DataBrain - RAG AI Solutions

Overview

DataBrain provides a RESTful API that allows developers to harness the power of Retrieval-Augmented Generation (RAG) technology. With our API, you can upload documents, create knowledge bases, and generate highly accurate, contextually relevant responses based on your data.

Our API is organized around REST principles. All requests should be made to the base URL https://api.databrain.ai/rag, using HTTPS, and will return JSON-encoded responses with standard HTTP response codes.

Document Management

Upload and manage your documents that will serve as sources for the RAG system.

Query Capabilities

Retrieve information from your documents using natural language queries.

Secure & Scalable

Enterprise-grade security with token-based authentication and scalable infrastructure.

Authentication

DataBrain API uses token-based authentication. You'll need to include your API token in the Authorization header for all requests.

Authorization Header

Authorization: Bearer YOUR_API_TOKEN

You can obtain your API token from the DataBrain Dashboard under API Settings. Keep your token secure and don't share it in publicly accessible areas such as GitHub or client-side code.

All API requests must be made over HTTPS. Calls made over plain HTTP will fail.

Document Management

DataBrain supports various document types including PDF, TXT, DOCX, MP3, and CSV files. Documents are processed and chunked automatically for optimal retrieval.

Upload Document

POST

Upload and process a document to be used as a knowledge source for RAG queries.

Endpoint

https://api.databrain.ai/rag/documents/upload

Parameters

Parameter	Type	Required	Description
document	File	Yes	The document file to upload (PDF, TXT, CSV, DOCX, MP3)

Response (201 Created)

{
    "message": "Documento processado com sucesso",
    "document_id": "123e4567-e89b-12d3-a456-426614174000",
    "name": "exemplo.pdf",
    "type": "pdf",
    "chunks": 15
}

List Documents

GET

Retrieve a list of all documents uploaded by the current user.

Endpoint

https://api.databrain.ai/rag/documents

Parameters

No parameters required.

Response (200 OK)

{
    "documents": [
        {
            "id": "123e4567-e89b-12d3-a456-426614174000",
            "name": "exemplo1.pdf",
            "type": "pdf",
            "created_at": "2023-06-01T15:30:45Z"
        },
        {
            "id": "123e4567-e89b-12d3-a456-426614174001",
            "name": "exemplo2.txt",
            "type": "txt",
            "created_at": "2023-06-02T10:15:30Z"
        }
    ]
}

Queries

The heart of DataBrain's RAG system is the ability to query your documents using natural language and receive accurate, context-aware responses.

Query RAG

POST

Perform a RAG query against all documents in your knowledge base.

Endpoint

https://api.databrain.ai/rag/query

Request Body

Parameter	Type	Required	Description
query	String	Yes	The natural language query to process

Example Request

{
    "query": "Quais são os principais pontos do documento sobre política de privacidade?"
}

Response (200 OK)

{
    "answer": "Os principais pontos da política de privacidade incluem: 1) Coleta de dados pessoais apenas com consentimento; 2) Utilização de dados para melhorar serviços; 3) Não compartilhamento de dados com terceiros sem autorização; 4) Direito de acesso e retificação de dados pelo usuário; 5) Armazenamento seguro com criptografia.",
    "sources": [
        {
            "document_id": "123e4567-e89b-12d3-a456-426614174000",
            "document_name": "Política de Privacidade.pdf",
            "relevance": 0.92,
            "content": "A política de privacidade estabelece que coletamos dados pessoais apenas com consentimento explícito do usuário. Utilizamos estes dados exclusivamente para melhorar nossos serviços e experiência do usuário."
        },
        {
            "document_id": "123e4567-e89b-12d3-a456-426614174000",
            "document_name": "Política de Privacidade.pdf",
            "relevance": 0.87,
            "content": "Comprometemo-nos a não compartilhar dados pessoais com terceiros sem autorização expressa. Todos os usuários têm direito de acessar, retificar e excluir seus dados a qualquer momento."
        },
        {
            "document_id": "123e4567-e89b-12d3-a456-426614174000",
            "document_name": "Política de Privacidade.pdf",
            "relevance": 0.81,
            "content": "Todos os dados são armazenados em servidores seguros com criptografia de ponta a ponta, garantindo máxima proteção contra vazamentos e acessos não autorizados."
        }
    ]
}

Filtered Query

POST

Perform a RAG query against specific documents in your knowledge base.

Endpoint

https://api.databrain.ai/rag/filtered-query

Request Body

Parameter	Type	Required	Description
query	String	Yes	The natural language query to process
document_ids	Array	Yes	Array of document IDs to query against

Example Request

{
    "query": "Quais são os principais pontos do documento sobre política de privacidade?",
    "document_ids": ["123e4567-e89b-12d3-a456-426614174000", "123e4567-e89b-12d3-a456-426614174001"]
}

Response (200 OK)

{
    "answer": "Os principais pontos da política de privacidade incluem: 1) Coleta de dados pessoais apenas com consentimento; 2) Utilização de dados para melhorar serviços; 3) Não compartilhamento de dados com terceiros sem autorização; 4) Direito de acesso e retificação de dados pelo usuário; 5) Armazenamento seguro com criptografia.",
    "sources": [
        {
            "document_id": "123e4567-e89b-12d3-a456-426614174000",
            "document_name": "Política de Privacidade.pdf",
            "relevance": 0.92,
            "content": "A política de privacidade estabelece que coletamos dados pessoais apenas com consentimento explícito do usuário. Utilizamos estes dados exclusivamente para melhorar nossos serviços e experiência do usuário."
        },
        {
            "document_id": "123e4567-e89b-12d3-a456-426614174000",
            "document_name": "Política de Privacidade.pdf",
            "relevance": 0.87,
            "content": "Comprometemo-nos a não compartilhar dados pessoais com terceiros sem autorização expressa. Todos os usuários têm direito de acessar, retificar e excluir seus dados a qualquer momento."
        },
        {
            "document_id": "123e4567-e89b-12d3-a456-426614174000",
            "document_name": "Política de Privacidade.pdf",
            "relevance": 0.81,
            "content": "Todos os dados são armazenados em servidores seguros com criptografia de ponta a ponta, garantindo máxima proteção contra vazamentos e acessos não autorizados."
        }
    ]
}

Code Examples

Here are some examples of how to use the DataBrain API in different programming languages.

Upload a Document

curl -X POST \
  https://api.databrain.ai/rag/documents/upload \
  -H 'Authorization: Bearer YOUR_API_TOKEN' \
  -H 'Accept: application/json' \
  -F 'document=@/path/to/your/document.pdf'

Query RAG

curl -X POST \
  https://api.databrain.ai/rag/query \
  -H 'Authorization: Bearer YOUR_API_TOKEN' \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json' \
  -d '{
    "query": "What are the main points of the privacy policy?"
}'

Upload a Document

<?php
$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.databrain.ai/rag/documents/upload",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => [
    'document' => new CURLFILE('/path/to/your/document.pdf')
  ],
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer YOUR_API_TOKEN",
    "Accept: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

Query RAG

<?php
$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.databrain.ai/rag/query",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'query' => 'What are the main points of the privacy policy?'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer YOUR_API_TOKEN",
    "Content-Type: application/json",
    "Accept: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

Upload a Document

import requests

url = "https://api.databrain.ai/rag/documents/upload"

headers = {
    'Authorization': 'Bearer YOUR_API_TOKEN',
    'Accept': 'application/json'
}

files = {
    'document': open('/path/to/your/document.pdf', 'rb')
}

response = requests.post(url, headers=headers, files=files)

print(response.json())

Query RAG

import requests
import json

url = "https://api.databrain.ai/rag/query"

headers = {
    'Authorization': 'Bearer YOUR_API_TOKEN',
    'Content-Type': 'application/json',
    'Accept': 'application/json'
}

payload = {
    'query': 'What are the main points of the privacy policy?'
}

response = requests.post(url, headers=headers, data=json.dumps(payload))

print(response.json())

Upload a Document

const fs = require('fs');
const axios = require('axios');
const FormData = require('form-data');

async function uploadDocument() {
  const formData = new FormData();
  formData.append('document', fs.createReadStream('/path/to/your/document.pdf'));

  try {
    const response = await axios.post('https://api.databrain.ai/rag/documents/upload', formData, {
      headers: {
        ...formData.getHeaders(),
        'Authorization': 'Bearer YOUR_API_TOKEN',
        'Accept': 'application/json'
      }
    });
    
    console.log(response.data);
  } catch (error) {
    console.error(error);
  }
}

uploadDocument();

Query RAG

const axios = require('axios');

async function queryRag() {
  try {
    const response = await axios.post('https://api.databrain.ai/rag/query', {
      query: 'What are the main points of the privacy policy?'
    }, {
      headers: {
        'Authorization': 'Bearer YOUR_API_TOKEN',
        'Content-Type': 'application/json',
        'Accept': 'application/json'
      }
    });
    
    console.log(response.data);
  } catch (error) {
    console.error(error);
  }
}

queryRag();

API Documentation

Overview

Document Management

Query Capabilities

Secure & Scalable

Authentication

Authorization Header

Document Management

Upload Document

Endpoint

Parameters

Response (201 Created)

List Documents

Endpoint

Parameters

Response (200 OK)

Queries

Query RAG

Endpoint

Request Body

Example Request

Response (200 OK)

Filtered Query

Endpoint

Request Body

Example Request

Response (200 OK)

Code Examples

Upload a Document

Query RAG

Upload a Document

Query RAG

Upload a Document

Query RAG

Upload a Document

Query RAG

Need Help With Integration?

Comprehensive Documentation

Client Libraries

Developer Community

Ready to enhance your applications with DataBrain RAG?

Subscribe to our newsletter.