AI-Native Enterprise Intelligence Platform
Getting Started • Architecture • API Reference • Features • Contributing
- Overview
- Quick Links
- Documentation Structure
- Getting Started
- Architecture
- API Reference
- Features
- Development
- Deployment
- Integrations
- Security
- Tutorials
- Troubleshooting
- Reference
NeuronIP is a comprehensive enterprise intelligence platform that combines multiple capabilities into a unified AI-native system built on PostgreSQL. The platform provides end-to-end data intelligence, governance, and automation capabilities.
| Feature | Description | Status |
|---|---|---|
| 🔍 Semantic Knowledge Search | Vector-based semantic search across knowledge base with RAG pipeline | ✅ Active |
| 💬 Data Warehouse Q&A | Natural language to SQL with query execution and visualization | ✅ Active |
| 🤖 Customer Support Memory | AI-powered support with long-term memory and context awareness | ✅ Active |
| 🛡️ Compliance & Audit Analytics | Policy matching, anomaly detection, semantic filtering, audit trails | ✅ Active |
| ⚙️ Agent Workflows | Multi-step workflow execution with AI agents and NeuronDB integration | ✅ Active |
| Feature Category | Capabilities | Status |
|---|---|---|
| Data Governance | Column/Row-level security, RBAC, Policy management, Access controls | ✅ Active |
| Data Lineage | Table & column-level lineage, Impact analysis, Cross-system tracking | ✅ Active |
| Data Quality | Quality metrics, Trend analysis, Automated profiling, Outlier detection | ✅ Active |
| Data Catalog | Dataset management, Schema evolution tracking, Search & discovery | ✅ Active |
| Data Ingestion | 30+ connectors (Snowflake, BigQuery, MySQL, etc.), ETL integration | ✅ Active |
| Data Classification | Automated PII detection, Data classification, Masking | ✅ Active |
| Observability | Query performance tracking, Metrics collection, Health monitoring | ✅ Active |
| Knowledge Graph | Entity extraction, Relationship mapping, Graph traversal | ✅ Active |
| Versioning | Data versioning, Model versioning, Pipeline versioning | ✅ Active |
| Multi-Tenancy | Tenant isolation, Multi-region support, Workspace management | ✅ Active |
| Feature | Description | Status |
|---|---|---|
| Authentication | API Keys, JWT, OAuth 2.0, OIDC, SSO, 2FA, SCIM | ✅ Active |
| Authorization | RBAC, ABAC, Column/Row-level security, Permission management | ✅ Active |
| Privacy | DSAR automation, PIA, Consent management, GDPR compliance | ✅ Active |
| Audit | Comprehensive audit logging, Compliance reporting | ✅ Active |
| Data Protection | Encryption at rest, Data masking, PII detection | ✅ Active |
| Component | Purpose | Status |
|---|---|---|
| NeuronDB | AI-native database extensions for vectors, ML, embeddings | ✅ Active |
| NeuronAgent | AI agent framework with sessions and workflows | ✅ Active |
| NeuronMCP | Model Context Protocol tools for AI operations | ✅ Active |
| Webhooks | Event-driven integrations with external systems | ✅ Active |
| Slack/Teams | Notification and alert integrations | ✅ Active |
- Backend: Go 1.24+ with Gorilla Mux, Structured logging, Prometheus metrics
- Frontend: Next.js 14 with TypeScript, Tailwind CSS, React Query
- Database: PostgreSQL 16+ with NeuronDB extension, Row-level security
- Infrastructure: Docker, Kubernetes, Multi-region support, HA deployment
- Integrations: NeuronDB, NeuronAgent, NeuronMCP, 30+ data connectors
- 🚀 Getting Started Guide - Start using NeuronIP in minutes
- 📖 Feature Documentation - Learn about all features
- 🎓 Tutorials - Step-by-step guides
- 🔧 Troubleshooting - Common issues and solutions
- 🏗️ Architecture Overview - System design and components
- 💻 Development Setup - Set up your development environment
- 📝 API Reference - Complete API documentation
- 🤝 Contributing Guide - How to contribute
- 🐳 Docker Deployment - Deploy with Docker
- 📦 Production Packaging - How images are built and packaged
- ☸️ Production Deployment - Production checklist
- ☸️ Kubernetes Deployment - Kubernetes deployment guide
- 📊 Monitoring - Observability and monitoring
- 🔒 Security Guide - Security best practices
docs/
├── README.md # This file - Documentation index
├── getting-started.md # Quick start guide
├── authentication.md # API key & login flow
├── authentication-session.md # Session details
├── FEATURE_MAP.md # Module → UI → API → migrations map
├── UX_MAP.md # Dashboard routes & page archetypes
├── implementation-status.md # Implementation phases status
├── IMPLEMENTATION-COMPLETE.md # Completion summary
├── ENTERPRISE_FEATURES_IMPLEMENTATION.md
├── neurondb-capability-audit.md # NeuronDB capability audit
├── architecture/ # Architecture documentation
│ ├── README.md
│ ├── overview.md
│ ├── backend.md
│ ├── frontend.md
│ ├── database.md
│ ├── data-flow.md
│ └── request-flow.md # Request/response lifecycle & middleware order
├── api/ # API documentation
│ ├── README.md
│ ├── overview.md
│ ├── endpoints.md
│ ├── authentication.md
│ └── rate-limiting.md
├── features/ # Feature documentation
│ ├── semantic-search.md
│ ├── warehouse-qa.md
│ ├── support-memory.md
│ ├── compliance.md
│ ├── agent-workflows.md
│ └── (see Features section for full list)
├── development/ # Development guides
│ ├── setup.md
│ ├── contributing.md
│ ├── coding-standards.md
│ ├── testing.md
│ ├── debugging.md
│ ├── error-handling.md
│ ├── validation.md
│ ├── wizards.md
│ └── neurondb-local-dev.md
├── deployment/ # Deployment guides
│ ├── docker.md
│ ├── packaging.md
│ ├── production.md
│ ├── kubernetes.md
│ ├── monitoring.md
│ └── multi-region.md
├── competitive-analysis/ # Competitive analysis & status
│ └── README.md (+ comparison, gap analysis, etc.)
├── integrations/ # Integration guides
│ ├── neurondb.md
│ ├── neuronagent.md
│ ├── neuronmcp.md
│ └── custom-integrations.md
├── security/ # Security documentation
│ ├── overview.md
│ ├── authentication.md
│ ├── authorization.md
│ └── data-protection.md
├── tutorials/ # Tutorials and examples
│ ├── quick-start-tutorial.md
│ ├── semantic-search-tutorial.md
│ ├── warehouse-qa-tutorial.md
│ ├── agent-workflow-tutorial.md
│ └── api-integration-tutorial.md
├── troubleshooting/ # Troubleshooting guides
│ ├── common-issues.md
│ ├── performance.md
│ └── errors.md
└── reference/ # Reference documentation
├── configuration.md
├── environment-variables.md
├── database-schema.md
└── glossary.md
Quick start: To run the stack: QUICK-START.md. To load demo data: demo/QUICK-START.md.
New to NeuronIP? Start here:
- Quick Start Guide - Get NeuronIP running in 5 minutes
- Architecture Overview - Understand the system
- First Tutorial - Build your first integration
- ✅ Docker and Docker Compose
- ✅ PostgreSQL 16+ with NeuronDB extension
- ✅ Go 1.24+ (for backend development)
- ✅ Node.js 18+ (for frontend development)
💡 Tip: Check the Getting Started Guide for detailed setup instructions.
Understand how NeuronIP is built:
- System Overview - High-level architecture with diagrams
- Backend Architecture - Go services and design patterns
- Frontend Architecture - Next.js components and structure
- Database Design - Schema and data modeling
- Data Flow - How data moves through the system
- Request Flow - Request/response lifecycle and middleware order
Complete API documentation:
- API Overview - Introduction to the REST API
- Endpoints - Complete endpoint reference
- Authentication - Auth flows and security
- Rate Limiting - Quotas and limits
# Health check
curl http://localhost:8082/health
# Semantic search
curl -X POST http://localhost:8082/api/v1/semantic/search \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{"query": "What is NeuronIP?", "limit": 10}'Detailed documentation for each feature:
Search your knowledge base by meaning, not just keywords. Powered by vector embeddings and semantic similarity.
Key Capabilities:
- Vector-based semantic search with similarity scoring
- Document chunking and indexing with metadata support
- RAG (Retrieval-Augmented Generation) pipeline
- Collection management and organization
- Semantic document embedding and retrieval
- Context-aware search results
Ask natural language questions about your data warehouse and get SQL queries, visualizations, and explanations.
Key Capabilities:
- Natural language to SQL conversion
- Schema discovery and management
- Query execution and result visualization
- Query history and analytics
- Query optimization recommendations
- Result caching and performance tracking
AI-powered customer support with long-term memory and context awareness.
Key Capabilities:
- Ticket management with priority routing
- Conversation history and context preservation
- Similar case retrieval using semantic search
- AI agent integration with NeuronAgent
- Multi-turn conversation support
- Support analytics and metrics
Automated compliance checking, anomaly detection, and audit trail management.
Key Capabilities:
- Policy matching and enforcement
- Anomaly detection with ML-based patterns
- Comprehensive audit logging
- Compliance reporting and dashboards
- DSAR (Data Subject Access Request) automation
- PIA (Privacy Impact Assessment) workflows
- Consent management
Build and execute complex workflows with AI agents and long-term memory.
Key Capabilities:
- Workflow definition with YAML/JSON
- Multi-step agent orchestration
- State management and persistence
- Error recovery and retry logic
- Workflow templates and reuse
- Scheduled execution
- Monitoring and observability
- Clustering - Multi-node clustering, Raft, sharding, task queue
- Streaming & CDC - Real-time streaming and change data capture
- ML Lifecycle & Models - Model registry, governance, prompts
- Notion UI: Blocks & Databases - Notion-like blocks and databases
- Workload & Data Products - Workload management and data products
- Decision Dashboards & ITSM - Decision dashboards and ITSM integration
- Notebooks - Collaborative notebooks
- Onboarding & Partners - Onboarding flows and partner ecosystem
Data Lineage:
- Table-level and column-level lineage tracking
- End-to-end lineage across systems
- Impact analysis and risk scoring
- Automatic lineage discovery from queries
- Transformation logic capture
Data Quality:
- Automated quality checks and metrics
- Trend analysis and anomaly detection
- Data profiling with statistics
- Quality dashboards and reporting
- Alerting and notification system
Data Catalog:
- Dataset discovery and search
- Schema evolution tracking
- Metadata management
- Ownership and stewardship
- Comments and collaboration
Authentication & Authorization:
- API key management
- JWT token-based authentication
- OAuth 2.0 and OIDC integration
- Single Sign-On (SSO)
- Two-factor authentication (2FA)
- SCIM 2.0 user provisioning
Access Controls:
- Role-Based Access Control (RBAC)
- Attribute-Based Access Control (ABAC)
- Column-level security policies
- Row-level security with PostgreSQL RLS
- Permission management and auditing
Data Protection:
- PII detection and classification
- Data masking and anonymization
- Encryption at rest and in transit
- Consent management
- Privacy compliance automation
Query Performance:
- Query execution tracking
- Performance metrics and analytics
- Slow query identification
- Query optimization recommendations
Metrics & Analytics:
- Business metrics management
- Custom metric definitions
- Metric search and discovery
- Analytics dashboards
Health & Monitoring:
- Health check endpoints
- Component health tracking
- System metrics collection
- Prometheus integration
- Alerting and notifications
Supported Connectors (30+):
- Databases: PostgreSQL, MySQL, SQL Server, Oracle, Snowflake, BigQuery, Redshift, Databricks, Teradata, Azure SQL, Azure Synapse
- NoSQL: MongoDB, Cassandra, DynamoDB, Redis, Elasticsearch
- Data Lakes: S3, Azure Blob Storage
- Streaming: Kafka
- BI Tools: Tableau, Power BI, Looker
- ETL Tools: dbt, Airflow, Fivetran, Stitch
- CDP: Segment, HubSpot
- Monitoring: Splunk
- Entity extraction from text
- Relationship mapping and linking
- Graph traversal and exploration
- Entity search and discovery
- Knowledge graph visualization
- Data Versioning: Track data changes over time
- Model Versioning: ML model version management
- Pipeline Versioning: Data pipeline version tracking
- Schema Evolution: Automatic schema change detection and tracking
- Multi-Tenancy: Workspace isolation and management
- Multi-Region: Geographic distribution and data residency
- Backup & Recovery: Automated backups and disaster recovery
- High Availability: HA deployment with Kubernetes
- Billing: Usage tracking and billing integration
Resources for developers:
- Development Setup - Set up your environment
- NeuronDB Local Dev - Run NeuronIP with a local NeuronDB build
- Contributing Guide - How to contribute
- Coding Standards - Code style guide
- Testing Guide - Testing best practices
- Debugging Guide - Debugging tips
# Backend
cd api
go mod download
go run cmd/server/main.go
# Frontend
cd frontend
npm install
npm run devDeployment guides and best practices:
- Docker Deployment - Deploy with Docker Compose
- Production Packaging - How images are built and packaged
- Production Deployment - Production checklist
- Kubernetes Deployment - Kubernetes deployment guide
- Monitoring - Observability setup
# Start all services
docker compose up -d
# Check status
docker compose ps
# View logs
docker compose logs -f neuronip-apiIntegration guides:
- NeuronDB Integration - NeuronDB setup and usage
- NeuronAgent Integration - Agent configuration
- NeuronMCP Integration - MCP tools setup
- Custom Integrations - Build your own
Security documentation:
- Security Overview - Security architecture
- Authentication - Auth mechanisms
- Authorization - RBAC and permissions
- Data Protection - Encryption and privacy
Authentication docs (by topic): API key & login flow | Session details | API auth & tokens | Security auth
🔒 Security Note: Always use HTTPS in production and keep your API keys secure.
Step-by-step tutorials:
- Quick Start Tutorial - Your first NeuronIP integration
- Semantic Search Tutorial - Build a knowledge base
- Warehouse Q&A Tutorial - Connect your data warehouse
- Agent Workflow Tutorial - Create an AI workflow
- API Integration Tutorial - Integrate with external systems
Common issues and solutions:
- Common Issues - Frequently encountered problems
- Performance - Optimization tips
- Error Reference - Error codes and meanings
Reference documentation:
- Configuration - All configuration options
- Environment Variables - Complete env var reference
- Database Schema - Full schema documentation
- Glossary - Terminology and definitions
We welcome contributions! See our Contributing Guide for details. For repo-wide guidelines, see CONTRIBUTING.md.
- Read the Contributing Guide
- Follow Coding Standards
- Write tests for new features
- Update documentation
- Submit a pull request
Need help?
- 📖 Check the Troubleshooting Guide
- 💬 Open an issue on GitHub
- 📧 Contact support: support@neurondb.ai
- 🔒 For security issues, see SECURITY.md
This project is licensed under the MIT License - see the LICENSE file for details.
- Built with NeuronDB - AI-native database
- Powered by NeuronAgent - AI agent framework
- Integrated with NeuronMCP - Model Context Protocol
Made with ❤️ by the NeuronDB team