Create Fine-Tune Job with Lamini API on New Access Proposal from Google Drive API

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

Trigger workflow on

New Access Proposal from the Google Drive API

Next, do this

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

Select this integration
Configure the New Access Proposal trigger
1. Connect your Google Drive account
2. Configure timer
3. Optional- Select a Drive
4. Select a File or Folder
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
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 Access Proposal on Google Drive

Description:Emit new event when a new access proposal is requested in Google Drive

Version:0.0.2

Key:google_drive-new-access-proposal

View on GitHub

Google Drive Overview#

The Google Drive API on Pipedream allows you to automate various file management tasks, such as creating, reading, updating, and deleting files within your Google Drive. You can also share files, manage permissions, and monitor changes to files and folders. This opens up possibilities for creating workflows that seamlessly integrate with other apps and services, streamlining document handling, backup processes, and collaborative workflows.

Trigger Code#

import googleDrive from "../../google_drive.app.mjs";
import { DEFAULT_POLLING_SOURCE_TIMER_INTERVAL } from "@pipedream/platform";
import sampleEmit from "./test-event.mjs";

export default {
  key: "google_drive-new-access-proposal",
  name: "New Access Proposal",
  description: "Emit new event when a new access proposal is requested in Google Drive",
  version: "0.0.2",
  type: "source",
  dedupe: "unique",
  props: {
    googleDrive,
    db: "$.service.db",
    timer: {
      type: "$.interface.timer",
      default: {
        intervalSeconds: DEFAULT_POLLING_SOURCE_TIMER_INTERVAL,
      },
    },
    drive: {
      propDefinition: [
        googleDrive,
        "watchedDrive",
      ],
    },
    fileOrFolderId: {
      propDefinition: [
        googleDrive,
        "fileOrFolderId",
        (c) => ({
          drive: c.drive,
        }),
      ],
    },
  },
  methods: {
    _getLastTs() {
      return this.db.get("lastTs") || 0;
    },
    _setLastTs(lastTs) {
      this.db.set("lastTs", lastTs);
    },
    generateMeta(item) {
      return {
        id: item.proposalId,
        summary: `New Request From: ${item.requesterEmailAddress}`,
        ts: Date.parse(item.createTime),
      };
    },
  },
  async run() {
    const lastTs = this._getLastTs();
    let maxTs = lastTs;
    let pageToken;

    do {
      const {
        accessProposals, nextPageToken,
      } = await this.googleDrive.listAccessProposals({
        fileId: this.fileOrFolderId,
        pageToken,
      });
      if (!accessProposals) {
        break;
      }
      for (const proposal of accessProposals) {
        const ts = Date.parse(proposal.createTime);
        if (ts > lastTs) {
          const meta = this.generateMeta(proposal);
          this.$emit(proposal, meta);
          maxTs = Math.max(ts, maxTs);
        }
      }
      pageToken = nextPageToken;
    } while (pageToken);

    this._setLastTs(maxTs);
  },
  sampleEmit,
};

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
Google Drive	`googleDrive`	`app`	This component uses the Google Drive app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
	`timer`	`$.interface.timer`
Drive	`drive`	`string`	Select a value from the drop down menu.
File or Folder	`fileOrFolderId`	`string`	Select a value from the drop down menu.

Trigger Authentication#

Google Drive uses OAuth authentication. When you connect your Google Drive account, Pipedream will open a popup window where you can sign into Google Drive and grant Pipedream permission to connect to your account. Pipedream securely stores and automatically refreshes the OAuth tokens so you can easily authenticate any Google Drive API.

Pipedream requests the following authorization scopes when you connect your account:

https://www.googleapis.com/auth/drive

About Google Drive#

Google Drive is a file storage and synchronization service which allows you to create and share your work online, and access your documents from anywhere.

Action#

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

View on GitHub

Action 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}`,
    };
  },
};

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
Lamini	`app`	`app`	This component uses the Lamini app.
Model Name	`modelName`	`string`	Select a value from the drop down menu.
Dataset ID	`datasetId`	`string`	Previously uploaded dataset to use for training. Please use the Upload Dataset action to upload a dataset.
Finetune Arguments	`fineTuneArgs`	`object`	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 Config	`gpuConfig`	`object`	Optional GPU configuration for fine-tuning. See the documentation
Is Public	`isPublic`	`boolean`	Whether this fine-tuning job and dataset should be publicly accessible.
Custom Model Name	`customModelName`	`string`	A human-readable name for the fine-tuned model.
Wait for Completion	`waitForCompletion`	`boolean`	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.

Action 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 Connect Lamini + Google Drive#

Other Popular Integrations#

Generate Completion with Lamini API on New Presentation (Instant) from Google Drive API

Google Drive + Lamini

Create Fine-Tune Job with Lamini API on New Access Proposal from Google Drive API

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

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

Developers ♥ Pipedream

1-24of2,700+apps by most popular

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