Node.js and TypeScript

Start and follow fine-tuning runs from Node or TypeScript by calling the Langtrain REST API with fetch. No extra package is needed.

Node 18+
TypeScript
fetch

Authenticate

Create an API key in the dashboard under API keys and put it in LANGTRAIN_API_KEY. Keep it on the server; never ship it to a browser.

python

1export LANGTRAIN_API_KEY=sk-lt-...

Start a run from TypeScript

Upload your dataset in the dashboard and copy its ID, then start a run. The API reference lists every field.

python

1const API = "https://api.langtrain.xyz/api/v1";
2const headers = {
3  "X-API-Key": process.env.LANGTRAIN_API_KEY!,
4  "Content-Type": "application/json",
5};
6
7const res = await fetch(`${API}/training/jobs`, {
8  method: "POST",
9  headers,
10  body: JSON.stringify({
11    base_model: "meta-llama/Llama-3.1-8B-Instruct",
12    dataset_id: "YOUR_DATASET_ID",
13    training_method: "qlora",
14  }),
15});
16if (!res.ok) throw new Error(`${res.status}: ${await res.text()}`);
17const job = await res.json();

Wait for it to finish

Poll the run until its status is completed, failed or cancelled.

python

1let run = job;
2while (!["completed", "failed", "cancelled"].includes(run.status)) {
3  await new Promise((r) => setTimeout(r, 10_000));
4  run = await (await fetch(`${API}/training/jobs/${job.id}`, { headers })).json();
5  console.log(run.status, run.progress);
6}

Node.js and TypeScript

Start and follow fine-tuning runs from Node or TypeScript by calling the Langtrain REST API with fetch. No extra package is needed.

Node 18+
TypeScript
fetch

Authenticate

Create an API key in the dashboard under API keys and put it in LANGTRAIN_API_KEY. Keep it on the server; never ship it to a browser.

python

1export LANGTRAIN_API_KEY=sk-lt-...

Start a run from TypeScript

Upload your dataset in the dashboard and copy its ID, then start a run. The API reference lists every field.

python

1const API = "https://api.langtrain.xyz/api/v1";
2const headers = {
3  "X-API-Key": process.env.LANGTRAIN_API_KEY!,
4  "Content-Type": "application/json",
5};
6
7const res = await fetch(`${API}/training/jobs`, {
8  method: "POST",
9  headers,
10  body: JSON.stringify({
11    base_model: "meta-llama/Llama-3.1-8B-Instruct",
12    dataset_id: "YOUR_DATASET_ID",
13    training_method: "qlora",
14  }),
15});
16if (!res.ok) throw new Error(`${res.status}: ${await res.text()}`);
17const job = await res.json();

Wait for it to finish

Poll the run until its status is completed, failed or cancelled.

python

1let run = job;
2while (!["completed", "failed", "cancelled"].includes(run.status)) {
3  await new Promise((r) => setTimeout(r, 10_000));
4  run = await (await fetch(`${API}/training/jobs/${job.id}`, { headers })).json();
5  console.log(run.status, run.progress);
6}