Getting Started with QuerySpire

Welcome to QuerySpire documentation. This guide will help you integrate our RAG retrieval engine into your AI applications.

Quick Start

Get up and running in less than 5 minutes:

npm install @queryspire/client

import { QuerySpire } from '@queryspire/client';

const client = new QuerySpire({
  apiKey: 'your-api-key'
});

const results = await client.query({
  text: 'What is RAG?',
  topK: 5
});

Installation

Node.js

npm install @queryspire/client

Python

pip install queryspire

Authentication

All API requests require an API key. You can generate one from your dashboard:

const client = new QuerySpire({
  apiKey: process.env.QUERYSPIRE_API_KEY
});

Query API

The Query API allows you to retrieve relevant documents based on semantic similarity:

const results = await client.query({
  text: 'your query text',
  topK: 10,
  filters: {
    category: 'documentation'
  }
});

Index API

Index your documents for retrieval:

await client.index({
  documents: [
    {
      id: 'doc-1',
      text: 'Document content',
      metadata: { category: 'docs' }
    }
  ]
});

Integration Guide

QuerySpire integrates seamlessly with popular frameworks:

LangChain
LlamaIndex
Haystack
Custom implementations

Optimization Tips

Maximize retrieval performance:

Use appropriate chunk sizes (512-1024 tokens)
Add rich metadata for filtering
Implement caching for frequent queries
Monitor analytics to identify bottlenecks

Documentation