Get Contents with Exa API on Random item from multiple RSS feeds from RSS API

Pipedream makes it easy to connect APIs for Exa, RSS and 3,000+ other apps remarkably fast.

Trigger workflow on

Random item from multiple RSS feeds from the RSS API

Next, do this

Get Contents with the Exa 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 Exa action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the Random item from multiple RSS feeds trigger
1. Connect your RSS account
2. Configure timer
3. Configure Feed URLs
Configure the Get Contents action
1. Connect your Exa account
2. Configure URLs
3. Optional- Configure Include Text
4. Optional- Configure Highlights Num Sentences
5. Optional- Configure Highlights Per URL
6. Optional- Configure Highlights Query
7. Optional- Configure Summary Query
8. Optional- Configure Summary Schema
9. Optional- Select a Live Crawl
10. Optional- Configure Live Crawl Timeout
11. Optional- Configure Subpages
12. Optional- Configure Subpage Target
13. Optional- Configure Extras Links
14. Optional- Configure Extras Image Links
15. Optional- Configure Include Context
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#

Random item from multiple RSS feeds on RSS

Description:Emit a random item from multiple RSS feeds

Version:0.2.9

Key:rss-random-item-in-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 { defineSource } from "@pipedream/types";
import rss from "../../app/rss.app.mjs";
import rssCommon from "../common/common.mjs";
export default defineSource({
    ...rssCommon,
    key: "rss-random-item-in-multiple-feeds",
    name: "Random item from multiple RSS feeds",
    type: "source",
    description: "Emit a random item from multiple RSS feeds",
    version: "0.2.9",
    props: {
        ...rssCommon.props,
        urls: {
            propDefinition: [
                rss,
                "urls",
            ],
        },
    },
    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);
            items.push(...feedItems);
        }
        const item = items[Math.floor(Math.random() * items.length)];
        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 either one or multiple URLs from any public RSS feed

Trigger Authentication#

The RSS API does not require authentication.

About RSS#

Real Simple Syndication

Action#

Get Contents on Exa

Description:Retrieves full page contents, summaries, and metadata for a list of URLs. Uses cached results with optional live crawling fallback. [See the documentation](https://docs.exa.ai/reference/get-contents)

Version:0.0.1

Key:exa-get-contents

View on GitHub

Action Code#

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

export default {
  key: "exa-get-contents",
  name: "Get Contents",
  description: "Retrieves full page contents, summaries, and metadata for a list of URLs. Uses cached results with optional live crawling fallback. [See the documentation](https://docs.exa.ai/reference/get-contents)",
  version: "0.0.1",
  type: "action",
  annotations: {
    destructiveHint: false,
    openWorldHint: true,
    readOnlyHint: true,
  },
  props: {
    app,
    urls: {
      propDefinition: [
        app,
        "urls",
      ],
    },
    text: {
      description: "If `true`, returns full page text with default settings. If `false`, disables text return.",
      propDefinition: [
        app,
        "text",
      ],
    },
    highlightsNumSentences: {
      propDefinition: [
        app,
        "highlightsNumSentences",
      ],
    },
    highlightsPerUrl: {
      propDefinition: [
        app,
        "highlightsPerUrl",
      ],
    },
    highlightsQuery: {
      propDefinition: [
        app,
        "highlightsQuery",
      ],
    },
    summaryQuery: {
      propDefinition: [
        app,
        "summaryQuery",
      ],
    },
    summarySchema: {
      propDefinition: [
        app,
        "summarySchema",
      ],
    },
    livecrawl: {
      propDefinition: [
        app,
        "livecrawl",
      ],
    },
    livecrawlTimeout: {
      type: "integer",
      label: "Live Crawl Timeout",
      description: "Timeout in milliseconds for live crawling (default: 10000)",
      optional: true,
    },
    subpages: {
      propDefinition: [
        app,
        "subpages",
      ],
    },
    subpageTarget: {
      propDefinition: [
        app,
        "subpageTarget",
      ],
    },
    extrasLinks: {
      propDefinition: [
        app,
        "extrasLinks",
      ],
    },
    extrasImageLinks: {
      propDefinition: [
        app,
        "extrasImageLinks",
      ],
    },
    context: {
      description: "Return page contents as a context string for LLM. When true, combines all result contents into one string. We recommend using 10000+ characters for best results, though no limit works best. Context strings often perform better than highlights for RAG applications.",
      propDefinition: [
        app,
        "context",
      ],
    },
  },
  async run({ $ }) {
    const {
      app,
      urls,
      text,
      highlightsNumSentences,
      highlightsPerUrl,
      highlightsQuery,
      summaryQuery,
      summarySchema,
      livecrawl,
      livecrawlTimeout,
      subpages,
      subpageTarget,
      extrasLinks,
      extrasImageLinks,
      context,
    } = this;

    let parsedSchema;
    if (summarySchema) {
      if (typeof summarySchema === "string") {
        try {
          parsedSchema = JSON.parse(summarySchema);
        } catch (error) {
          throw new ConfigurationError(`Invalid JSON schema format: ${error.message}. Please provide a valid JSON object.`);
        }
      } else {
        parsedSchema = summarySchema;
      }
    }

    const response = await app.getContents({
      $,
      data: {
        urls,
        text,
        livecrawl,
        livecrawlTimeout,
        subpages,
        subpageTarget,
        context,
        ...(extrasLinks
        || extrasImageLinks
          ? {
            extras: {
              links: extrasLinks,
              imageLinks: extrasImageLinks,
            },
          }
          : undefined
        ),
        ...(highlightsNumSentences
          || highlightsPerUrl
          || highlightsQuery
          ? {
            highlights: {
              numSentences: highlightsNumSentences,
              highlightsPerUrl,
              query: highlightsQuery,
            },
          }
          : undefined
        ),
        ...(summaryQuery
          || summarySchema
          ? {
            summary: {
              query: summaryQuery,
              schema: parsedSchema,
            },
          }
          : undefined
        ),
      },
    });

    $.export("$summary", `Successfully retrieved contents with ID \`${response.requestId}\`.`);
    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
Exa	`app`	`app`	This component uses the Exa app.
URLs	`urls`	`string[]`	List of URLs to retrieve contents for
Include Text	`text`	`boolean`	If `true`, returns full page text with default settings. If `false`, disables text return.
Highlights Num Sentences	`highlightsNumSentences`	`integer`	The number of sentences to return for each snippet.
Highlights Per URL	`highlightsPerUrl`	`integer`	The number of snippets to return for each result.
Highlights Query	`highlightsQuery`	`string`	Custom query to direct the LLM's selection of highlights.
Summary Query	`summaryQuery`	`string`	Custom query to guide summary generation
Summary Schema	`summarySchema`	`object`	JSON schema for structured output from summary. See JSON Schema documentation for details. Example: `{ "$schema": "http://json-schema.org/draft-07/schema#", "title": "Title", "type": "object", "properties": { "Property 1": { "type": "string", "description": "Description" }, "Property 2": { "type": "string", "enum": ["option 1", "option 2", "option 3"], "description": "Description" } }, "required": ["Property 1"] }`
Live Crawl	`livecrawl`	`string`	Select a value from the drop down menu:`neverfallbackalwayspreferred`
Live Crawl Timeout	`livecrawlTimeout`	`integer`	Timeout in milliseconds for live crawling (default: 10000)
Subpages	`subpages`	`integer`	Number of subpages to crawl per result
Subpage Target	`subpageTarget`	`string`	Keywords to identify specific subpages to crawl
Extras Links	`extrasLinks`	`integer`	Number of URLs to return from each webpage.
Extras Image Links	`extrasImageLinks`	`integer`	Number of images to return for each result.
Include Context	`context`	`boolean`	Return page contents as a context string for LLM. When true, combines all result contents into one string. We recommend using 10000+ characters for best results, though no limit works best. Context strings often perform better than highlights for RAG applications.

Action Authentication#

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

About Exa#

More Ways to Connect Exa + RSS#

Other Popular Integrations#

Answer Question with Exa API on New Item From Multiple RSS Feeds from RSS API

RSS + Exa

Try it

Answer Question with Exa API on New Item in Feed from RSS API

RSS + Exa

Try it

Answer Question with Exa API on Random item from multiple RSS feeds from RSS API

RSS + Exa

Try it

Get Contents with Exa API on New Item From Multiple RSS Feeds from RSS API

RSS + Exa

Try it

Get Contents with Exa API on New Item in Feed from RSS API

RSS + Exa

Try it

Popular Triggers#

New Item in Feed from the RSS API

Emit new items from an RSS feed

Try it

New Item From Multiple RSS Feeds from the RSS API

Emit new items from multiple RSS feeds

Try it

Random item from multiple RSS feeds from the RSS API

Emit a random item from multiple RSS feeds

Try it

Popular Actions#

Merge RSS Feeds with the RSS API

Retrieve multiple RSS feeds and return a merged array of items sorted by date See documentation

Try it

Answer Question with the Exa API

Generates LLM-powered responses to queries, informed by Exa search results with citations. Handles both factual queries requiring direct answers and open-ended questions needing detailed summaries. See the documentation

Try it

Find Similar Links with the Exa API

Identifies and retrieves web pages similar to a provided URL with optional content extraction. See the documentation

Try it

Get Contents with the Exa API

Retrieves full page contents, summaries, and metadata for a list of URLs. Uses cached results with optional live crawling fallback. See the documentation

Try it

Search with the Exa API

Performs an intelligent web search. See the documentation

Try it