Enterprise AI Platform for Intelligent Applications

Getting Started • API Reference • Deployment • Examples

Overview

Devana.ai is an enterprise-grade AI platform that empowers organizations to deploy, integrate, and control AI assistants at scale. Built for privacy, compliance, and performance.

Key Capabilities

🤖 Custom AI Agents          📄 Document Intelligence      🔐 Enterprise Security
   Deploy specialized         Process & analyze docs        SSO, RBAC, audit logs
   assistants in minutes      with Odin engine              GDPR & SOC 2 ready

🔌 Flexible Integration      📊 Usage Analytics            🏢 On-Premise Ready
   REST API, WebSocket,       Track tokens, costs,          Full Kubernetes support
   IFrame, SDKs               and performance               Private cloud deployment

Getting Started

Cloud Deployment

The fastest way to get started with Devana.ai:

# 1. Create account at devana.ai
# 2. Generate API key from Settings → API
# 3. Make your first request

curl -X POST https://api.devana.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "agentId": "your-agent-id",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Next steps:

• Authentication Guide
• API Reference
• Integration Examples

Self-Hosted Deployment

Deploy Devana.ai in your infrastructure for full control:

1. Review Requirements → Sizing & Specifications
2. Configure LLM Providers → LLM Configuration
3. Deploy with Kubernetes → Installation Guide

Prerequisites:

• Kubernetes 1.24+
• PostgreSQL 14+
• 16GB RAM minimum (see requirements for production sizing)

Documentation

For Developers

API Reference

Complete REST API documentation for building AI-powered applications.

• Agents - Manage AI agents
• Conversations - Chat & history
• Completions - Streaming responses
• Documents - Upload & process files

SDKs & Tools

Client libraries and integration packages.

• devana-ws-tools - WebSocket client
• n8n-nodes-devana - Workflow automation
• Custom integrations via Tools API

Integration Guides

Embed Devana.ai in your applications.

• IFrame Integration - Embed chatbots
• Custom Tools - Extend with your APIs
• Webhooks - Event-driven flows

Supported Formats

File types and data formats.

• Documents (PDF, Office, Text)
• Images with OCR support
• Structured data (JSON, CSV)

For DevOps & SysAdmins

Deployment Guide

Production-ready deployment.

• Requirements ⭐ Start here
• Kubernetes - K8s/OpenShift
• PostgreSQL - Database setup
• LLM Providers - Model configuration

Operations

Monitor and maintain your deployment.

• Health Checks - System monitoring
• License Management - Usage tracking
• Troubleshooting - Common issues

Authentication

Enterprise identity integration.

• Azure AD, Google Workspace
• LDAP, OIDC, SAML
• Custom SSO providers

Architecture

System design and scaling.

• Component architecture
• Data flows and security
• Performance optimization

For Product Teams

Changelogs

Track new features and improvements.

• Devana Platform - Main platform updates (v0.6.0108)
• Odin Service - Document processing engine (v0.1.25)

Examples

Basic Chat Completion

curl -X POST https://api.devana.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "agentId": "cm123abc",
    "messages": [
      {"role": "user", "content": "Explain quantum computing"}
    ]
  }'

Streaming Response

const response = await fetch("https://api.devana.ai/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    agentId: "cm123abc",
    messages: [{ role: "user", content: "Tell me a story" }],
    stream: true,
  }),
});

const reader = response.body.getReader();
// Process stream...

IFrame Integration

<!-- Embed an AI assistant in your webpage -->
<iframe
  src="https://app.devana.ai/chat/your-agent-id"
  width="100%"
  height="600px"
  frameborder="0"
></iframe>

WebSocket Real-Time

import { DevanaWSClient } from "devana-ws-tools";

const client = new DevanaWSClient({
  apiKey: "YOUR_API_KEY",
  agentId: "your-agent-id",
});

// Register custom tool
client.registerTool({
  name: "getWeather",
  handler: async (params) => {
    return { temperature: 22, condition: "sunny" };
  },
});

await client.connect();

More examples:

• IFrame Chatbot Widget
• Custom Tools Implementation
• n8n Workflow Automation

Architecture

┌─────────────────────────────────────────────────────────────┐
│                      Devana.ai Platform                     │
├─────────────────────────────────────────────────────────────┤
│                                                             │
│  ┌─────────────┐  ┌──────────────┐  ┌─────────────────┐   │
│  │  Front-end  │  │  API Server  │  │  Odin Service   │   │
│  │  (Next.js)  │◄─┤  (Node.js +  │◄─┤  (Document      │   │
│  │             │  │   GraphQL)   │  │   Processing)   │   │
│  └─────────────┘  └──────────────┘  └─────────────────┘   │
│         │                │                     │            │
│         └────────────────┼─────────────────────┘            │
│                          ▼                                  │
│            ┌───────────────────────────┐                    │
│            │  PostgreSQL               │                    │
│            │  (Relational + Vector DB) │                    │
│            └───────────────────────────┘                    │
│                                                             │
└─────────────────────────────────────────────────────────────┘
                          │
            ┌─────────────┼─────────────┐
            ▼             ▼             ▼
    ┌──────────┐   ┌───────────┐  ┌─────────┐
    │   LLM    │   │ Embedding │  │ Storage │
    │ Providers│   │  Models   │  │ (S3/...)│
    └──────────┘   └───────────┘  └─────────┘

Learn more: Architecture Documentation

Use Cases

🎓 Knowledge Management

Deploy RAG-powered assistants that answer questions from your documentation, wikis, and knowledge bases.

💼 Customer Support

Integrate AI agents into your support workflow with custom tools, CRM connections, and escalation handling.

📊 Document Processing

Extract, analyze, and summarize documents at scale with Odin's OCR and NLP capabilities.

🔧 Developer Tools

Build AI-powered features into your applications using our REST API, WebSocket SDK, or workflow automation.

Security & Compliance

• Data Privacy: On-premise deployment keeps your data within your infrastructure
• Access Control: Role-based permissions, SSO integration, audit logs
• Compliance Ready: GDPR, SOC 2, ISO 27001 compliance support
• Encryption: TLS in transit, encryption at rest for sensitive data

Learn more: Security Documentation

Support

Documentation & Resources

• 📖 Full Documentation
• 🎓 Integration Guides
• 🔧 Troubleshooting

Get Help

• 📧 Technical Support: support-it@devana.ai
• 🐛 Bug Reports: tyr.devana.ai
• 🌐 Website: devana.ai
• 💻 GitHub: Devana • Odin