import fs from "fs";
import { ConfigurationError } from "@pipedream/platform";
import app from "../../lamini.app.mjs";
import constants from "../../common/constants.mjs";
export default {
key: "lamini-upload-dataset",
name: "Upload Dataset",
description: "Upload a dataset to Lamini for training.",
version: "0.0.2",
type: "action",
props: {
app,
fileUrl: {
type: "string",
label: "Dataset File URL",
description: "URL of the file containing your training data. Supported formats include `.jsonl` and `.jsonlines`. Eg. `https://raw.githubusercontent.com/lamini-ai/lamini-examples/refs/heads/main/data/results/spot_check_results.jsonl`.",
},
inputKey: {
type: "string",
label: "Input Key",
description: "Key of the JSON dictionary to use as the input. Eg. `question`.",
},
outputKey: {
type: "string",
label: "Output Key",
description: "Key of the JSON dictionary to use as the output. Eg. `answer`.",
optional: true,
},
isPublic: {
type: "boolean",
label: "Is Public",
description: "Whether this dataset should be publicly accessible.",
optional: true,
},
},
methods: {
uploadLocalData(args = {}) {
return this.app.post({
versionPath: constants.VERSION_PATH.V1,
path: "/local-data",
...args,
});
},
getUploadBasePath() {
return this.app.makeRequest({
versionPath: constants.VERSION_PATH.V1,
path: "/get-upload-base-path",
});
},
},
async run({ $ }) {
const {
app,
fileUrl,
inputKey,
outputKey,
isPublic,
} = this;
const {
fileName, filePath,
} = await app.downloadFileToTmp({
$,
url: fileUrl,
});
if (!fileName.endsWith(".jsonl") && !fileName.endsWith(".jsonlines")) {
throw new ConfigurationError(`Unsupported file format for \`${fileName}\`. Only **.jsonl** and **.jsonlines** files are supported.`);
}
const { upload_base_path: uploadBasePath } = await this.getUploadBasePath();
let allData = [];
const fileContent = fs.readFileSync(filePath, "utf8");
const lines = fileContent.trim().split("\n");
for (const line of lines) {
try {
const row = JSON.parse(line);
if (!row[inputKey]) {
throw new ConfigurationError(`File ${fileName} is missing required key: ${inputKey}`);
}
allData.push({
input: row[inputKey],
output: row[outputKey] || "",
});
} catch (e) {
if (e.message.includes("missing required key")) {
throw e;
}
}
}
if (allData.length === 0) {
throw new ConfigurationError("No valid data found in the provided files.");
}
const response = await this.uploadLocalData({
$,
data: {
upload_base_path: uploadBasePath,
data: allData,
is_public: isPublic,
},
});
$.export("$summary", `Successfully uploaded file as dataset with ID \`${response.dataset_id}\`.`);
return {
...response,
num_data_points: allData.length,
};
},
};
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.