Build & Deploy

Create Your Account

Sign up for a free Vectorize account and create your first workspace.

1. Visit platform.vectorize.io
2. Click "Sign Up" and complete registration
3. Verify your email address
4. Create your first workspace

Connect Your Data Source

Connect to your first data source to start building your knowledge base.

// Using the Vectorize CLI
vectorize sources add \
  --type=google-drive \
  --name="Company Docs" \
  --folder-id="1ABC123DEF456" \
  --sync=realtime

Supported data sources include:

• Google Drive, Dropbox, OneDrive
• Notion, Confluence, SharePoint
• GitHub repositories
• Direct file uploads (PDF, DOCX, etc.)

Configure Your Pipeline

Set up your embedding model, chunking strategy, and vector database.

// Pipeline configuration
{
  "name": "knowledge-base-v1",
  "embedding": {
    "model": "text-embedding-ada-002",
    "dimensions": 1536
  },
  "chunking": {
    "strategy": "recursive",
    "chunkSize": 1000,
    "overlap": 200,
    "separators": ["\n\n", "\n", ". ", " "]
  },
  "vectorDatabase": {
    "provider": "pinecone",
    "environment": "us-west1-gcp"
  }
}

Test Your Pipeline

Run your first queries to ensure everything is working correctly.

// Test query using the API
curl -X POST https://api.vectorize.io/v1/search \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "How do I reset my password?",
    "pipeline_id": "your-pipeline-id",
    "limit": 5
  }'

Deploy Your Application

Integrate Vectorize into your application and deploy to production.

// Example Node.js integration
const { VectorizeClient } = require('@vectorize/sdk');

const vectorize = new VectorizeClient({
  apiKey: process.env.VECTORIZE_API_KEY
});

app.post('/search', async (req, res) => {
  const { query } = req.body;
  
  const results = await vectorize.search({
    query,
    pipelineId: 'your-pipeline-id',
    limit: 10
  });
  
  res.json(results);
});