Classify Text with Cohere API on New Item From Multiple RSS Feeds from RSS API

Pipedream makes it easy to connect APIs for Cohere, RSS and 2,400+ other apps remarkably fast.

Trigger workflow on

New Item From Multiple RSS Feeds from the RSS API

Next, do this

Classify Text with the Cohere 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 RSS trigger and Cohere action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Item From Multiple RSS Feeds trigger
1. Connect your RSS account
2. Configure timer
3. Configure Feed URLs
4. Optional- Configure Max per Feed
Configure the Classify Text action
1. Connect your Cohere account
2. Configure Inputs
3. Optional- Select a Model
4. Optional- Configure Preset
5. Optional- Select a Truncate
6. Configure Number of Examples
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 Item From Multiple RSS Feeds on RSS

Description:Emit new items from multiple RSS feeds

Version:1.2.7

Key:rss-new-item-from-multiple-feeds

View on GitHub

RSS Overview#

The RSS app allows users to automatically fetch and parse updates from web feeds. This functionality is pivotal for staying abreast of content changes or updates from websites, blogs, and news outlets that offer RSS feeds. With Pipedream, you can harness the RSS API to trigger workflows that enable a broad range of automations, like content aggregation, monitoring for specific keywords, notifications, and data synchronization across platforms.

Trigger Code#

import rss from "../../app/rss.app.mjs";
import { defineSource } from "@pipedream/types";
import rssCommon from "../common/common.mjs";
export default defineSource({
    ...rssCommon,
    key: "rss-new-item-from-multiple-feeds",
    name: "New Item From Multiple RSS Feeds",
    type: "source",
    description: "Emit new items from multiple RSS feeds",
    version: "1.2.7",
    props: {
        ...rssCommon.props,
        urls: {
            propDefinition: [
                rss,
                "urls",
            ],
            description: "Enter one or multiple URLs from any public RSS feed. To avoid timeouts, 5 or less URLs is recommended.",
        },
        max: {
            type: "integer",
            label: "Max per Feed",
            description: "Maximum number of posts per feed to retrieve at one time. Defaults to 20.",
            optional: true,
            default: 20,
        },
    },
    dedupe: "unique",
    hooks: {
        async activate() {
            // Try to parse the feed one time to confirm we can fetch and parse.
            // The code will throw any errors to the user.
            for (const url of this.urls) {
                await this.rss.fetchAndParseFeed(url);
            }
        },
    },
    async run() {
        const items = [];
        for (const url of this.urls) {
            const feedItems = (await this.rss.fetchAndParseFeed(url))?.slice(0, this.max);
            console.log(`Retrieved items from ${url}`);
            items.push(...feedItems);
        }
        this.rss.sortItems(items).forEach((item) => {
            const meta = this.generateMeta(item);
            this.$emit(item, meta);
        });
    },
});

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
RSS	`rss`	`app`	This component uses the RSS app.
	`timer`	`$.interface.timer`	How often you want to poll the feed for new items
Feed URLs	`urls`	`string[]`	Enter one or multiple URLs from any public RSS feed. To avoid timeouts, 5 or less URLs is recommended.
Max per Feed	`max`	`integer`	Maximum number of posts per feed to retrieve at one time. Defaults to 20.

Trigger Authentication#

The RSS API does not require authentication.

About RSS#

Real Simple Syndication

Action#

Classify Text on Cohere

Description:This action makes a prediction about which label fits the specified text inputs best. [See the documentation](https://docs.cohere.com/reference/classify-1)

Version:0.1.0

Key:cohere_platform-classify-text

View on GitHub

Cohere Overview#

The Cohere API enables the development of apps with advanced natural language understanding capabilities. Utilizing machine learning, it can help with tasks like text generation, summarization, sentiment analysis, and more. On Pipedream, you can seamlessly integrate Cohere's features into serverless workflows, triggering actions based on text input, processing large volumes of data, or even enhancing chatbots with more human-like responses.

Action Code#

import app from "../../cohere_platform.app.mjs";
import { clearObj } from "../../common/utils.mjs";

export default {
  key: "cohere_platform-classify-text",
  name: "Classify Text",
  version: "0.1.0",
  description: "This action makes a prediction about which label fits the specified text inputs best. [See the documentation](https://docs.cohere.com/reference/classify-1)",
  type: "action",
  props: {
    app,
    inputs: {
      type: "string[]",
      label: "Inputs",
      description: "Represents a list of queries to be classified, each entry must not be empty. The maximum is 96 inputs.",
    },
    model: {
      propDefinition: [
        app,
        "classifyModel",
      ],
    },
    preset: {
      propDefinition: [
        app,
        "preset",
      ],
    },
    truncate: {
      propDefinition: [
        app,
        "truncate",
      ],
    },
    numExamples: {
      type: "integer",
      label: "Number of Examples",
      description: "To make a prediction, Classify uses provided examples of text + label pairs. Specify the number of examples to provide. Each example is a text string and its associated label/class. At least 2 unique labels must be provided and each label should have at least 2 different examples.",
      default: 4,
      reloadProps: true,
    },
  },
  additionalProps() {
    const props = {};

    for (let i = 0; i < this.numExamples; i++) {
      props[`text_${i}`] = {
        type: "string",
        label: `Example ${i + 1} Text`,
        description: "Text string of the example",
      };
      props[`label_${i}`] = {
        type: "string",
        label: `Example ${i + 1} Label`,
        description: "Label of the example. Each unique label requires at least 2 examples associated with it.",
      };
    }

    return props;
  },
  methods: {
    getExamples() {
      const examples = [];
      for (let i = 0; i < this.numExamples; i++) {
        examples.push({
          text: this[`text_${i}`],
          label: this[`label_${i}`],
        });
      }
      return examples;
    },
    classifyText(data) {
      return this.app.client().classify(data);
    },
  },
  async run({ $ }) {
    const {
      classifyText,
      inputs,
      model,
      preset,
      truncate,
      getExamples,
    } = this;

    const response = await classifyText(clearObj({
      inputs,
      model,
      preset,
      truncate,
      examples: getExamples(),
    }));

    $.export("$summary", `The text was successfully classified with ID \`${response.id}\``);
    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
Cohere	`app`	`app`	This component uses the Cohere app.
Inputs	`inputs`	`string[]`	Represents a list of queries to be classified, each entry must not be empty. The maximum is 96 inputs.
Model	`model`	`string`	Select a value from the drop down menu:`embed-multilingual-v2.0embed-english-light-v2.0embed-english-v2.0`
Preset	`preset`	`string`	The ID of a custom playground preset. You can create presets in the playground. If you use a preset, all other parameters become optional, and any included parameters will override the preset's parameters.
Truncate	`truncate`	`string`	Select a value from the drop down menu:`NONESTARTEND`
Number of Examples	`numExamples`	`integer`	To make a prediction, Classify uses provided examples of text + label pairs. Specify the number of examples to provide. Each example is a text string and its associated label/class. At least 2 unique labels must be provided and each label should have at least 2 different examples.