Architecture and Solution Overview

---

Key Features of the Solution

Streamlit in ECS

• Deployed in ECS for faster, containerized deployments compared to EC2.
• Easily adaptable to other compute environments.

Containerization Benefits

• Provides isolated environments, ensuring consistent deployments across different setups.

Tooling Selection

• Front-End Framework: Streamlit chosen for ease of building data applications for data analysts and data engineers.
• Python Implementation: Python framework used to build the front end (Streamlit).
• Time-Saving Components: Built-in Streamlit components reduced the need for custom UI coding.

Infrastructure Setup

• AWS as the Cloud Provider: Chosen for organizational support, team experience, and sandbox availability.
• Public Subnets: Default VPC and subnet configurations for quick setup, though future segregation is planned.
• Cost Considerations: Focused on maintaining a consistent environment while minimizing costs.

Database Choice

• Postgres: Selected for its vectorization capabilities and full-text search support, critical for generating accurate SQL query results.
• Initial configuration placed the database in a public subnet for simplicity.

Model Selection

• Amazon Bedrock Model (Claude Sonnet 3.5): Chosen for fast response times and strong code generation capabilities, essential for generating SQL queries.

Code Logic and Query Execution

• LangChain Usage: Two chains interact with Bedrock:
  1. Convert user queries into SQL queries.
  2. Convert SQL results into natural language responses.
• Prompt Engineering: Ensures SQL queries or natural language responses adhere to rules for accurate output.
• Query Execution: Queries executed against Postgres, with results fed back for natural language conversion.

App Link: http://customer-chatbot-771534023.us-east-1.elb.amazonaws.com/

Future Improvements

Planned Enhancements

1. Memory Store: Make memory non-local (Database Persistence) to retain query history across sessions.
2. Avoid Hard-Coded Configurations: Ensure easier updates and maintainability (Prompting rules).
3. Security Improvements: Privatize (Private Subnets) the database and adopt best practices.

---