Skip to main content

Welcome to Actyze

Actyze is a secure, AI-powered analytics platform that lets enterprises ask questions across live data and act on insights—without ETL, lock-in, or compromise.

What is Actyze?​

Actyze transforms natural language into SQL queries instantly. Connect directly to your databases, ask questions in plain English (50+ languages supported), and get accurate insights without moving your data. Self-hosted and secure—your data never leaves your infrastructure.

"Show me total revenue by region for Q4 2025"
↓
SELECT region, SUM(revenue) as total_revenue 
FROM sales 
WHERE quarter = 'Q4' AND year = 2025 
GROUP BY region

Key Features​

Natural Language to SQL​

Powered by advanced language models, Actyze understands complex business questions and generates accurate SQL queries. Recommended: Claude Sonnet 4.5, GPT-4o, or equivalent models for optimal results.

Multilingual Support (50+ Languages)​

Query your data in over 50 languages including English, Spanish, French, German, Chinese, Japanese, Arabic, Hindi, and more. Powered by advanced multilingual semantic embeddings for accurate schema matching across languages.

Intelligent Schema Detection​

FAISS-powered semantic search combined with spaCy Named Entity Recognition ensures the right tables and columns are selected for your queries.

Private & Secure​

Deploy Actyze within your own infrastructure. Your data never leaves your network. Supports Kubernetes and Docker deployments.

Multi-Database Support​

Connect to Trino, PostgreSQL, and other popular data sources from a single interface.

Fast & Scalable​

  • Query generation in 1-3 seconds with external LLMs
  • Schema recommendations in under 100ms
  • Kubernetes-native with horizontal scaling

Architecture​

Actyze consists of core components that work together to transform natural language into SQL queries:

┌─────────────────┐    ┌──────────────────┐    ┌─────────────────┐
│   Frontend      │    │   Nexus API      │    │   PostgreSQL    │
│   (React+nginx) │───▶│   (FastAPI)      │───▶│   (Metadata DB) │
└─────────────────┘    └──────────────────┘    └─────────────────┘
                              │
                              ▼
                       ┌──────────────────┐
                       │  Schema Service  │
                       │  (FAISS+spaCy)   │
                       └──────────────────┘
                              │
                              ▼
                       ┌──────────────────┐
                       │      Trino       │
                       │   (Optional)     │
                       └──────────────────┘
                              │
                              │
        ┌─────────────────────┼─────────────────────┬─────────────────────┐
        │                     │                     │                     │
        ▼                     ▼                     ▼                     ▼
┌───────────────┐     ┌───────────────┐     ┌───────────────┐     ┌───────────────┐
│               │     │               │     │               │     │               │
│  PostgreSQL   │     │     MySQL     │     │   Snowflake   │     │    MongoDB    │
│               │     │               │     │               │     │               │
│  Your Data    │     │  Your Data    │     │  Your Data    │     │  Your Data    │
│               │     │               │     │               │     │               │
└───────────────┘     └───────────────┘     └───────────────┘     └───────────────┘

Components​

  • Frontend: React-based web application with nginx, providing the user interface
  • Nexus API: FastAPI orchestration service that handles LLM integration and query management
  • PostgreSQL: Stores user data, query history, metadata, and uploaded files
  • Schema Service: FAISS vector search with spaCy NER for intelligent schema recommendations
  • Trino: Optional distributed SQL query engine that connects to multiple data sources (PostgreSQL, MySQL, Snowflake, MongoDB, and more)
  • Your Databases: Connect your existing databases through Trino connectors for unified querying

Deployment-Specific Details:

Deployment Options​

For Local Development & Testing​

Use Docker Compose for quick setup and iteration:

cd dashboard
./docker/start.sh

Access at http://localhost:3000

📖 See: Docker Deployment Guide

For Production​

Deploy to Kubernetes using Helm charts:

helm install dashboard ./dashboard \
  --namespace actyze \
  --create-namespace \
  --values dashboard/values.yaml \
  --values dashboard/values-secrets.yaml

📖 See: Helm Deployment Guide

LLM Provider Support​

Actyze supports any LLM provider with flexible authentication:

ProviderBest ForResponse Time
Claude Sonnet 4.5Recommended - Superior accuracy2-5s
GPT-4oRecommended - Excellent accuracy3-6s
PerplexityFast inference2-4s
GroqUltra-fast inference<1s
Together AIOpen source models1-3s

Note: Any equivalent or higher-performance models will also provide excellent results.

📖 See: LLM Provider Configuration

Quick Start​

Get started with Actyze in three steps:

  1. Install Actyze - Choose Docker or Helm
  2. Configure LLM Provider - Set up your AI model
  3. Connect Your Data Sources - Configure Trino connectors for your databases

Use Cases​

Business Intelligence​

Enable business analysts to query data without SQL knowledge:

  • "What were our top 10 products by revenue last quarter?"
  • "Show customer churn rate by region"

Data Exploration​

Let data scientists explore datasets faster:

  • "Find all tables containing customer information"
  • "Show me the schema for the sales database"

Operational Analytics​

Empower operations teams with real-time insights:

  • "How many orders are pending shipment?"
  • "Show inventory levels below reorder point"

Support & Resources​

Next Steps​

Ready to get started? Follow our installation guide:

→ Installation Guide