📝 Research :https://ojitha.blogspot.com.au for my lengthy articles.
AWS Bedrock Multi-Agent RAG with LangGraph
This implementation demonstrates building Multi-Agent RAG systems using AWS Bedrock's Amazon Large Language Models (LLMs) integrated with LangGraph for intelligent document processing (IDP). The system implements document relevance grading using Titan Express LLM and integrates Chroma vector database with Amazon Titan embeddings for semantic search, processing articles into optimized chunks for RAG performance. LangGraph's workflow orchestration creates adaptive AI agents that automatically retry and transform queries up to 3 times with sophisticated conditional routing logic based on document relevance scores. The multi-agent architecture utilizes specialized Bedrock models for answer generation, document grading, and query rewriting, creating a production-ready system with LangChain Expression Language (LCEL) integration for seamless component chaining.
AWS S3 Access Points
This post delves into AWS S3 Access Points, highlighting how they simplify managing data access at scale by providing dedicated access policies per application. Learn how Access Points streamline S3 permissions, enhance security with granular controls, and support services like AWS PrivateLink for secure connectivity. Discover best practices for implementing and leveraging S3 Access Points for efficient and secure data lake management on AWS, crucial for modern cloud architectures.
Scala Notes
Explore fundamental Scala programming concepts including its functional and object-oriented nature, immutable variables , mutable variables, type inference, and basic syntax for defining functions and classes. This guide introduces key Scala features for developers familiar with other programming languages looking to understand its core principles and get started with Scala development. Discover the power and expressiveness of Scala through this concise overview of its building blocks.
Scala Collections
Explores the powerful Scala Collections library, detailing immutable and mutable collection types like Lists, Sets, and Maps, along with their common operations for efficient data manipulation. Understand the benefits of immutability and the flexibility of mutable collections in Scala for building robust applications. This guide highlights essential tools for any Scala developer working with structured data.
LLM Fine Tuning on AWS SageMaker
This comprehensive guide explores fine-tuning Large Language Models (LLMs) on AWS SageMaker, covering essential concepts from basic language model architecture to practical deployment. Learn about transformer-based models, self-attention mechanisms, and positional encoding that enable parallel processing of sequential data. Discover Parameter-Efficient Fine-Tuning (PEFT) techniques like LoRA that reduce trainable parameters by up to 10,000 times while maintaining performance. The tutorial demonstrates hands-on implementation using Databricks Dolly-v2-3b model, including dataset preparation, tokenization, and training configuration. Explore prompt engineering strategies including zero-shot, few-shot, and chain-of-thought approaches for optimal model outputs. Master n-gram tokenization principles underlying modern BPE and WordPiece methods. Follow step-by-step deployment instructions using SageMaker’s DJL framework, from model artifact creation to inference endpoint testing. Perfect for AI practitioners seeking cost-effective, domain-specific LLM customization on AWS infrastructure.