import fs from "fs";
import path from "path";
import { ConfigurationError } from "@pipedream/platform";
import app from "../../jina_reader.app.mjs";
export default {
key: "jina_reader-convert-to-llm-friendly-input",
name: "Convert URL To LLM-Friendly Input",
description: "Converts a provided URL to an LLM-friendly input using Jina Reader. [See the documentation](https://github.com/jina-ai/reader)",
version: "0.0.1",
type: "action",
props: {
app,
url: {
type: "string",
label: "URL",
description: "The URL to convert to an LLM-friendly input.",
optional: true,
},
contentFormat: {
type: "string",
label: "Content Format",
description: "You can control the level of detail in the response to prevent over-filtering. The default pipeline is optimized for most websites and LLM input.",
optional: true,
options: [
"markdown",
"html",
"text",
"screenshot",
"pageshot",
],
},
timeout: {
type: "integer",
label: "Timeout",
description: "Maximum time to wait for the webpage to load. Note that this is NOT the total time for the whole end-to-end request.",
optional: true,
},
targetSelector: {
type: "string",
label: "Target Selector",
description: "Provide a list of CSS selector to focus on more specific parts of the page. Useful when your desired content doesn't show under the default settings. E.g., `body, .class, #id`.",
optional: true,
},
waitForSelector: {
type: "string",
label: "Wait For Selector",
description: "Provide a list of CSS selector to wait for specific elements to appear before returning. Useful when your desired content doesn't show under the default settings. E.g., `body, .class, #id`.",
optional: true,
},
excludedSelector: {
type: "string",
label: "Excluded Selector",
description: "Provide a list of CSS selector to remove the specified elements of the page. Useful when you want to exclude specific parts of the page like headers, footers, etc. E.g., `header, .class, #id`.",
optional: true,
},
jsonResponse: {
type: "boolean",
label: "JSON Response",
description: "The response will be in JSON format, containing the URL, title, content, and timestamp (if available). In Search mode, it returns a list of five entries, each following the described JSON structure. Keep in mind **JSON Response** will take piority over **Stream mode** if both are enabled.",
optional: true,
},
forwardCookie: {
type: "string",
label: "Forward Cookie",
description: "The API server can forward your custom cookie settings when accessing the URL, which is useful for pages requiring extra authentication. Note that requests with cookies will not be cached. E.g., `<cookie-name>=<cookie-value>, <cookie-name-1>=<cookie-value>; domain=<cookie-1-domain>`. [Learn more here](https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Set-Cookie).",
optional: true,
},
useProxyServer: {
type: "string",
label: "Proxy Server URL",
description: "The API server can utilize your proxy to access URLs, which is helpful for pages accessible only through specific proxies. E.g., `http://your_proxy_server.com`. [Learn more here](https://en.wikipedia.org/wiki/Proxy_server).",
optional: true,
},
bypassCache: {
type: "boolean",
label: "Bypass Cache",
description: "The API server caches both Read and Search mode contents for a certain amount of time. To bypass this cache, set this header to `true`.",
optional: true,
},
streamMode: {
type: "boolean",
label: "Stream Mode",
description: "Stream mode is beneficial for large target pages, allowing more time for the page to fully render. If standard mode results in incomplete content, consider using **Stream mode**. [Learn more here](https://github.com/jina-ai/reader?tab=readme-ov-file#streaming-mode). Keep in mind **JSON Response** will take piority over **Stream mode** if both are enabled.",
optional: true,
},
browserLocale: {
type: "string",
label: "Browser Locale",
description: "Control the browser locale to render the page. eg. `en-US`. [Learn more here](https://developer.mozilla.org/en-US/docs/Web/API/Navigator/language).",
optional: true,
},
iframeContent: {
type: "boolean",
label: "Iframe",
description: "Returning result will also include the content of the iframes on the page.",
optional: true,
},
shadowDomContent: {
type: "boolean",
label: "Include Shadow DOM Content",
description: "Returning result will also include the content of the shadow DOM on the page.",
optional: true,
},
pdf: {
type: "string",
label: "PDF File Path",
description: "The path to the pdf file saved to the `/tmp` directory (e.g. `/tmp/example.pdf`). [See the documentation](https://pipedream.com/docs/workflows/steps/code/nodejs/working-with-files/#the-tmp-directory).",
optional: true,
},
html: {
type: "string",
label: "HTML File Path",
description: "The path to the html file saved to the `/tmp` directory (e.g. `/tmp/example.html`). [See the documentation](https://pipedream.com/docs/workflows/steps/code/nodejs/working-with-files/#the-tmp-directory).",
optional: true,
},
},
methods: {
async readFileFromTmp(filePath, encoding) {
if (!filePath) {
return;
}
const resolvedPath = path.resolve(filePath);
if (!resolvedPath.startsWith("/tmp/")) {
throw new ConfigurationError(`${filePath} must be located in the '/tmp/' directory`);
}
return await fs.promises.readFile(resolvedPath, encoding);
},
},
async run({ $ }) {
const {
app,
readFileFromTmp,
url,
contentFormat,
timeout,
targetSelector,
waitForSelector,
excludedSelector,
jsonResponse,
forwardCookie,
useProxyServer,
bypassCache,
streamMode,
browserLocale,
iframeContent,
shadowDomContent,
pdf,
html,
} = this;
if (!url && !pdf && !html) {
throw new ConfigurationError("You must provide at least one of **URL**, **PDF File Path**, or **HTML File Path**.");
}
const response = await app.post({
$,
headers: {
"X-Return-Format": contentFormat,
"X-Timeout": timeout,
"X-Target-Selector": targetSelector,
"X-Wait-For-Selector": waitForSelector,
"X-Remove-Selector": excludedSelector,
"X-Set-Cookie": forwardCookie,
"X-Proxy-Url": useProxyServer,
"X-No-Cache": bypassCache,
"Accept": jsonResponse
? "application/json"
: streamMode
? "text/event-stream"
: undefined,
"X-Locale": browserLocale,
"X-With-Shadow-Dom": shadowDomContent,
"X-Iframe": iframeContent,
},
data: {
url,
pdf: await readFileFromTmp(pdf, "base64"),
html: await readFileFromTmp(html, "utf-8"),
},
});
$.export("$summary", "Converted URL to LLM-friendly input successfully.");
return response;
},
};
Chase Roberts@chsrbrts@benedictevans If you haven’t used @pipedream yet, then you haven’t lived.
✨Ellie Day✨@heyelliedayEvaluation update: @pipedream has quite literally been a dream to work with! I’m excited to leverage this tool for all the various workflows I need to write. I’m currently at 11k invocations a day from the initial workflows I’ve written in the past couple weeks.
Michael Braedley@MBraedleyUpdate: I got it working properly, and it's working so well that I'm dropping IFTTT. @pipedream can do everything that IFTTT basic can, and most (if not all things) IFTTT pro can for free or at a reasonable price if you need it. I am recommending it for basically any power user.
Thomas Cutting@mrthomascuttingWant quick+dirty integrations for a serverless workflow - @pipedream is my new go-to 😃
Matthew Roberts@mattdotrobertsday 013 - finally hit node js. This is the secret sauce of taking #nocode projects that one step further. Pumped about getting deeper into @pipedream now
Kenneth Auchenberg 💭@auchenbergYahoo Pipes is back! Kinda 😍 @pipedream
Raymond Camden 🥑@raymondcamdenAwesome video by the @pipedream folks showing real time twitter sentiment analysis integrated with Google Sheets. This is where Pipedream *really* shines, connecting systems together in easy workflows.
Nacho Caballero@nachocaballeroI couldn't recommend @pipedream more. It's an amazing service to integrate different APIs. Much more powerful than Zapier and more user-friendly than AWS Lambda. I'm very proud to wear this t-shirt #NoCode
Jason Snow@jyksnwDeveloped a working prototype environmental sensor IoT solution with @particle Photon, @pipedream, and @MongoDB with full graphing and alerting in less than a day! All amazing technology, will def. be exploring these more.
Steven Terrana@steven_terrana@burgwyn you've inspired me to finally set up my own blog. I'll make sure my first blog post explains the tech behind the setup. think @obsdmd + @GatsbyJS + @pipedream.
🚄 James Augeri, PhD@DotDotJamesWant to low-code your back end, need more horsepower than @Bubble / @KnackHQ, or just miss Yahoo! Pipes? Check out @PipeDream
Sébastien Chopin@AtinuxGitHub issues should be like @linear_app for maintainers. Looking forward more integrations with GH actions or tools like @pipedream 👀
Raul@raul_predescuIf you're a dev and not using @pipedream, you're missing out. Been using it for months, daily. FREE for devs. Plenty of integrations and good limits. Absolutely love it.
Bruno Skvorc@bitfallsSo @pipedream is pretty amazing. In 3 minutes I just made a flow which adds @rickastley's Never Gonna Give You Up to my @spotify playlist whenever a new pull request arrives in an old repo of mine.
Zach Lanich@ZachLanichUm, wow 🤯 @pipedream
Steven Bell@bellontechI just used @pipedream to build a Shopify App. Wow, they make small backed tasks easy.
Jay Hack 🎩🇺🇸@_jayhack_Very impressed with this bad boi - it reminds me of a @PalantirTech internal tool, but geared towards integrations instead of data analysis and far more customizable. Great expectations here 🚀🤩
Tree Sturgeon 🔥🚴♂️🌳@philsturgeonFor context this is day 2 of a really challenging and stupid migration from Notion to @airtable with disparate/missing data. It's going better than expected and thanks to @pipedream I don't have to bother the iOS dev to add W3W.