client - VLM Run

Client Configuration

The VlmRun client is the main entry point for interacting with the VLM Run API. It provides access to all SDK functionality including file operations, model operations, and predictions.

Initialization

import { VlmRun } from "vlmrun";

const client = new VlmRun({
  apiKey: "your-api-key",
  // Optional configuration options
  baseUrl?: string;
});

Configuration Options

Option	Type	Description	Default
`apiKey`	`string`	Your VLM Run API key	Required
`baseUrl`	`string`	Custom API base URL	`https://api.vlm.run`

Client Components

The client provides access to different components for specific operations:

// File operations
client.files.upload({
  /* ... */
});
client.files.get();

client.files.list();

// Model operations
client.models.list();

// Image predictions
client.image.generate({
  /* ... */
});

// Document predictions
client.document.generate({
  /* ... */
});

Error Handling

The client throws typed errors for different scenarios:

import { VlmRun, ApiError } from "vlmrun";

try {
  const client = new VlmRun({
    apiKey: "invalid-key",
  });
  await client.models.list();
} catch (error) {
  if (error instanceof ApiError) {
    console.error("API Error:", error.message);
    console.error("Status:", error.http_status);
  } else if (error instanceof VlmRunError) {
    console.error("SDK Error:", error.message);
  } else {
    console.error("Unknown Error:", error);
  }
}

TypeScript Interfaces

interface ApiError extends Error {
  message: string;
  http_status: number;
  headers?: Record<string, string>;
}

interface VlmRunError extends Error {
  message: string;
  code?: string;
  cause?: Error;
}