Chat with OpenAI (ChatGPT) API on New Pub/Sub Messages from Google Cloud API

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

Trigger workflow on

New Pub/Sub Messages from the Google Cloud API

Next, do this

Chat 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 Google Cloud 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 Pub/Sub Messages trigger
1. Connect your Google Cloud account
2. Select a Type
Configure the Chat action
1. Connect your OpenAI (ChatGPT) account
2. Select a Model
3. Configure User Message
4. Optional- Configure System Instructions
5. Optional- Configure Prior Message History
6. Optional- Configure Max Tokens
7. Optional- Configure Temperature
8. Optional- Configure Top P
9. Optional- Configure N
10. Optional- Configure Stop
11. Optional- Configure Presence Penalty
12. Optional- Configure Frequency Penalty
13. Optional- Configure User
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 Pub/Sub Messages on Google Cloud

Description:Emit new Pub/Sub topic in your GCP account. Messages published to this topic are emitted from the Pipedream source.

Version:0.1.5

Key:google_cloud-new-pubsub-messages

View on GitHub

Google Cloud Overview#

The Google Cloud API allows developers to access a variety of Google Cloud
services from their own applications. Services that can be accessed include
Google Cloud Storage, Google Cloud Datastore, Google Cloud Functions, and
Google Cloud Pub/Sub. With the Google Cloud API, developers can build a variety
of applications that take advantage of Google Cloud services.

Trigger Code#

import { PubSub } from "@google-cloud/pubsub";
import googleCloud from "../../google_cloud.app.mjs";

export default {
  key: "google_cloud-new-pubsub-messages",
  name: "New Pub/Sub Messages",
  description: "Emit new Pub/Sub topic in your GCP account. Messages published to this topic are emitted from the Pipedream source.",
  version: "0.1.5",
  type: "source",
  dedupe: "unique", // Dedupe on Pub/Sub message ID
  props: {
    googleCloud,
    http: "$.interface.http",
    db: "$.service.db",
    topicType: {
      type: "string",
      label: "Type",
      description: "Do you have an existing Pub/Sub topic, or would you like to create a new one?",
      options: [
        "existing",
        "new",
      ],
      reloadProps: true,
    },
  },
  async additionalProps() {
    const topic = {
      type: "string",
      label: "Pub/Sub Topic Name",
      description: "Select a Pub/Sub topic from your GCP account to watch",
      options: async () => {
        return this.getTopics();
      },
    };
    if (this.topicType === "new") {
      topic.description = "**Pipedream will create a Pub/Sub topic with this name in your account**, converting it to a [valid Pub/Sub topic name](https://cloud.google.com/pubsub/docs/admin#resource_names).";
      delete topic.options;
    }
    return {
      topic,
    };
  },
  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);
    },
    async getTopics() {
      const sdkParams = this.googleCloud.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, "-");
    },
  },
  hooks: {
    async activate() {
      const sdkParams = this.googleCloud.sdkParams();
      const pubSubClient = new PubSub(sdkParams);

      const currentTopic = {
        name: this.topic,
      };
      if (this.topicType === "new") {
        const topicName = this.convertNameToValidPubSubTopicName(this.topic);
        console.log(`Creating Pub/Sub topic ${topicName}`);
        const [
          topic,
        ] = await pubSubClient.createTopic(topicName);
        currentTopic.name = topic.name;
      }
      this._setTopicName(currentTopic.name);

      const pushEndpoint = this.http.endpoint;
      const subscriptionName = this.convertNameToValidPubSubTopicName(pushEndpoint);
      const subscriptionOptions = {
        pushConfig: {
          pushEndpoint,
        },
      };
      console.log(
        `Subscribing this source's URL to the Pub/Sub topic: ${pushEndpoint}
        (under name ${subscriptionName}).`,
      );
      const [
        subscriptionResult,
      ] = await pubSubClient
        .topic(currentTopic.name)
        .createSubscription(subscriptionName, subscriptionOptions);
      this._setSubscriptionName(subscriptionResult.name);
    },
    async deactivate() {
      const sdkParams = this.googleCloud.sdkParams();
      const pubSubClient = new PubSub(sdkParams);

      const subscriptionName = this._getSubscriptionName();
      if (subscriptionName) {
        await pubSubClient.subscription(subscriptionName).delete();
      }

      if (this.topicType === "new") {
        const topicName = this._getTopicName();
        if (topicName) {
          await pubSubClient.topic(topicName).delete();
        }
      }
    },
  },
  async run(event) {
    const {
      data,
      messageId,
      publishTime,
    } = event.body.message;

    if (!data) {
      console.warn("No message present, exiting");
      return;
    }
    const dataString = Buffer.from(data, "base64").toString("utf-8");
    const metadata = {
      id: messageId,
      summary: dataString,
      ts: +new Date(publishTime),
    };

    let dataObj;
    try {
      dataObj = JSON.parse(dataString);
    } catch (err) {
      console.error(
        `Couldn't parse message as JSON. Emitting raw message. Error: ${err}`,
      );
      dataObj = {
        rawMessage: dataString,
      };
    }
    this.$emit(dataObj, metadata);
  },
};

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
Google Cloud	`googleCloud`	`app`	This component uses the Google Cloud app.
N/A	`http`	`$.interface.http`	This component uses `$.interface.http` to generate a unique URL when the component is first instantiated. Each request to the URL will trigger the `run()` method of the component.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
Type	`topicType`	`string`	Select a value from the drop down menu:`existingnew`

Trigger Authentication#

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

Create a service account in GCP and set the permissions you need for Pipedream workflows.
Generate a service account key
Download the key details in JSON format
Open the JSON in a text editor, and copy and paste its contents here.

About Google Cloud#

The Google Cloud Platform, including BigQuery

Action#

Chat on OpenAI (ChatGPT)

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

Version:0.1.2

Key:openai-chat

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

export default {
  ...common,
  name: "Chat",
  version: "0.1.2",
  key: "openai-chat",
  description: "The Chat API, using the `gpt-3.5-turbo` or `gpt-4` model. [See docs here](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.",
    },
    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,
    },
    ...common.props,
  },
  async run({ $ }) {
    const args = this._getChatArgs();
    const response = await this.openai.createChatCompletion({
      $,
      args,
    });

    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.

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.
User Message	`userMessage`	`string`	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.
System Instructions	`systemInstructions`	`string`	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 History	`messages`	`string[]`	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.
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.

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 apps like ChatGPT and DALL·E 2.