TARQAAI
DOCUMENTATION

Quick Start

Generate API Key

Navigate to the API Keys tab in your dashboard and create a new key. Save it securely — you'll only see it once!

Make Your First Request

Use curl or your favourite HTTP client to test the API with your authentication key.

curl -X POST "https://api.tarqaai.com/api/v1/ask?model=model_name" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"message": "Hello, Tarqa!"}'

Start Building

Explore our endpoints, integrate with your application, and monitor usage in real-time.

Authentication

Authorization: Bearer YOUR_API_KEY

X-API-Key: YOUR_API_KEY

Endpoints Overview

Chat API

Fastest with advanced multimodal capabilities

Most advanced model for complex reasoning

Fast Gemini 2.0 for general tasks

RAG System

Upload and chunk your documents into searchable segments with vector embeddings.

Find relevant information using meaning-based search with relevance scoring.

AI generates responses using retrieved context from your documents.

{
  "title": "Product Documentation Q&A",
  "knowledgeBaseType": "custom"
}

{
  "conversationId": "conv_abc123",
  "documentText": "TarqaAI is a unified AI platform...",
  "metadata": {
    "source": "product-docs",
    "category": "features"
  }
}

{
  "conversationId": "conv_abc123",
  "message": "What AI models does TarqaAI support?",
  "model": "gemini-2.5-flash",
  "topK": 3
}

API Key Analytics

Code Generation

Document Q&A

Extract key terms from contracts, analyze legal documents, find specific clauses.

Summarize findings, extract methodology, compare multiple papers.

Build searchable documentation, internal wikis, customer support systems.

Extract diagnoses, medications, treatment plans from medical documents.

Create Conversation

curl -X POST https://api.tarqaai.com/api/v1/context/conversations/create \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "title": "Legal Contract Analysis",
    "knowledgeBaseType": "custom"
  }'

Index Your Document

curl -X POST https://api.tarqaai.com/api/v1/rag/index \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "conversationId": "conv_abc123",
    "documentText": "Your full document text here...",
    "metadata": {
      "filename": "contract.pdf",
      "uploadDate": "2025-12-07"
    }
  }'

Ask Questions

curl -X POST https://api.tarqaai.com/api/v1/rag/chat \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "conversationId": "conv_abc123",
    "message": "What are the payment terms in this contract?",
    "model": "gemini-2.5-flash",
    "topK": 5
  }'

Code Examples

import { useState } from 'react';

function SupportChatbot() {
  const [messages, setMessages] = useState([]);
  const [input, setInput] = useState('');
  const [loading, setLoading] = useState(false);

  const sendMessage = async () => {
    if (!input.trim()) return;

    const userMessage = { role: 'user', content: input };
    setMessages(prev => [...prev, userMessage]);
    setInput('');
    setLoading(true);

    try {
      const response = await fetch(`${BASE_URL}/v1/chat/completions`, {
        method: 'POST',
        headers: {
          'Authorization': 'Bearer YOUR_API_KEY',
          'Content-Type': 'application/json',
        },
        body: JSON.stringify({
          model: 'gemini-2.5-flash',
          messages: [...messages, userMessage],
          stream: false
        })
      });

      const data = await response.json();
      const aiMessage = {
        role: 'assistant',
        content: data.choices[0].message.content
      };

      setMessages(prev => [...prev, aiMessage]);
    } catch (error) {
      logger.error('Chat error:', error);
    } finally {
      setLoading(false);
    }
  };

  return (
    <div className="chat-container">
      <div className="messages">
        {messages.map((msg, i) => (
          <div key={i} className={`message ${msg.role}`}>
            {msg.content}
          </div>
        ))}
      </div>
      <input
        value={input}
        onChange={(e) => setInput(e.target.value)}
        onKeyPress={(e) => e.key === 'Enter' && sendMessage()}
        disabled={loading}
      />
    </div>
  );
}

from tarqa import TarqaAI
import PyPDF2

client = TarqaAI(api_key="sk-your-api-key")

def analyze_document(pdf_path, question):
    # Extract text from PDF
    with open(pdf_path, 'rb') as file:
        reader = PyPDF2.PdfReader(file)
        document_text = ""
        for page in reader.pages:
            document_text += page.extract_text()

    # Create conversation
    conversation = client.context.create_conversation(
        title="Document Analysis",
        knowledge_base_type="custom"
    )

    # Index document
    client.rag.index(
        conversation_id=conversation['id'],
        document_text=document_text,
        metadata={"filename": pdf_path}
    )

    # Ask question
    response = client.rag.chat(
        conversation_id=conversation['id'],
        message=question,
        model="gemini-2.5-flash",
        top_k=5
    )

    return response['answer']

# Usage
answer = analyze_document(
    "contract.pdf",
    "What are the termination clauses?"
)
print(answer)

Multi-Language Translator

Real-time translation using streaming responses

Sales Email Generator

Generate personalized sales emails at scale

Content Moderation

Automatically flag inappropriate content

Data Extraction

Extract structured data from unstructured text

SDKs & Libraries

JavaScript / TypeScript SDK

For Node.js, React, Vue, Next.js, and more

npm install @tarqa/sdk

Python SDK

For Flask, FastAPI, Django, and data science

pip install tarqa-sdk

Rate Limits

Error Handling

API key is missing, malformed, or invalid

Too many requests — see rate limits section

Account has run out of credits

Requested model is temporarily unavailable

Request body is malformed or missing required fields

Message exceeds model context window

RAG conversation ID does not exist

Internal server error — please retry