Quick Start

Get up and running with EasyRAG in 5 minutes using real API endpoints.

Prerequisites

• A EasyRAG account (sign up here)
• cURL or any HTTP client

Step 1: Get Your API Key

1. Sign up at easyrag.com
2. Navigate to Settings → API Keys
3. Click Generate API Key
4. Copy and save it securely (shown only once)

Your API key looks like: sk_abc123xyz...

⚠️ Keep your API key secure - store it in environment variables, never commit to Git.

Step 2: Upload Your First Document

Upload a PDF to create and index it in a dataset.

Request

bash
curl -X POST https://api.easyrag.com/v1/files/upload \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "datasetId=my-first-dataset" \
  -F "file=@document.pdf"

Replace:

• YOUR_API_KEY with your actual API key
• document.pdf with your file path

Response

json
{
  "success": true,
  "message": "Files processed and indexed successfully!",
  "files": [
    {
      "fileId": "f7a3b2c1-4d5e-6f7g",
      "originalName": "document.pdf",
      "datasetId": "my-first-dataset",
      "created": "2024-12-13T10:30:00.000Z"
    }
  ],
  "billed": {
    "fileCount": 1,
    "uploadUnits": 10
  }
}

Cost: 1 credit per file

The file is now indexed and ready to search!

Step 3: Search Your Document

Find relevant content using semantic search.

Request

bash
curl -X POST https://api.easyrag.com/v1/search \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "datasetId": "my-first-dataset",
    "question": "What is this document about?"
  }'

Response

json
{
  "success": true,
  "data": [
    {
      "score": 0.89,
      "pageContent": "This document outlines the key features...",
      "metadata": {
        "fileId": "f7a3b2c1-4d5e-6f7g",
        "originalName": "document.pdf"
      }
    }
  ]
}

Cost: 0.1 credit

Step 4: Get an AI Answer

Ask a question and get a ChatGPT-style answer.

Request

bash
curl -X POST https://api.easyrag.com/v1/query \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "datasetId": "my-first-dataset",
    "question": "Summarize the key points",
    "stream": false
  }'

Response

json
{
  "success": true,
  "data": {
    "result": "Based on the document, the key points are:\n\n1. Automated document processing\n2. Semantic search capabilities\n3. AI-powered question answering\n4. Multi-tenant architecture"
  }
}

Cost: 0.1 credit

What You Just Did

1. ✅ Created an API key
2. ✅ Uploaded and indexed a document
3. ✅ Searched for relevant content
4. ✅ Got an AI-generated answer

Next Steps

Upload Multiple Files

bash
curl -X POST https://api.easyrag.com/v1/files/upload \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "datasetId=my-first-dataset" \
  -F "file=@file1.pdf" \
  -F "file=@file2.pdf"

Add Metadata

bash
curl -X POST https://api.easyrag.com/v1/files/upload \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "datasetId=my-first-dataset" \
  -F 'metadata={"contract.pdf":{"department":"legal"}}' \
  -F "file=@contract.pdf"

Filter by Metadata

bash
curl -X POST https://api.easyrag.com/v1/search \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "datasetId": "my-first-dataset",
    "question": "contract terms",
    "filters": [{"key": "department", "match": {"value": "legal"}}]
  }'

Stream Responses

bash
curl -X POST https://api.easyrag.com/v1/query \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "datasetId": "my-first-dataset",
    "question": "Explain the main features",
    "stream": true
  }'

Using from Code

Node.js (Server-Side)

javascript
const apiKey = process.env.EASYRAG_API_KEY;

// Upload
const formData = new FormData();
formData.append('datasetId', 'my-first-dataset');
formData.append('file', fs.createReadStream('document.pdf'));

await fetch('https://api.easyrag.com/v1/files/upload', {
  method: 'POST',
  headers: { 'Authorization': `Bearer ${apiKey}` },
  body: formData
});

// Search
const searchRes = await fetch('https://api.easyrag.com/v1/search', {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${apiKey}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    datasetId: 'my-first-dataset',
    question: 'What is this about?'
  })
});

const { data } = await searchRes.json();

// Query
const queryRes = await fetch('https://api.easyrag.com/v1/query', {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${apiKey}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    datasetId: 'my-first-dataset',
    question: 'Summarize this',
    stream: false
  })
});

const { data: answer } = await queryRes.json();

Python (Server-Side)

python
import requests
import os

api_key = os.environ['EASYRAG_API_KEY']
headers = {'Authorization': f'Bearer {api_key}'}

# Upload
files = {'file': open('document.pdf', 'rb')}
upload_res = requests.post(
    'https://api.easyrag.com/v1/files/upload',
    headers=headers,
    data={'datasetId': 'my-first-dataset'},
    files=files
)

# Search
search_res = requests.post(
    'https://api.easyrag.com/v1/search',
    headers={**headers, 'Content-Type': 'application/json'},
    json={
        'datasetId': 'my-first-dataset',
        'question': 'What is this about?'
    }
)

# Query
query_res = requests.post(
    'https://api.easyrag.com/v1/query',
    headers={**headers, 'Content-Type': 'application/json'},
    json={
        'datasetId': 'my-first-dataset',
        'question': 'Summarize this',
        'stream': False
    }
)

Common Issues

"Invalid API key"

• Ensure key starts with sk_
• Check for extra spaces
• Verify it hasn't been revoked

"Insufficient credits"

• Check balance in dashboard
• Purchase more credits
• Uploads cost 1 credit, queries cost 0.1 credit

File upload fails

• Max 100MB for documents, 2GB for media
• Supported: .pdf, .docx, .xlsx, .pptx, .csv, .mp3, .wav, .mp4

API Endpoints

Learn More

• Authentication - API keys and tokens
• Uploading Files - Advanced options
• Searching - Search guide
• Asking Questions - Query guide
• API Reference - Full API docs

Support

📧 support@easyrag.com