build-on-aws/rag-postgresql-agent-bedrock
This application is built in four stages using infrastructure as code with CDK with Python to deploy. In the first stage, an Amazon Aurora PostgreSQL vector database is set up. In the second stage, the Knowledge Base for Amazon Bedrock is created using the established database. The third stage involves creating an Amazon
# Technical Summary Implements a multi-stage RAG system combining Bedrock Agents with Aurora PostgreSQL vector embeddings to handle both text and voice queries via WhatsApp, using CDK-managed infrastructure across Lambda, API Gateway, and DynamoDB for ticket/passenger data storage. The architecture leverages Bedrock's built-in agent orchestration to eliminate custom session management, while Aurora's pgvector extension stores embeddings generated by Titan Embeddings V2 for semantic search. Integrates Amazon Transcribe for voice-to-text conversion and Systems Manager Parameter Store for inter-stack configuration sharing in multi-stage deployments.
Stars
34
Forks
11
Language
Python
License
MIT-0
Category
Last pushed
Mar 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/data-engineering/build-on-aws/rag-postgresql-agent-bedrock"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.