HN 표시: 일반 영어로 온프레미스 데이터베이스 및 DynamoDB 쿼리

IntelliHybrid is a production-ready, AI-powered framework that enables secure, seamless bidirectional communication between on-premise infrastructure and AWS cloud — with natural language querying, auto-generated schema documentation, and zero code changes after setup. IntelliHybrid bridges the gap between your on-premise data center and AWS cloud by: - 🔐 Establishing secure VPN tunnels (Site-to-Site, OpenVPN, or Direct Connect) - 🗄️ Connecting on-prem databases (MySQL, PostgreSQL, Oracle, SQL Server) to AWS - ⚡ Auto-provisioning DynamoDB tables with your custom Partition Key (PK) and Sort Key (SK) - 🔄 Bidirectional data synchronization — on-prem → cloud and cloud → on-prem - 🛡️ Enterprise-grade security — IAM roles, KMS encryption, TLS everywhere - 🤖 AI-powered data intelligence — query in plain English, auto-generated column descriptions, instant data dictionaries ┌─────────────────────────────────┐ ┌──────────────────────────────────┐ │ ON-PREMISE │ │ AWS CLOUD │ │ │ │ │ │ ┌─────────────┐ │◄───────►│ ┌──────────────────┐ │ │ │ Your DB │ │ VPN / │ │ DynamoDB │ │ │ │ MySQL / │ IntelliHybrid│ Direct │ │ Tables (auto- │ │ │ │ Postgres / │◄──────────────►│ Connect │ │ provisioned) │ │ │ │ Oracle │ │ │ └──────────────────┘ │ │ └─────────────┘ │ │ │ │ │ │ ┌──────────────────┐ │ │ ┌─────────────┐ │ │ │ AI Assistant │ │ │ │ App Server │ │ │ │ NL Queries + │ │ │ │ (any lang) │ │ │ │ Schema Intel │ │ │ └─────────────┘ │ │ └──────────────────┘ │ └─────────────────────────────────┘ └──────────────────────────────────┘ ▲ ▲ └──────── IntelliHybrid ───────┘ config.yaml + Claude AI drives all Experience natural language queries, schema intelligence, and data dictionaries in your browser — no setup needed. IntelliHybrid includes a full AI layer powered by Claude that understands your DynamoDB tables. No more writing queries — just ask. Write questions the way you'd say them out loud. IntelliHybrid translates them into the correct DynamoDB operation and returns live data. from src.ai.assistant import AIAssistant assistant = AIAssistant(config, anthropic_api_key="sk-ant-...") result = await assistant.chat("Show me all orders from customer C-001") result = await assistant.chat("How many products have stock below 10?") result = await assistant.chat("Find users who signed up this month") result = await assistant.chat("Add a new user: Jane Doe, email [email protected]") Examples of questions that just work: | What you type | What runs | |---|---| "Show me all orders from customer C-001" | query with KeyConditionExpression | "How many products are low on stock?" | scan with FilterExpression | "Find the 5 most recent signups" | scan with Limit + sort | "Get order ORD-8821" | get_item with exact key | "Delete expired session sess-99" | delete_item | The AI also maintains conversation history, so follow-up questions like "now filter those by electronics" work naturally. IntelliHybrid reads your table schema and a few sample rows, then generates clear business-friendly descriptions for every attribute — automatically. from src.ai.schema_intelligence import SchemaIntelligence intel = SchemaIntelligence(config, anthropic_api_key="sk-ant-...") description = await intel.describe_table("orders-table") { "table_description": "Stores customer order transactions with fulfillment status tracking", "attribute_descriptions": { "orderId": "Unique identifier for each order transaction", "customerId": "References the placing customer — links to users-table PK", "status": "Fulfillment state: processing, shipped, delivered, or cancelled", "total": "Order value in USD cents", "createdAt": "Unix timestamp when placed, used as sort key for date-range queries" }, "access_patterns": [ "Query all orders for a specific customer", "Get a single order by ID", "Filter orders by status for a fulfillment dashboard" ], "suggestions": [ "Consider adding a GSI on status+createdAt for pipeline queries" ] } One call produces a fully formatted markdown data dictionary — ready for wikis, compliance documentation, or technical portfolios. dictionary = await intel.generate_data_dictionary("orders-table") print(dictionary) # Data Dictionary: `orders-table` **Purpose:** Stores all customer order transactions... ## Attributes | Attribute | Type | Description | |--------------------|------|------------------------------------------------------| | `orderId` 🔑 PK | S | Unique identifier for each order transaction | | `customerId` 🔑 SK | S | References the customer — links to users-table PK | | `status` | S | Fulfillment state: processing, shipped, delivered... | | `total` | N | Order value in USD cents | | `createdAt` | N | Unix timestamp, used for date-range queries | ## Common Access Patterns 1. Query all orders for a specific customer 2. Get a single order by ID 3. Filter orders by status Expose the entire AI layer over HTTP — connect any frontend, dashboard, or external tool. pip install "intellihybrid[ai]" export ANTHROPIC_API_KEY="sk-ant-..." uvicorn src.ai.server:app -