Skip to content

Azterix101/genai-chatbot

Repository files navigation

Serverless Retail Sales RAG Copilot

Serverless RAG (Retrieval-Augmented Generation) architecture combining S3-based document stores with an Aurora Serverless PostgreSQL pgvector database and Amazon ECS container processors.

Request Flow

sequenceDiagram
    Client->>CloudFront: HTTPS Query
    CloudFront->>API Gateway: Route API Traffic
    API Gateway->>Orchestrator Lambda: Parse payload
    Orchestrator->>DynamoDB: Log user session state
    Orchestrator->>RAG Lambda (VPC): Synchronous trigger
    RAG Lambda->>Aurora PostgreSQL: pgvector similarity query
    Aurora PostgreSQL-->>RAG Lambda: Context chunk payload
    RAG Lambda->>LLM Provider: Grounded prompt execution
    LLM Provider-->>RAG Lambda: Formulated answer
    RAG Lambda-->>Orchestrator: 200 OK Response
    Orchestrator-->>Client: Answer Output
Loading

About

Serverless RAG chatbot using AWS S3, Aurora Serverless v2 (pgvector), Lambda, and ECS Fargate. Fully automated via Terraform and GitHub Actions.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors