature
    6. Optional- Configure Top P
    7. Optional- Configure N
    8. Optional- Configure Stop
    9. Optional- Configure Presence Penalty
    10. Optional- Configure Frequency Penalty
    11. Optional- Configure User
    12. Optional- Configure System Instructions
    13. Optional- Configure Prior Message History
    14. Optional- Configure Images
    15. Optional- Configure Audio
    16. Optional- Select a Response Format
    17. Optional- Select one or more Tool Types
  4. Deploy the workflow
  5. Send a test event to validate your setup
  6. 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

Description:Emit new event when a new email is received.
Version:0.1.9
Key:gmail-new-email-received

New Email Received Overview

The Gmail - New Email Received (Instant) source enables you to trigger Pipedream workflows based on real-time changes to your Gmail inbox.

Trigger Code

import gmail from "../../gmail.app.mjs";
import common from "../common/polling-history.mjs";
import {
  axios,
  DEFAULT_POLLING_SOURCE_TIMER_INTERVAL,
  ConfigurationError,
} from "@pipedream/platform";
import { PubSub } from "@google-cloud/pubsub";
import { v4 as uuidv4 } from "uuid";
import verifyClient from "../common/verify-client-id.mjs";

export default {
  ...common,
  key: "gmail-new-email-received",
  name: "New Email Received",
  description: "Emit new event when a new email is received.",
  type: "source",
  version: "0.1.9",
  dedupe: "unique",
  props: {
    gmail,
    db: "$.service.db",
    triggerType: {
      type: "string",
      label: "Trigger Type",
      options: [
        "webhook",
        "polling",
      ],
      description:
        "Configuring this source as a `webhook` (instant) trigger requires a custom OAuth client. [Refer to the guide here to get started](https://pipedream.com/apps/gmail/#getting-started).",
      reloadProps: true,
    },
    serviceAccountKeyJson: {
      type: "string",
      label: "Service Account Key JSON",
      optional: true,
      hidden: true,
      reloadProps: true,
    },
    serviceAccountKeyJsonInstructions: {
      type: "alert",
      alertType: "info",
      content: `1) [Create a service account in GCP](https://cloud.google.com/iam/docs/creating-managing-service-accounts) and set the following permission: **Pub/Sub Admin**
        \n2) [Generate a service account key](https://cloud.google.com/iam/docs/creating-managing-service-account-keys)
        \n3) Download the key details in JSON format
        \n4) Open the JSON in a text editor, and **copy and paste its contents here**.
      `,
      hidden: true,
    },
    topicType: {
      type: "string",
      label: "Pub/Sub Topic",
      description:
        "Do you have an existing Pub/Sub topic, or would you like to create a new one?",
      options: [
        "existing",
        "new",
      ],
      optional: true,
      hidden: true,
      reloadProps: true,
    },
    topic: {
      type: "string",
      label: "Pub/Sub Topic Name",
      description: "Select a Pub/Sub topic from your GCP account to watch",
      async options() {
        return this.getTopics();
      },
      optional: true,
      hidden: true,
      reloadProps: true,
    },
    label: {
      propDefinition: [
        gmail,
        "label",
      ],
      default: "INBOX",
      optional: true,
      hidden: true,
    },
    permissionAlert: {
      type: "alert",
      alertType: "error",
      content: `Unable to grant publish permission to Gmail API service account.
      \n1. Navigate to your [Google Cloud PubSub Topics List](https://console.cloud.google.com/cloudpubsub)
      \n2. Select "View Permissions" for the topic you intend to use for this source.
      \n3. Click "ADD PRINCIPAL"
      \n4. Select "Pub/Sub Publisher" for the Role.
      \n5. Enter \`serviceAccount:gmail-api-push@system.gserviceaccount.com\` as the principal. 
      \n6. Click "Save"
      `,
      hidden: true,
    },
    latencyWarningAlert: {
      type: "alert",
      alertType: "warning",
      content:
        "Please allow up to 1 minute for deployment. We're setting up your real-time email notifications behind the scenes.",
      hidden: true,
    },
  },
  async additionalProps(props) {
    const newProps = {};
    if (this.triggerType === "polling") {
      newProps.timer = {
        type: "$.interface.timer",
        default: {
          intervalSeconds: DEFAULT_POLLING_SOURCE_TIMER_INTERVAL,
        },
      };
    }
    if (this.triggerType === "webhook") {
      // verify that a Custom OAuth client is being used
      const isValidClientId = await this.checkClientId();
      if (!isValidClientId) {
        throw new ConfigurationError(
          "Configuring this source as a `webhook` (instant) trigger requires a custom OAuth client. [Refer to the guide here to get started](https://pipedream.com/apps/gmail/#getting-started).",
        );
      }

      newProps.http = {
        type: "$.interface.http",
        customResponse: true,
      };
      newProps.timer = {
        type: "$.interface.timer",
        default: {
          intervalSeconds: 60 * 60,
        },
        hidden: true,
      };

      props.serviceAccountKeyJson.hidden = false;
      props.serviceAccountKeyJson.optional = false;
      props.serviceAccountKeyJsonInstructions.hidden = false;

      if (!this.serviceAccountKeyJson) {
        return newProps;
      }

      props.topicType.hidden = false;
      props.topicType.optional = false;

      if (!this.topicType) {
        return newProps;
      }

      // create topic prop
      let topicName = this.topic;
      if (this.topicType === "new") {
        const authKeyJSON = JSON.parse(this.serviceAccountKeyJson);
        const { project_id: projectId } = authKeyJSON;
        topicName = `projects/${projectId}/topics/${this.convertNameToValidPubSubTopicName(
          uuidv4(),
        )}`;
        props.topic.default = topicName;
        props.topic.reloadProps = false;
      } else {
        props.topic.hidden = false;
        props.topic.optional = false;
      }

      if (this.topic || this.topicType === "new") {
        const topic = await this.getOrCreateTopic(topicName);

        // Retrieves the IAM policy for the topic
        let hasPublisherRole;
        try {
          const [
            policy,
          ] = await topic.iam.getPolicy();
          hasPublisherRole = policy.bindings.find(
            ({
              members, role,
            }) =>
              members.includes(
                "serviceAccount:gmail-api-push@system.gserviceaccount.com",
              ) && role === "roles/pubsub.publisher",
          );
        } catch {
          console.log("Could not retrieve iam policy");
        }

        if (!hasPublisherRole) {
          // Grant publish permission to Gmail API service account
          try {
            await topic.iam.setPolicy({
              bindings: [
                {
                  role: "roles/pubsub.publisher",
                  members: [
                    "serviceAccount:gmail-api-push@system.gserviceaccount.com",
                  ],
                },
              ],
            });
            console.log("Permissions granted to Gmail API service account.");
          } catch {
            props.permissionAlert.hidden = false;
            return newProps;
          }
        }

        props.latencyWarningAlert.hidden = false;

        const {
          historyId, expiration,
        } = await this.setupGmailNotifications(topicName);
        newProps.initialHistoryId = {
          type: "string",
          default: historyId,
          hidden: true,
        };
        newProps.expiration = {
          type: "string",
          default: expiration,
          hidden: true,
        };
      }
    }
    props.label.hidden = false;
    return newProps;
  },
  hooks: {
    ...common.hooks,
    async activate() {
      if (this.triggerType === "polling") {
        return;
      }

      const sdkParams = this.sdkParams();
      const pubSubClient = new PubSub(sdkParams);

      const currentTopic = {
        name: this.topic,
      };

      // Create subscription
      const pushEndpoint = this.http.endpoint;
      const subscriptionName =
        this.convertNameToValidPubSubTopicName(pushEndpoint);
      const subscriptionOptions = {
        pushConfig: {
          pushEndpoint,
        },
      };
      const [
        subscriptionResult,
      ] = await pubSubClient
        .topic(currentTopic.name)
        .createSubscription(subscriptionName, subscriptionOptions);
      this._setSubscriptionName(subscriptionResult.name);
    },
    async deactivate() {
      if (this.triggerType === "polling") {
        return;
      }

      const sdkParams = this.sdkParams();
      const pubSubClient = new PubSub(sdkParams);

      const subscriptionName = this._getSubscriptionName();
      if (subscriptionName) {
        await pubSubClient.subscription(subscriptionName).delete();
      }
    },
  },
  methods: {
    ...verifyClient.methods,
    ...common.methods,
    _getTopicName() {
      return this.db.get("topicName");
    },
    _setTopicName(topicName) {
      this.db.set("topicName", topicName);
    },
    _getSubscriptionName() {
      return this.db.get("subscriptionName");
    },
    _setSubscriptionName(subscriptionName) {
      this.db.set("subscriptionName", subscriptionName);
    },
    _getLastProcessedHistoryId() {
      return this.db.get("lastProcessedHistoryId");
    },
    _setLastProcessedHistoryId(lastProcessedHistoryId) {
      this.db.set("lastProcessedHistoryId", lastProcessedHistoryId);
    },
    _getExpiration() {
      return this.db.get("expiration");
    },
    _setExpiration(expiration) {
      this.db.set("expiration", expiration);
    },
    _getLastReceivedTime() {
      return this.db.get("lastReceivedTime");
    },
    _setLastReceivedTime(lastReceivedTime) {
      this.db.set("lastReceivedTime", lastReceivedTime);
    },
    sdkParams() {
      const authKeyJSON = JSON.parse(this.serviceAccountKeyJson);
      const {
        project_id: projectId, client_email, private_key,
      } = authKeyJSON;
      const sdkParams = {
        credentials: {
          client_email,
          private_key,
        },
        projectId,
      };
      return sdkParams;
    },
    async getTopics() {
      const sdkParams = this.sdkParams();
      const pubSubClient = new PubSub(sdkParams);
      const topics = (await pubSubClient.getTopics())[0];
      if (topics.length > 0) {
        return topics.map((topic) => topic.name);
      }
      return [];
    },
    convertNameToValidPubSubTopicName(name) {
      // For valid names, see https://cloud.google.com/pubsub/docs/admin#resource_names
      return (
        name
          // Must not start with `goog`. We add a `pd-` at the beginning if that's the case.
          .replace(/(^goog.*)/g, "pd-$1")
          // Must start with a letter, otherwise we add `pd-` at the beginning.
          .replace(/^(?![a-zA-Z]+)/, "pd-")
          // Only certain characters are allowed, the rest will be replaced with a `-`.
          .replace(/[^a-zA-Z0-9_\-.~+%]+/g, "-")
      );
    },
    makeRequest({
      $ = this, path, ...opts
    }) {
      return axios($, {
        url: `https://gmail.googleapis.com/gmail/v1${path}`,
        headers: {
          Authorization: `Bearer ${this.gmail.getToken()}`,
        },
        ...opts,
      });
    },
    async setupGmailNotifications(topicName) {
      // Set up Gmail push notifications using OAuth token
      const watchResponse = await this.makeRequest({
        method: "POST",
        path: "/users/me/watch",
        data: {
          topicName,
          labelIds: [
            this.label || "INBOX",
          ],
        },
      });
      console.log("Watch response:", watchResponse);
      return watchResponse;
    },
    async getOrCreateTopic(name) {
      const sdkParams = this.sdkParams();
      const pubSubClient = new PubSub(sdkParams);
      const topicName = name || this.topic;
      // Create or get Pub/Sub topic
      let topic;
      try {
        [
          topic,
        ] = await pubSubClient.createTopic(topicName);
        console.log(`Topic ${topicName} created.`);
      } catch (error) {
        if (error.code === 6) {
          // Already exists
          topic = pubSubClient.topic(topicName);
        } else {
          throw error;
        }
      }
      return topic;
    },
    getHistoryTypes() {
      return [
        "messageAdded",
      ];
    },
    generateMeta(message) {
      return {
        id: message.id,
        summary: message.snippet,
        ts: +message.internalDate,
      };
    },
    filterHistory(history) {
      return this.label
        ? history.filter(
          (item) =>
            item.messagesAdded?.length &&
              item.messagesAdded[0].message.labelIds &&
              item.messagesAdded[0].message.labelIds.includes(this.label),
        )
        : history.filter((item) => item.messagesAdded?.length);
    },
    async getMessageDetails(ids) {
      const messages = await Promise.all(ids.map(async (id) => {
        try {
          const message = await this.gmail.getMessage({
            id,
          });
          return message;
        } catch {
          console.log(`Could not find message ${id}`);
          return null;
        }
      }));
      return messages;
    },
    getHistoryResponse(startHistoryId) {
      return this.gmail.listHistory({
        startHistoryId,
        historyTypes: [
          "messageAdded",
        ],
        labelId: this.label,
      });
    },
  },
  async run(event) {
    if (this.triggerType === "polling") {
      let lastHistoryId = this._getLastHistoryId();

      if (!lastHistoryId) {
        lastHistoryId = await this.getHistoryId();
      }
      await this.emitHistories(lastHistoryId);
    }

    if (this.triggerType === "webhook") {
      if (event.timestamp) {
        // event was triggered by timer
        const topicName = this._getTopicName();
        if (topicName) {
          // renew Gmail push notifications if expiring within the next hour
          // or if no email has been received within the last hour
          const currentExpiration = this._getExpiration();
          const lastReceivedTime = this._getLastReceivedTime();
          if (
            (+currentExpiration < (event.timestamp + 3600) * 1000)
            || (lastReceivedTime < (event.timestamp - 3600) * 1000)
          ) {
            const { expiration } = await this.setupGmailNotifications(topicName);
            this._setExpiration(expiration);
          }
          return;
        } else {
          // first run, no need to renew push notifications
          this._setTopicName(this.topic);
          const initialHistoryId = this.initialHistoryId || this._getLastHistoryId();
          this._setLastProcessedHistoryId(initialHistoryId);
          this._setExpiration(this.expiration);
          return;
        }
      }

      this.http.respond({
        status: 200,
      });

      // Extract the Pub/Sub message data
      const pubsubMessage = event.body.message;
      if (!pubsubMessage) {
        return;
      }
      const decodedData = JSON.parse(
        Buffer.from(pubsubMessage.data, "base64").toString(),
      );

      console.log("Decoded Pub/Sub data:", decodedData);

      const { historyId: receivedHistoryId } = decodedData;

      // Retrieve the last processed historyId
      const lastProcessedHistoryId = this._getLastProcessedHistoryId();
      console.log("Last processed historyId:", lastProcessedHistoryId);

      // Use the minimum of lastProcessedHistoryId and the received historyId
      let startHistoryId = Math.min(
        parseInt(lastProcessedHistoryId),
        parseInt(receivedHistoryId),
      );
      console.log("Using startHistoryId:", startHistoryId);

      // Fetch the history
      let historyResponse;
      try {
        historyResponse = await this.getHistoryResponse(startHistoryId);
      } catch {
        // catch error thrown if startHistoryId is invalid or expired

        // emit recent messages to attempt to avoid missing any messages
        await this.emitRecentMessages();

        // set startHistoryId to the historyId received from the webhook
        startHistoryId = parseInt(receivedHistoryId);
        console.log("Using startHistoryId:", startHistoryId);
        historyResponse = await this.getHistoryResponse(startHistoryId);
      }

      console.log(
        "History response:",
        JSON.stringify(historyResponse, null, 2),
      );

      // Process history to find new messages
      const newMessages = [];
      if (historyResponse.history) {
        for (const historyItem of historyResponse.history) {
          if (historyItem.messagesAdded) {
            newMessages.push(
              ...historyItem.messagesAdded.map((msg) => msg.message),
            );
          }
        }
      }

      console.log("New messages found:", newMessages.length);

      // Fetch full message details for new messages
      const newMessageIds = newMessages?.map(({ id }) => id) || [];
      const messageDetails = await this.getMessageDetails(newMessageIds);

      if (!messageDetails?.length) {
        return;
      }

      console.log("Fetched message details count:", messageDetails.length);

      // Store the latest historyId in the db
      const latestHistoryId = historyResponse.historyId || receivedHistoryId;
      this._setLastProcessedHistoryId(latestHistoryId);
      console.log("Updated lastProcessedHistoryId:", latestHistoryId);

      this._setLastReceivedTime(Date.now());

      messageDetails.forEach((message) => {
        if (message?.id) {
          this.emitEvent(message);
        }
      });
    }
  },
};

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.
LabelPropTypeDescription
GmailgmailappThis component uses the Gmail app.
N/Adb$.service.dbThis component uses $.service.db to maintain state between executions.
Trigger TypetriggerTypestringSelect a value from the drop down menu:webhookpolling

Trigger Authentication

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

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

emailprofileopenidhttps://www.googleapis.com/auth/gmail.labelshttps://www.googleapis.com/auth/gmail.sendhttps://www.googleapis.com/auth/gmail.modifyhttps://www.googleapis.com/auth/gmail.composehttps://www.googleapis.com/auth/gmail.settings.basic

About Gmail

Gmail offers private and secure email by Google at no cost, for business and consumer accounts.

Action

Description:The Chat API, using the `gpt-3.5-turbo` or `gpt-4` model. [See the documentation](https://platform.openai.com/docs/api-reference/chat)
Version:0.2.3
Key:openai-chat

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 openai from "../../openai.app.mjs";
import common from "../common/common.mjs";
import constants from "../../common/constants.mjs";
import { ConfigurationError } from "@pipedream/platform";

export default {
  ...common,
  name: "Chat",
  version: "0.2.3",
  key: "openai-chat",
  description: "The Chat API, using the `gpt-3.5-turbo` or `gpt-4` model. [See the documentation](https://platform.openai.com/docs/api-reference/chat)",
  type: "action",
  props: {
    openai,
    modelId: {
      propDefinition: [
        openai,
        "chatCompletionModelId",
      ],
    },
    userMessage: {
      label: "User Message",
      type: "string",
      description: "The user messages provide instructions to the assistant. They can be generated by the end users of an application, or set by a developer as an instruction.",
    },
    ...common.props,
    systemInstructions: {
      label: "System Instructions",
      type: "string",
      description: "The system message helps set the behavior of the assistant. For example: \"You are a helpful assistant.\" [See these docs](https://platform.openai.com/docs/guides/chat/instructing-chat-models) for tips on writing good instructions.",
      optional: true,
    },
    messages: {
      label: "Prior Message History",
      type: "string[]",
      description: "_Advanced_. Because [the models have no memory of past chat requests](https://platform.openai.com/docs/guides/chat/introduction), all relevant information must be supplied via the conversation. You can provide [an array of messages](https://platform.openai.com/docs/guides/chat/introduction) from prior conversations here. If this param is set, the action ignores the values passed to **System Instructions** and **Assistant Response**, appends the new **User Message** to the end of this array, and sends it to the API.",
      optional: true,
    },
    images: {
      label: "Images",
      type: "string[]",
      description: "Provide one or more images to [OpenAI's vision model](https://platform.openai.com/docs/guides/vision). Accepts URLs or base64 encoded strings. Compatible with the `gpt4-vision-preview` model",
      optional: true,
    },
    audio: {
      type: "string",
      label: "Audio",
      description: "Provide the file path to an audio file in the `/tmp` directory. For use with the `gpt-4o-audio-preview` model. Currently supports `wav` and `mp3` files.",
      optional: true,
    },
    responseFormat: {
      type: "string",
      label: "Response Format",
      description: "Specify the format that the model must output. \n- **Text** (default): Returns unstructured text output.\n- **JSON Object**: Ensures the model's output is a valid JSON object.\n- **JSON Schema** (GPT-4o and later): Enables you to define a specific structure for the model's output using a JSON schema. Supported with models `gpt-4o-2024-08-06` and later, and `gpt-4o-mini-2024-07-18` and later.",
      options: Object.values(constants.CHAT_RESPONSE_FORMAT),
      default: constants.CHAT_RESPONSE_FORMAT.TEXT.value,
      optional: true,
      reloadProps: true,
    },
    toolTypes: {
      type: "string[]",
      label: "Tool Types",
      description: "The types of tools to enable on the assistant",
      options: constants.TOOL_TYPES.filter((toolType) => toolType === "function"),
      optional: true,
      reloadProps: true,
    },
  },
  additionalProps() {
    const {
      responseFormat,
      toolTypes,
      numberOfFunctions,
    } = this;
    const props = {};

    if (responseFormat === constants.CHAT_RESPONSE_FORMAT.JSON_SCHEMA.value) {
      props.jsonSchema = {
        type: "string",
        label: "JSON Schema",
        description: "Define the schema that the model's output must adhere to. [See the documentation here](https://platform.openai.com/docs/guides/structured-outputs/supported-schemas).",
      };
    }

    if (toolTypes?.includes("function")) {
      props.numberOfFunctions = {
        type: "integer",
        label: "Number of Functions",
        description: "The number of functions to define",
        optional: true,
        reloadProps: true,
        default: 1,
      };

      for (let i = 0; i < (numberOfFunctions || 1); i++) {
        props[`functionName_${i}`] = {
          type: "string",
          label: `Function Name ${i + 1}`,
          description: "The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.",
        };
        props[`functionDescription_${i}`] = {
          type: "string",
          label: `Function Description ${i + 1}`,
          description: "A description of what the function does, used by the model to choose when and how to call the function.",
          optional: true,
        };
        props[`functionParameters_${i}`] = {
          type: "object",
          label: `Function Parameters ${i + 1}`,
          description: "The parameters the functions accepts, described as a JSON Schema object. See the [guide](https://platform.openai.com/docs/guides/text-generation/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format.",
          optional: true,
        };
      }
    }

    return props;
  },
  methods: {
    ...common.methods,
    _buildTools() {
      const tools = this.toolTypes?.filter((toolType) => toolType !== "function")?.map((toolType) => ({
        type: toolType,
      })) || [];
      if (this.toolTypes?.includes("function")) {
        const numberOfFunctions = this.numberOfFunctions || 1;
        for (let i = 0; i < numberOfFunctions; i++) {
          tools.push({
            type: "function",
            function: {
              name: this[`functionName_${i}`],
              description: this[`functionDescription_${i}`],
              parameters: this[`functionParameters_${i}`],
            },
          });
        }
      }
      return tools.length
        ? tools
        : undefined;
    },
  },
  async run({ $ }) {
    if (this.audio && !this.modelId.includes("gpt-4o-audio-preview")) {
      throw new ConfigurationError("Use of audio files requires using the `gpt-4o-audio-preview` model.");
    }

    const args = this._getChatArgs();

    const response = await this.openai.createChatCompletion({
      $,
      data: {
        ...args,
        tools: this._buildTools(),
      },
    });

    if (response) {
      $.export("$summary", `Successfully sent chat with id ${response.id}`);
    }

    const { messages } = args;
    return {
      original_messages: messages,
      original_messages_with_assistant_response: messages.concat(response.choices[0]?.message),
      ...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.

LabelPropTypeDescription
OpenAI (ChatGPT)openaiappThis component uses the OpenAI (ChatGPT) app.
ModelmodelIdstringSelect a value from the drop down menu.
User MessageuserMessagestring

The user messages provide instructions to the assistant. They can be generated by the end users of an application, or set by a developer as an instruction.

Max TokensmaxTokensinteger

The maximum number of tokens to generate in the completion.

Temperaturetemperaturestring

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 PtopPstring

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.

Nninteger

How many completions to generate for each prompt

Stopstopstring[]

Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

Presence PenaltypresencePenaltystring

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 PenaltyfrequencyPenaltystring

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.

Useruserstring

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more here.

System InstructionssystemInstructionsstring

The system message helps set the behavior of the assistant. For example: "You are a helpful assistant." See these docs for tips on writing good instructions.

Prior Message Historymessagesstring[]

Advanced. Because the models have no memory of past chat requests, all relevant information must be supplied via the conversation. You can provide an array of messages from prior conversations here. If this param is set, the action ignores the values passed to System Instructions and Assistant Response, appends the new User Message to the end of this array, and sends it to the API.

Imagesimagesstring[]

Provide one or more images to OpenAI's vision model. Accepts URLs or base64 encoded strings. Compatible with the gpt4-vision-preview model

Audioaudiostring

Provide the file path to an audio file in the /tmp directory. For use with the gpt-4o-audio-preview model. Currently supports wav and mp3 files.

Response FormatresponseFormatstringSelect a value from the drop down menu:{ "label": "Text", "value": "text" }{ "label": "JSON Object", "value": "json_object" }{ "label": "JSON Schema", "value": "json_schema" }
Tool TypestoolTypesstring[]Select a value from the drop down menu:function

Action Authentication

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

About OpenAI (ChatGPT)

OpenAI is an AI research and deployment company with the mission to ensure that artificial general intelligence benefits all of humanity. They are the makers of popular models like ChatGPT, DALL-E, and Whisper.

More Ways to Connect OpenAI (ChatGPT) + Gmail

Create Run (Assistants) with OpenAI (ChatGPT) API on New Labeled Email from Gmail API
Gmail + OpenAI (ChatGPT)
 
Try it
Create Run (Assistants) with OpenAI (ChatGPT) API on New Sent Email from Gmail API
Gmail + OpenAI (ChatGPT)
 
Try it
Analyze Image Content with OpenAI (ChatGPT) API on New Labeled Email from Gmail API
Gmail + OpenAI (ChatGPT)
 
Try it
Cancel Run (Assistants) with OpenAI (ChatGPT) API on New Labeled Email from Gmail API
Gmail + OpenAI (ChatGPT)
 
Try it
Chat with Assistant with OpenAI (ChatGPT) API on New Labeled Email from Gmail API
Gmail + OpenAI (ChatGPT)
 
Try it
New Attachment Received from the Gmail API

Emit new event for each attachment in a message received. This source is capped at 100 max new messages per run.

 
Try it
New Email Matching Search from the Gmail API

Emit new event when an email matching the search criteria is received. This source is capped at 100 max new messages per run.

 
Try it
New Email Received from the Gmail API

Emit new event when a new email is received.

 
Try it
New Labeled Email from the Gmail API

Emit new event when a new email is labeled.

 
Try it
New Sent Email from the Gmail API

Emit new event for each new email sent. (Maximum of 100 events emited per execution)

 
Try it
Add Label to Email with the Gmail API

Add label(s) to an email message. See the docs

 
Try it
Create Draft with the Gmail API

Create a draft from your Google Workspace email account. See the documentation

 
Try it
Download Attachment with the Gmail API

Download an attachment by attachmentId to the /tmp directory. See the documentation

 
Try it
Find Email with the Gmail API

Find an email using Google's Search Engine. See the docs

 
Try it
Remove Label from Email with the Gmail API

Remove label(s) from an email message. See the docs

 
Try it

Explore Other Apps

1
-
24
of
2,400+
apps by most popular

HTTP / Webhook
HTTP / Webhook
Get a unique URL where you can send HTTP or webhook requests
Node
Node
Anything you can do with Node.js, you can do in a Pipedream workflow. This includes using most of npm's 400,000+ packages.
Python
Python
Anything you can do in Python can be done in a Pipedream Workflow. This includes using any of the 350,000+ PyPi packages available in your Python powered workflows.
OpenAI (ChatGPT)
OpenAI (ChatGPT)
OpenAI is an AI research and deployment company with the mission to ensure that artificial general intelligence benefits all of humanity. They are the makers of popular models like ChatGPT, DALL-E, and Whisper.
Premium
Salesforce
Salesforce
Web services API for interacting with Salesforce
Premium
HubSpot
HubSpot
HubSpot's CRM platform contains the marketing, sales, service, operations, and website-building software you need to grow your business.
Premium
Zoho CRM
Zoho CRM
Zoho CRM is an online Sales CRM software that manages your sales, marketing, and support in one CRM platform.
Premium
Stripe
Stripe
Stripe powers online and in-person payment processing and financial solutions for businesses of all sizes.
Shopify
Shopify
Shopify is a complete commerce platform that lets anyone start, manage, and grow a business. You can use Shopify to build an online store, manage sales, market to customers, and accept payments in digital and physical locations.
Premium
WooCommerce
WooCommerce
WooCommerce is the open-source ecommerce platform for WordPress.
Premium
Snowflake
Snowflake
A data warehouse built for the cloud
Premium
MongoDB
MongoDB
MongoDB is an open source NoSQL database management program.
Supabase
Supabase
Supabase is an open source Firebase alternative.
MySQL
MySQL
MySQL is an open-source relational database management system.
PostgreSQL
PostgreSQL
PostgreSQL is a free and open-source relational database management system emphasizing extensibility and SQL compliance.
Premium
AWS
AWS
Amazon Web Services (AWS) offers reliable, scalable, and inexpensive cloud computing services.
Premium
Twilio SendGrid
Twilio SendGrid
Send marketing and transactional email through the Twilio SendGrid platform with the Email API, proprietary mail transfer agent, and infrastructure for scalable delivery.
Amazon SES
Amazon SES
Amazon SES is a cloud-based email service provider that can integrate into any application for high volume email automation
Premium
Klaviyo
Klaviyo
Email Marketing and SMS Marketing Platform
Premium
Zendesk
Zendesk
Zendesk is award-winning customer service software trusted by 200K+ customers. Make customers happy via text, mobile, phone, email, live chat, social media.
Notion
Notion
Notion is a new tool that blends your everyday work apps into one. It's the all-in-one workspace for you and your team.
Slack
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.
Microsoft Teams
Microsoft Teams
Microsoft Teams has communities, events, chats, channels, meetings, storage, tasks, and calendars in one place.
Schedule
Schedule
Trigger workflows on an interval or cron schedule.