Skip to Content
TypeScript SDKQuickstart

TypeScript SDK Quickstart

Get started with the Endee TypeScript SDK to build powerful vector search applications. This guide will walk you through installation, setup, and creating your first index.

Requirements

  • Node.js 18.0.0 or higher
  • Endee Local server running (see Quick Start)

New to Endee? Set up your local environment first by following the Quick Start Guide.

Installation

Install the Endee TypeScript SDK using npm:

npm install endee

Or using yarn:

yarn add endee

Setup Endee and Create Index

Initialize the Client

The Endee client is the main interface for all vector operations. Initialize it to connect to your local server:

import { Endee } from 'endee';
 
// Connect to local Endee server (defaults to localhost:8080)
const client = new Endee();

Using Authentication? If your server has NDD_AUTH_TOKEN set, pass the same token when initializing:

const client = new Endee('your-auth-token');

See Authentication for details.

Create a Dense Index

Create a vector index for semantic similarity search:

import { Endee, Precision } from 'endee';
 
const client = new Endee();
 
await client.createIndex({
  name: 'my_vectors',
  dimension: 384,
  spaceType: 'cosine',
  precision: Precision.INT8D,
});

Dense Index Parameters: (see CreateIndexOptions)

ParameterDescription
nameUnique name for your index
dimensionVector dimensionality (must match your embedding model’s output)
spaceTypeDistance metric - "cosine", "l2", or "ip" (see SpaceType)
MGraph connectivity - higher values increase recall but use more memory (default: 16)
efConConstruction-time parameter - higher values improve index quality (default: 128)
precisionQuantization precision (default: Precision.INT8D) - see Precision

Create a Hybrid Index

Hybrid indexes combine dense vector search with sparse vector search for improved retrieval. Add the sparseDimension parameter to enable hybrid search:

await client.createIndex({
  name: 'my_hybrid_index',
  dimension: 384,           // Dense vector dimension
  sparseDimension: 30000,   // Sparse vector dimension (vocabulary size)
  spaceType: 'cosine',
  precision: Precision.INT8D,
});

Additional Hybrid Parameter:

ParameterDescription
sparseDimensionSparse vector dimension (e.g., vocabulary size for SPLADE)

List and Access Indexes

// List all indexes
const indexes = await client.listIndexes();
 
// Get reference to an existing index
const index = await client.getIndex('my_vectors');
 
// Delete an index
await client.deleteIndex('my_vectors');

Complete Example

Here’s a complete example putting it all together:

import { Endee, Precision } from 'endee';
 
// Initialize client
const client = new Endee();
 
// Create a dense index
await client.createIndex({
  name: 'documents',
  dimension: 384,
  spaceType: 'cosine',
  precision: Precision.INT8D,
});
 
// Get the index
const index = await client.getIndex('documents');
 
// Add vectors
await index.upsert([
  {
    id: 'doc1',
    vector: [0.1, 0.2, ...],  // 384-dimensional vector
    meta: { title: 'First Document' },
    filter: { category: 'tech' },
  },
  {
    id: 'doc2',
    vector: [0.3, 0.4, ...],
    meta: { title: 'Second Document' },
    filter: { category: 'science' },
  },
]);
 
// Query the index
const results = await index.query({
  vector: [0.15, 0.25, ...],
  topK: 5,
});
 
for (const item of results) {
  console.log(`ID: ${item.id}, Similarity: ${item.similarity}`);
}

Next Steps

Now that you have your index set up, learn how to:

UsageUsage