Project Description
• Concept: Automate document handling using GenAI and Retrieval-Augmented Generation (RAG).
• Microservices:
o Ingestion Service: Extracts text from uploaded files (PDF/Images) using OCR.
o Vector Database Service: Stores embeddings (using ChromaDB or Pinecone).
o Query/Analysis Service: Uses LangChain to answer questions or classify documents.
• Automation: Automatically tags, classifies, and extracts metadata from invoices or contracts, storing them in the appropriate databases.
Key Skills Demonstrated
• Microservices Design: Independent deployment using Docker/Kubernetes, API Gateway.
• AI Integration: Deploying ML models (TensorFlow/PyTorch) as RESTful services or using streaming input.
• Automation: Event-driven architecture using Apache Kafka or RabbitMQ.
• Data Handling: Asynchronous processing of data between services
PROJECT 2) TITLE
• Containerized: Kubernetes
• Project tracker: Jira
• Logging system: Prometheus
• Messaging & task queuing: Amazon SQS
• Programming language: Python Flask, ReactJS, Golang
• Microservice: Apache Kafka, gRPC
• CI/CD pipeline:
• Automation:
• Database: DynamoDB