← Lamini

Create Fine-Tune Job with Lamini API

Pipedream makes it easy to connect APIs for Lamini and 2,700+ other apps remarkably fast.

Trigger workflow on
HTTP requests, schedules and app events
Next, do this
Create Fine-Tune Job with the Lamini API
No credit card required
Intro to Pipedream
Watch us build a workflow
Watch us build a workflow
8 min
Watch now ➜

Trusted by 1,000,000+ developers from startups to Fortune 500 companies

Adyen logo
Appcues logo
Bandwidth logo
Checkr logo
ChartMogul logo
Dataminr logo
Gopuff logo
Gorgias logo
LinkedIn logo
Logitech logo
Replicated logo
Rudderstack logo
SAS logo
Scale AI logo
Webflow logo
Warner Bros. logo
Adyen logo
Appcues logo
Bandwidth logo
Checkr logo
ChartMogul logo
Dataminr logo
Gopuff logo
Gorgias logo
LinkedIn logo
Logitech logo
Replicated logo
Rudderstack logo
SAS logo
Scale AI logo
Webflow logo
Warner Bros. logo

Developers Pipedream

Getting Started

Create a workflow to Create Fine-Tune Job with the Lamini API. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

  1. Configure the Create Fine-Tune Job action
    1. Connect your Lamini account
    2. Select a Model Name
    3. Configure Dataset ID
    4. Optional- Configure Finetune Arguments
    5. Optional- Configure GPU Config
    6. Optional- Configure Is Public
    7. Optional- Configure Custom Model Name
    8. Optional- Configure Wait for Completion
  2. Select a trigger to run your workflow on HTTP requests, schedules or app events
  3. Deploy the workflow
  4. Send a test event to validate your setup
  5. Turn on the trigger

Integrations

Create Fine-Tune Job with Lamini API on New Requests (Payload Only) from HTTP / Webhook API
HTTP / Webhook + Lamini
 
Try it
Create Fine-Tune Job with Lamini API on New Submission from Typeform API
Typeform + Lamini
 
Try it
Create Fine-Tune Job with Lamini API on New Submission (Instant) from Jotform API
Jotform + Lamini
 
Try it
Create Fine-Tune Job with Lamini API on New Scheduled Tasks from Pipedream API
Pipedream + Lamini
 
Try it
Create Fine-Tune Job with Lamini API on New Download Counts from npm API
npm + Lamini
 
Try it

Details

This is a pre-built, source-available component from Pipedream's GitHub repo. The component is 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.

Create Fine-Tune Job on Lamini
Description:Create a fine-tuning job with a dataset. [See the documentation](https://docs.lamini.ai/api/).
Version:0.0.2
Key:lamini-create-fine-tune-job

Code

import app from "../../lamini.app.mjs";
import constants from "../../common/constants.mjs";
import utils from "../../common/utils.mjs";

export default {
  key: "lamini-create-fine-tune-job",
  name: "Create Fine-Tune Job",
  description: "Create a fine-tuning job with a dataset. [See the documentation](https://docs.lamini.ai/api/).",
  version: "0.0.2",
  type: "action",
  props: {
    app,
    modelName: {
      description: "Base model to be fine-tuned.",
      propDefinition: [
        app,
        "modelName",
        () => ({
          includeFineTunedModels: false,
        }),
      ],
    },
    datasetId: {
      type: "string",
      label: "Dataset ID",
      description: "Previously uploaded dataset to use for training. Please use the **Upload Dataset** action to upload a dataset.",
    },
    fineTuneArgs: {
      type: "object",
      label: "Finetune Arguments",
      description: "Optional hyperparameters for fine-tuning. Each property is optional:\n- `index_pq_m`: Number of subquantizers for PQ (eg. 8)\n- `index_max_size`: Maximum index size (eg. 65536)\n- `max_steps`: Maximum number of training steps (eg. 60)\n- `batch_size`: Training batch size (eg. 1)\n- `learning_rate`: Learning rate (eg. 0.0003)\n- `index_pq_nbits`: Number of bits per subquantizer (eg. 8)\n- `max_length`: Maximum sequence length (eg. 2048)\n- `index_ivf_nlist`: Number of IVF lists (eg. 2048)\n- `save_steps`: Steps between checkpoints (eg. 60)\n- `args_name`: Name for the argument set (eg. \"demo\")\n- `r_value`: R value for LoRA (eg. 32)\n- `index_hnsw_m`: Number of neighbors in HNSW (eg. 32)\n- `index_method`: Indexing method (eg. \"IndexIVFPQ\")\n- `optim`: Optimizer to use (eg. \"adafactor\")\n- `index_hnsw_efConstruction`: HNSW construction parameter (eg. 16)\n- `index_hnsw_efSearch`: HNSW search parameter (eg. 8)\n- `index_k`: Number of nearest neighbors (eg. 2)\n- `index_ivf_nprobe`: Number of IVF probes (eg. 48)\n- `eval_steps`: Steps between evaluations (eg. 30)\n[See the documentation](https://docs.lamini.ai/tuning/hyperparameters/#finetune_args).",
      optional: true,
    },
    gpuConfig: {
      type: "object",
      label: "GPU Config",
      description: "Optional GPU configuration for fine-tuning. [See the documentation](https://docs.lamini.ai/tuning/hyperparameters/#gpu_config).",
      optional: true,
    },
    isPublic: {
      type: "boolean",
      label: "Is Public",
      description: "Whether this fine-tuning job and dataset should be publicly accessible.",
      optional: true,
    },
    customModelName: {
      type: "string",
      label: "Custom Model Name",
      description: "A human-readable name for the fine-tuned model.",
      optional: true,
    },
    waitForCompletion: {
      type: "boolean",
      label: "Wait for Completion",
      description: "If set to `true`, the action will wait and poll until the fine-tuning job is `COMPLETED`. If is set to `false`, it will return immediately after creating the job.",
      default: false,
      optional: true,
    },
  },
  methods: {
    createFineTuneJob(args = {}) {
      return this.app.post({
        versionPath: constants.VERSION_PATH.V1,
        path: "/train",
        ...args,
      });
    },
  },
  async run({ $ }) {
    const {
      app,
      createFineTuneJob,
      modelName,
      datasetId,
      fineTuneArgs,
      gpuConfig,
      isPublic,
      customModelName,
      waitForCompletion,
    } = this;

    const MAX_RETRIES = 15;
    const DELAY = 1000 * 30; // 30 seconds
    const { run } = $.context;

    // First run: Create the fine-tune job
    if (run.runs === 1) {
      const { upload_base_path: uploadBasePath } =
        await app.getUploadBasePath({
          $,
        });

      await app.getExistingDataset({
        $,
        data: {
          dataset_id: datasetId,
          upload_base_path: uploadBasePath,
        },
      });

      const response = await createFineTuneJob({
        $,
        data: {
          model_name: modelName,
          dataset_id: datasetId,
          upload_file_path: `${uploadBasePath}/${datasetId}.jsonlines`,
          finetune_args: utils.parseJson(fineTuneArgs),
          gpu_config: utils.parseJson(gpuConfig),
          is_public: isPublic,
          custom_model_name: customModelName,
        },
      });

      $.export("$summary", `Successfully created a fine-tune job with ID \`${response.job_id}\`.`);

      // If user doesn't want to wait, return immediately
      if (!waitForCompletion) {
        return response;
      }

      // Store job_id for polling and start rerun
      $.flow.rerun(DELAY, {
        jobId: response.job_id,
      }, MAX_RETRIES);
      return response;
    }

    // Subsequent runs: Poll for job status
    if (run.runs > MAX_RETRIES) {
      throw new Error("Max retries exceeded - fine-tuning job may still be running");
    }

    const { jobId } = run.context;

    // Poll for status
    const statusResponse = await app.getJobStatus({
      $,
      jobId,
    });

    // If job is completed, return the final status
    if (statusResponse.status === "COMPLETED") {
      $.export("$summary", `Fine-tuning job \`${jobId}\` completed successfully.`);
      return statusResponse;
    }

    // If job failed, throw error
    if (statusResponse.status === "FAILED") {
      throw new Error(`Fine-tuning job \`${jobId}\` failed.`);
    }

    // Otherwise, continue polling
    $.flow.rerun(DELAY, {
      jobId,
    }, MAX_RETRIES);
    return {
      status: statusResponse.status,
      jobId,
      message: `Job is still running. Current status: ${statusResponse.status}`,
    };
  },
};

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.
LabelPropTypeDescription
LaminiappappThis component uses the Lamini app.
Model NamemodelNamestringSelect a value from the drop down menu.
Dataset IDdatasetIdstring

Previously uploaded dataset to use for training. Please use the Upload Dataset action to upload a dataset.

Finetune ArgumentsfineTuneArgsobject

Optional hyperparameters for fine-tuning. Each property is optional:

  • index_pq_m: Number of subquantizers for PQ (eg. 8)
  • index_max_size: Maximum index size (eg. 65536)
  • max_steps: Maximum number of training steps (eg. 60)
  • batch_size: Training batch size (eg. 1)
  • learning_rate: Learning rate (eg. 0.0003)
  • index_pq_nbits: Number of bits per subquantizer (eg. 8)
  • max_length: Maximum sequence length (eg. 2048)
  • index_ivf_nlist: Number of IVF lists (eg. 2048)
  • save_steps: Steps between checkpoints (eg. 60)
  • args_name: Name for the argument set (eg. "demo")
  • r_value: R value for LoRA (eg. 32)
  • index_hnsw_m: Number of neighbors in HNSW (eg. 32)
  • index_method: Indexing method (eg. "IndexIVFPQ")
  • optim: Optimizer to use (eg. "adafactor")
  • index_hnsw_efConstruction: HNSW construction parameter (eg. 16)
  • index_hnsw_efSearch: HNSW search parameter (eg. 8)
  • index_k: Number of nearest neighbors (eg. 2)
  • index_ivf_nprobe: Number of IVF probes (eg. 48)
  • eval_steps: Steps between evaluations (eg. 30)
    See the documentation
GPU ConfiggpuConfigobject

Optional GPU configuration for fine-tuning. See the documentation

Is PublicisPublicboolean

Whether this fine-tuning job and dataset should be publicly accessible.

Custom Model NamecustomModelNamestring

A human-readable name for the fine-tuned model.

Wait for CompletionwaitForCompletionboolean

If set to true, the action will wait and poll until the fine-tuning job is COMPLETED. If is set to false, it will return immediately after creating the job.

Authentication

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

About Lamini

Enterprise LLM Platform

More Ways to Use Lamini

Triggers

New Job Status from the Lamini API

Emit new events with the status of a training job. See the documentation

 
Try it

Actions

Evaluate Job with the Lamini API

Evaluate a fine-tuning job by job ID. See the documentation

 
Try it
Generate Completion with the Lamini API

Generate completions using a Lamini model. See the documentation

 
Try it
Get Batch Completions with the Lamini API

Retrieve the results of a batch completion request from Lamini. See the documentation

 
Try it
Upload Dataset with the Lamini API

Upload a dataset to Lamini for training.

 
Try it

Explore Other Apps

1
-
24
of
2,700+
apps by most popular

HTTP / Webhook
HTTP / Webhook
Get a unique URL where you can send HTTP or webhook requests
Node
Node
Anything you can do with Node.js, you can do in a Pipedream workflow. This includes using most of npm's 400,000+ packages.
Python
Python
Anything you can do in Python can be done in a Pipedream Workflow. This includes using any of the 350,000+ PyPi packages available in your Python powered workflows.
Pipedream Utils
Pipedream Utils
Utility functions to use within your Pipedream workflows
OpenAI (ChatGPT)
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.
Premium
Salesforce
Salesforce
Cloud-based customer relationship management (CRM) platform that helps businesses manage sales, marketing, customer support, and other business activities, ultimately aiming to improve customer relationships and streamline operations.
Premium
HubSpot
HubSpot
HubSpot's CRM platform contains the marketing, sales, service, operations, and website-building software you need to grow your business.
Premium
Zoho CRM
Zoho CRM
Zoho CRM is an online Sales CRM software that manages your sales, marketing, and support in one CRM platform.
Premium
Stripe
Stripe
Stripe powers online and in-person payment processing and financial solutions for businesses of all sizes.
Shopify
Shopify
Shopify is a complete commerce platform that lets anyone start, manage, and grow a business. You can use Shopify to build an online store, manage sales, market to customers, and accept payments in digital and physical locations.
Premium
WooCommerce
WooCommerce
WooCommerce is the open-source ecommerce platform for WordPress.
Premium
Snowflake
Snowflake
A data warehouse built for the cloud
Premium
MongoDB
MongoDB
MongoDB is an open source NoSQL database management program.
Supabase
Supabase
Supabase is an open source Firebase alternative.
MySQL
MySQL
MySQL is an open-source relational database management system.
PostgreSQL
PostgreSQL
PostgreSQL is a free and open-source relational database management system emphasizing extensibility and SQL compliance.
Premium
AWS
AWS
Amazon Web Services (AWS) offers reliable, scalable, and inexpensive cloud computing services.
Premium
Twilio SendGrid
Twilio SendGrid
Send marketing and transactional email through the Twilio SendGrid platform with the Email API, proprietary mail transfer agent, and infrastructure for scalable delivery.
Amazon SES
Amazon SES
Amazon SES is a cloud-based email service provider that can integrate into any application for high volume email automation
Premium
Klaviyo
Klaviyo
Email Marketing and SMS Marketing Platform
Premium
Zendesk
Zendesk
Zendesk is award-winning customer service software trusted by 200K+ customers. Make customers happy via text, mobile, phone, email, live chat, social media.
Premium
ServiceNow
ServiceNow
The smarter way to workflow
Notion
Notion
Notion is a new tool that blends your everyday work apps into one. It's the all-in-one workspace for you and your team.
Slack
Slack
Slack is a channel-based messaging platform. With Slack, people can work together more effectively, connect all their software tools and services, and find the information they need to do their best work — all within a secure, enterprise-grade environment.