Getting Started with the Vectorize API Client

Learn how to install the Vectorize client and make your first request.

Beta API

The Vectorize API is currently in beta. While we strive for stability, breaking changes may occasionally be necessary.

What you can do with the Vectorize Client

The Vectorize API enables you to programmatically:

• Manage pipelines - Create, start, stop, and monitor RAG pipelines
• Handle connectors - Create and manage source, destination, and AI platform connectors
• Process data - Extract text, and retrieve documents from a pipeline
• Monitor operations - Get pipeline events and metrics

Prerequisites

Before you begin, you'll need:

1. A Vectorize account
2. An API access token (create one here)
3. Your organization ID (see below)

Finding your Organization ID

Your organization ID is in the Vectorize platform URL:

https://platform.vectorize.io/organization/[YOUR-ORG-ID]

For example, if your URL is:

https://platform.vectorize.io/organization/ecf3fa1d-30d0-4df1-8af6-f4852bc851cb

Your organization ID is: ecf3fa1d-30d0-4df1-8af6-f4852bc851cb

Install the Vectorize Client

Python

pip install vectorize-client --upgrade

Node.js

npm install @vectorize-io/vectorize-client

Make Your First Request

Let's list your existing pipelines to verify everything is working:

Python

import vectorize_client as v

# Your credentials
org_id = "your-organization-id"
token = "your-api-token"

# Initialize the client
api = v.ApiClient(v.Configuration(access_token=token))

# Create API interface
pipelines_api = v.PipelinesApi(api)

# List all pipelines
try:
    response = pipelines_api.get_pipelines(org_id)
    print(f"Found {len(response.data)} pipelines:\n")
    
    for pipeline in response.data:
        print(f"  - {pipeline.name} (ID: {pipeline.id})")
        print(f"    Status: {pipeline.status}")
        print(f"    Created: {pipeline.created_at}\n")
        
except Exception as e:
    print(f"Error: {e}")

Node.js

const { Configuration, PipelinesApi } = require('@vectorize-io/vectorize-client');

// Your credentials
const orgId = 'your-organization-id';
const token = 'your-api-token';

// Initialize the client
const api = new Configuration({
    accessToken: token
});

// Create API interface
const pipelinesApi = new PipelinesApi(api);

async function listPipelines() {
    try {
        const response = await pipelinesApi.getPipelines({
            organization: orgId
        });
        
        console.log(`Found ${response.data.length} pipelines:\n`);
        
        for (const pipeline of response.data) {
            console.log(`  - ${pipeline.name} (ID: ${pipeline.id})`);
            console.log(`    Status: ${pipeline.status}`);
            console.log(`    Created: ${pipeline.createdAt}\n`);
        }
    } catch (error) {
        console.error('Error:', error.response?.status || error.message);
        if (error.response?.data) {
            console.error('Details:', error.response.data);
        }
    }
}

listPipelines();

Understanding the Response

A successful response will show your pipelines:

Found 2 pipelines:

  - Pipeline 1 (ID: aipcbf1b-3c22-449c-a1c4-a51023225a3c)
    Status: SHUTDOWN
    Created: 2025-06-13T17:46:22.895Z

  - Pipeline 2 (ID: aip2340c-0cc6-2372-81e0-4fdaa81c6116)
    Status: HIBERNATING
    Created: 2025-06-04T19:07:28.126Z

If you see an authentication error, verify:

• Your API access token is correct
• Your organization ID is correct

Next Steps

• Create a RAG Pipeline, perform vector search, and more
• Perform text extraction from unstructured data using Vectorize Iris
• Connect AI assistants using the MCP Server

Looking for a full working Python example? You can open it on Google Colab or download it from the GitHub repository

Looking for a full working Node.js example? You can find it on the GitHub repository

A complete reference for the Vectorize API can be found here: Vectorize API Reference. This site includes tools for interactively testing API calls as well as generating code in various programming languages.