Build powerful Generative AI applications using pgvector on Amazon Aurora PostgreSQL with Amazon Bedrock
This repository demonstrates sample implementations using pgvector, a powerful PostgreSQL extension for vector similarity search, seamlessly integrated with Aurora PostgreSQL and Amazon Bedrock for building production-ready AI applications.
- 📖 AWS Blog: Leverage pgvector and Aurora PostgreSQL for NLP, Chatbots and Sentiment Analysis
- 🚀 AWS Blog: Supercharging Vector Search with pgvector 0.8.0
- 🤖 AWS Blog: Database Development with AWS MCP Servers
- 🎓 AWS Workshop: Complete Hands-on Labs
- 🔧 PostgreSQL MCP Server Documentation
| Module | Duration | Difficulty | Description |
|---|---|---|---|
| Semantic Search & Sentiment Analysis | 45 min | 🟢 Beginner | Build a search engine that understands meaning and analyzes customer sentiment using Hugging Face models and Aurora ML |
| Product Recommendations | 45-60 min | 🟢 Beginner | Create a personalized product recommendation engine using Bedrock embeddings and similarity algorithms |
| Retrieval Augmented Generation (RAG) | 45-60 min | 🟡 Intermediate | Implement a Q&A chatbot with accurate, grounded responses using RAG architecture |
| Text Summarization | 45-60 min | 🟡 Intermediate | Build an automatic summarization system for large documents with key information extraction |
| Module | Duration | Difficulty | Description |
|---|---|---|---|
| Amazon Q Business Integration | 45-60 min | 🟡 Intermediate | Deploy an AI-powered data exploration platform for healthcare data democratization |
| Aurora ML + Bedrock Movies | 45-60 min | 🟡 Intermediate | Build a Netflix-style movie recommendation system using aws_ml extension |
| Bedrock Knowledge Bases | 45-60 min | 🟡 Intermediate | Create enterprise knowledge bases for financial documents with regulatory compliance |
| Blaize Bazaar | 45-60 min | 🔴 Advanced | Deploy a complete e-commerce platform with AI-powered search and recommendations |
| Incident Detection & Remediation | 45-60 min | 🔴 Advanced | Implement intelligent database monitoring with agentic workflows and auto-remediation using MCP servers |
- AWS account with appropriate permissions
- Basic knowledge of PostgreSQL and Python
- 15-30 minutes for environment setup
git clone https://github.com/aws-samples/aurora-postgresql-pgvector.git
cd aurora-postgresql-pgvector
# Deploy infrastructure
aws cloudformation create-stack \
--stack-name pgvector-workshop \
--template-body file://cloudformation/genai-pgvector-lab.yml \
--capabilities CAPABILITY_IAM- 🌱 Beginners: Start with Semantic Search → Product Recommendations → RAG
- 🚀 Advanced: Jump to Blaize Bazaar → Incident Detection → MCP Servers
- 🎯 Targeted: Choose specific labs based on your use case
- Amazon Aurora PostgreSQL with pgvector 0.8.0+
- Amazon Bedrock for foundation models
- Amazon SageMaker for ML hosting
- AWS MCP Servers for AI-database interactions
- Amazon Bedrock Agents for autonomous workflows
- ✅ Vector embeddings (up to 16,000 dimensions)
- ✅ HNSW and IVFFlat indexing
- ✅ Hybrid search capabilities
- ✅ RAG with streaming
- ✅ Multi-modal embeddings
- ✅ Agentic workflows
Pre-configured Code Editor (VS Code in browser) includes:
- Python 3.11 with ML/AI libraries
- PostgreSQL client tools with pgvector
- AWS CLI and SDKs
- Jupyter notebook support
- Pre-installed AI development extensions
This project is licensed under the MIT-0 License - see the LICENSE file for details.
- Educational Purpose: Sample code requiring adaptation for production use
- Cost Management: Running labs will incur AWS charges
- Clean Up: Always delete resources after completing labs
Ready to start? 🚀 Launch the Workshop | View Documentation