Create Embeddings with OpenAI (ChatGPT) API on New Stories by Keyword from Hacker News API

Pipedream makes it easy to connect APIs for OpenAI (ChatGPT), Hacker News and 1,600+ other apps remarkably fast.

Trigger workflow on

New Stories by Keyword from the Hacker News API

Next, do this

Create Embeddings with the OpenAI (ChatGPT) API

No credit card required

▶

Watch us build a workflow

7 min

Watch now ➜

Trusted by 750,000+ developers from startups to Fortune 500 companies

Developers ♥ Pipedream

Getting Started#

This integration creates a workflow with a Hacker News 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 Stories by Keyword trigger
1. Connect your Hacker News account
2. Configure timer
3. Optional- Configure Keyword
Configure the Create Embeddings action
1. Connect your OpenAI (ChatGPT) account
2. Select a Model
3. Configure Input
4. 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 Stories by Keyword on Hacker News

Description:Emit new stories that mention a specific keyword

Version:0.0.4

Key:hacker_news-new-stories-by-keyword

View on GitHub

Trigger Code#

const Parser = require("rss-parser");
const hacker_news = require("../../hacker_news.app.js");
const { DEFAULT_POLLING_SOURCE_TIMER_INTERVAL } = require("@pipedream/platform");

const parser = new Parser();

module.exports = {
  key: "hacker_news-new-stories-by-keyword",
  name: "New Stories by Keyword",
  description: "Emit new stories that mention a specific keyword",
  version: "0.0.4",
  type: "source",
  props: {
    hacker_news,
    timer: {
      type: "$.interface.timer",
      default: {
        intervalSeconds: DEFAULT_POLLING_SOURCE_TIMER_INTERVAL,
      },
    },
    db: "$.service.db",
    // If you want a single search feed but multiple keywords, separate the keywords with " OR ":
    keyword: {
      type: "string",
      label: "Keyword",
      description: "Keyword to watch. Matches story titles. Leave blank to get all stories.",
      optional: true,
      default: "",
    },
  },
  methods: {
    // in theory if alternate setting title and description or aren't unique this won't work
    itemKey(item) {
      return item.guid || item.id || item.title || item.description;
    },
  },
  async run() {
    const seenKeys = this.db.get("seenKeys") || [];
    const seenKeysMap = seenKeys.reduce((acc, v) => {
      acc[v] = true;
      return acc;
    }, {});
    // All elements of an item are optional,
    // however at least one of title or description must be present.
    // should be listed from most recent to least recent
    const feed = await parser.parseURL(`https://hnrss.org/newest?q=${encodeURIComponent(this.keyword)}`);
    for (let idx = feed.items.length - 1; idx >= 0; idx--) {
      const item = feed.items[idx];
      const key = this.itemKey(item);
      // XXX throw if !key?
      if (seenKeysMap[key]) continue;
      seenKeys.unshift(key);
      seenKeysMap[key] = true; // just in case of dupes
      this.$emit(item, {
        id: this.itemKey(item),
        summary: item.title,
        ts: item.pubdate && +new Date(item.pubdate),
      });
    }
    if (seenKeys.length) {
      // XXX restrict by byte size instead of el size
      this.db.set("seenKeys", seenKeys.slice(0, 1000));
    }
  },
};

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
Hacker News	`hacker_news`	`app`	This component uses the Hacker News app.
	`timer`	`$.interface.timer`
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
Keyword	`keyword`	`string`	Keyword to watch. Matches story titles. Leave blank to get all stories.

Trigger Authentication#

The Hacker News API does not require authentication.

About Hacker News#

Social news website

Action#

Create Embeddings on OpenAI (ChatGPT)

Description:Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms. [See the docs here](https://platform.openai.com/docs/api-reference/embeddings)

Version:0.0.6

Key:openai-create-embeddings

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

export default {
  name: "Create Embeddings",
  version: "0.0.6",
  key: "openai-create-embeddings",
  description: "Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms. [See the docs here](https://platform.openai.com/docs/api-reference/embeddings)",
  type: "action",
  props: {
    openai,
    modelId: {
      propDefinition: [
        openai,
        "embeddingsModelId",
      ],
    },
    input: {
      label: "Input",
      description: "Input text to get embeddings for, encoded as a string or array of tokens. To get embeddings for multiple inputs in a single request, pass an array of strings or array of token arrays. Each input must not exceed 8192 tokens in length.",
      type: "string[]",
    },
    user: common.props.user,
  },
  async run({ $ }) {
    // Confirm no element is more than 8192 tokens in length
    for (const [
      i,
      element,
    ] of this.input.entries()) {
      if (element.length > 8192) {
        throw new ConfigurationError(`Element #${i} is more than 8192 tokens in length. Each input must not exceed 8192 tokens in length.`);
      }
    }

    const response = await this.openai.createEmbeddings({
      $,
      args: {
        model: this.modelId,
        input: this.input,
      },
    });

    if (response) {
      $.export("$summary", "Successfully created embeddings");
    }

    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.
Input	`input`	`string[]`	Input text to get embeddings for, encoded as a string or array of tokens. To get embeddings for multiple inputs in a single request, pass an array of strings or array of token arrays. Each input must not exceed 8192 tokens in length.
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 models like ChatGPT, DALL-E, and Whisper.