Chat using Web Search with OpenAI (ChatGPT) API on New Event from Confection API

Pipedream makes it easy to connect APIs for OpenAI (ChatGPT), Confection and 2,500+ other apps remarkably fast.

Trigger workflow on

New Event from the Confection API

Next, do this

Chat using Web Search 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 Confection 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 Event trigger
1. Connect your Confection account
2. Configure timer
3. Configure Event Name
Configure the Chat using Web Search action
1. Connect your OpenAI (ChatGPT) account
2. Select a Model
3. Configure Chat Input
4. Optional- Configure Instructions
5. Optional- Configure Previous Response ID
6. Optional- Select a Truncation
7. Optional- Select one or more User Location
8. Optional- Select a Search Context Size
9. Optional- Select a Response Format
10. Optional- Configure Skip This Step
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 Event on Confection

Description:Emit new event when a UUID receives a value for the configured **Event Name**. The latest value as well a history of all values ever received for that **Event Name** will be returned.

Version:0.1.0

Key:confection-new-event

View on GitHub

Confection Overview#

Confection API provides a robust solution for collecting, managing, and utilizing user data in compliance with privacy regulations. It helps businesses capture data lost due to ad blockers and privacy tech, ensuring you don't miss out on valuable insights. With Pipedream, you can harness this data in real-time, triggering actions, analyzing trends, or integrating with other services for a comprehensive data strategy.

Trigger Code#

import common from "../common.mjs";
import confection from "../../confection.app.mjs";

export default {
  key: "confection-new-event",
  name: "New Event",
  version: "0.1.0",
  dedupe: "unique",
  type: "source",
  description:
    "Emit new event when a UUID receives a value for the configured **Event Name**. The latest value as well a history of all values ever received for that **Event Name** will be returned.",
  props: {
    ...common.props,
    eventName: {
      propDefinition: [
        confection,
        "eventName",
      ],
      description:
        "Provide the event name to watch. All accounts have `loadtime` & `pageviewBatch` events by default.",
    },
  },
  methods: {
    ...common.methods,
    /**
     * Get summary for the triggered event
     *
     * @param {string} uuid - Emitted data UUID
     */
    getSummary(uuid) {
      return `New ${this.eventName} event with UUID: ${uuid}`;
    },
    /**
     * Get data from Confection Live API
     *
     * @param {string} lastTimestamp - Start of results time frame
     * @param {string} timestamp - End of results time frame
     */
    getSourceData(lastTimestamp, timestamp) {
      return this.confection.getNewEvent(
        this.eventName,
        lastTimestamp,
        timestamp,
      );
    },
  },
  run: common.run,
};

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
Confection	`confection`	`app`	This component uses the Confection app.
	`timer`	`$.interface.timer`
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
Event Name	`eventName`	`string`	Provide the event name to watch. All accounts have `loadtime` & `pageviewBatch` events by default.

Trigger Authentication#

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

Find your account ID and API keys here: https://dashboard.confection.io/my-keys

Need an account? Using Confection for the first time? Please see our quick-start guide: https://confection.io/quick-start/pipedream

About Confection#

Confection collects, stores, and distributes data in a way that's unaffected by client-side disruptions involving cookies, cross-domain scripts, and device IDs. It's also compliant with global privacy laws so it’s good for people too.

Action#

Chat using Web Search on OpenAI (ChatGPT)

Description:Chat using the web search tool. [See the documentation](https://platform.openai.com/docs/guides/tools-web-search)

Version:0.0.3

Key:openai-chat-using-web-search

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 openai from "../../openai.app.mjs";
import common from "../common/common.mjs";
import constants from "../../common/constants.mjs";

export default {
  ...common,
  name: "Chat using Web Search",
  version: "0.0.3",
  key: "openai-chat-using-web-search",
  description: "Chat using the web search tool. [See the documentation](https://platform.openai.com/docs/guides/tools-web-search)",
  type: "action",
  props: {
    openai,
    modelId: {
      type: "string",
      label: "Model",
      description: "Model used to generate the response",
      default: "gpt-4o",
      options: [
        "gpt-4o",
        "gpt-4o-mini",
      ],
    },
    input: {
      type: "string",
      label: "Chat Input",
      description: "Text inputs to the model used to generate a response",
    },
    instructions: {
      type: "string",
      label: "Instructions",
      description: "Inserts a system (or developer) message as the first item in the model's context",
      optional: true,
    },
    previousResponseId: {
      type: "string",
      label: "Previous Response ID",
      description: "The unique ID of the previous response to the model. Use this to create multi-turn conversations",
      optional: true,
    },
    truncation: {
      type: "string",
      label: "Truncation",
      description: "Specifies the truncation mode for the response if it's larger than the context window size",
      optional: true,
      default: "auto",
      options: [
        "auto",
        "disabled",
      ],
    },
    userLocation: {
      type: "string[]",
      label: "User Location",
      description: "Additional configuration for approximate location parameters for the search",
      optional: true,
      options: [
        "City",
        "Region",
        "Country",
        "Timezone",
      ],
    },
    searchContextSize: {
      type: "string",
      label: "Search Context Size",
      description: "Determines the amount of context to use during the web search",
      optional: true,
      default: "medium",
      options: [
        "low",
        "medium",
        "high",
      ],
    },
    responseFormat: {
      type: "string",
      label: "Response Format",
      description: "- **Text**: Returns unstructured text output.\n- **JSON Schema**: Enables you to define a [specific structure for the model's output using a JSON schema](https://platform.openai.com/docs/guides/structured-outputs?api-mode=responses).",
      options: [
        "text",
        "json_schema",
      ],
      default: "text",
      optional: true,
      reloadProps: true,
    },
    skipThisStep: {
      type: "boolean",
      label: "Skip This Step",
      description: "Pass in a boolean custom expression to skip this step's execution at runtime",
      optional: true,
      default: false,
    },
  },
  additionalProps() {
    const {
      responseFormat,
      userLocation,
    } = this;
    const props = {};

    if (userLocation?.includes("City")) {
      props.city = {
        type: "string",
        label: "City",
        description: "Free text input for the city of the user, e.g. `San Francisco`",
      };
    }

    if (userLocation?.includes("Region")) {
      props.region = {
        type: "string",
        label: "Region",
        description: "Free text input for the region of the user, e.g. `California`",
      };
    }

    if (userLocation?.includes("Country")) {
      props.country = {
        type: "string",
        label: "Country",
        description: "The two-letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. `US`",
      };
    }

    if (userLocation?.includes("Timezone")) {
      props.timezone = {
        type: "string",
        label: "Timezone",
        description: "The [IANA timezone](https://timeapi.io/documentation/iana-timezones) of the user, e.g. `America/Los_Angeles`",
      };
    }

    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. [Generate one here](https://platform.openai.com/docs/guides/structured-outputs/supported-schemas).",
      };
    }

    return props;
  },
  methods: {
    ...common.methods,
  },
  async run({ $ }) {
    if (this.skipThisStep) {
      $.export("$summary", "Step execution skipped");
      return;
    }

    const data = {
      model: this.modelId,
      input: this.input,
      instructions: this.instructions,
      previous_response_id: this.previousResponseId,
      truncation: this.truncation,
      tools: [
        {
          type: "web_search_preview",
          user_location: {
            type: "approximate",
            city: this.city,
            country: this.country,
            region: this.region,
            timezone: this.timezone,
          },
          search_context_size: this.searchContextSize,
        },
      ],
    };

    if (this.responseFormat === constants.CHAT_RESPONSE_FORMAT.JSON_SCHEMA.value) {
      try {
        data.text = {
          format: {
            type: this.responseFormat,
            ...JSON.parse(this.jsonSchema),
          },
        };
      } catch (error) {
        throw new Error("Invalid JSON format in the provided JSON Schema");
      }
    }

    const response = await this.openai.responses({
      $,
      data,
    });

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

    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
OpenAI (ChatGPT)	`openai`	`app`	This component uses the OpenAI (ChatGPT) app.
Model	`modelId`	`string`	Select a value from the drop down menu:`gpt-4ogpt-4o-mini`
Chat Input	`input`	`string`	Text inputs to the model used to generate a response
Instructions	`instructions`	`string`	Inserts a system (or developer) message as the first item in the model's context
Previous Response ID	`previousResponseId`	`string`	The unique ID of the previous response to the model. Use this to create multi-turn conversations
Truncation	`truncation`	`string`	Select a value from the drop down menu:`autodisabled`
User Location	`userLocation`	`string[]`	Select a value from the drop down menu:`CityRegionCountryTimezone`
Search Context Size	`searchContextSize`	`string`	Select a value from the drop down menu:`lowmediumhigh`
Response Format	`responseFormat`	`string`	Select a value from the drop down menu:`textjson_schema`
Skip This Step	`skipThisStep`	`boolean`	Pass in a boolean custom expression to skip this step's execution at runtime

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) + Confection#

Other Popular Integrations#

Get Related UUIDs with Confection API on New Fine Tuning Job Created from OpenAI (ChatGPT) API

OpenAI (ChatGPT) + Confection

Chat using Web Search with OpenAI (ChatGPT) API on New Event from Confection API

Pipedream makes it easy to connect APIs for OpenAI (ChatGPT), Confection and 2,500+ other apps remarkably fast.

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

Developers ♥ Pipedream

1-24of2,500+apps by most popular

1
-
24
of
2,500+
apps by most popular