AI & ML
Why Open Web RAG Fails in AWS Bedrock
Building production-ready GenAI applications requires grounding your Large Language Models (LLMs) in real-time information. While static…
MNMaleesha Nuwanthi Kolombage · · 3 min read
Topic14 articles
AI & ML
Bedrock, SageMaker and Amazon Q: shipping models and agents on AWS without the hand-waving.
AI & ML
5 Mistakes That Wasted Our Money on AWS SageMaker
5 Mistakes That Wasted Our Money on AWS SageMaker (and the Free Checks That Stop Them) We paid for GPU time just to find out our training jobs were broken. Here’s what went wrong. Imagine booking a …
Nishara Ramasingha · · 4 min read
AI & ML
When Not to Use Similarity Search in a RAG Pipeline
When Not to Use Similarity Search in a RAG Pipeline When we learn about RAG, the usual flow feels very natural. A user asks a question, we create an embedding, search the vector database, retrieve …
Navindu Chathuranga · · 5 min read
AI & ML
What If You Could Control Every AI Call From One Place?
What If You Could Control Every AI Call From One Place? A practical guide to putting one layer between your application and AI models, so you can track costs, switch models, manage access, and …
Navindu Chathuranga · · 14 min read
AI & ML
Multi-Tenant RAG on Amazon S3 Vectors - Part 1: The Isolation Model
Multi-Tenant RAG on Amazon S3 Vectors - Part 1: The Isolation Model Part 1 of 3. This part is the requirements and the isolation model. Part 2 is the cost model with the arithmetic. Part 3 is the …
Chameera Dulanga · · 7 min read
AI & ML
Beyond Similarity Search: Metadata Filtering for RAG with Amazon S3 Vectors
Beyond Similarity Search: Metadata Filtering for RAG with Amazon S3 Vectors Semantic search is one of the most useful parts of RAG. A user does not need to ask a question using the exact same words …
Navindu Chathuranga · · 6 min read
AI & ML
Building a Structure-Aware RAG Chunking Pipeline with Amazon Bedrock and S3 Vectors
Building a Structure-Aware RAG Chunking Pipeline with Amazon Bedrock and S3 Vectors A RAG system can use a good embedding model and a reliable vector database, but the results can still feel less …
Navindu Chathuranga · · 10 min read
AI & ML
Building a Serverless RAG Pipeline with Amazon S3 Vectors and Amazon Bedrock
Building a Serverless RAG Pipeline with Amazon S3 Vectors and Amazon Bedrock When I first learned about Retrieval-Augmented Generation (RAG), the architecture looked simple: Store some documents → …
Navindu · · 8 min read
AI & ML
Amazon Bedrock AgentCore Explained for Developers
Amazon Bedrock AgentCore Explained for Developers What is Amazon Bedrock AgentCore? Most AI agent demos look strong for five minutes. Then the hard questions show up. Where does the agent run? How …
Binara Prabhanga · · 6 min read
AI & ML
Prompt Injection in AI-Powered Applications
Prompt Injection in AI-Powered Applications How to Test Against Prompt Injection in AI-Powered Applications? Introduction Every AI system operates on instructions. But what happens when someone slips …
Navindu · · 8 min read
AI & ML
What Is Amazon S3 Vectors? Use Cases, When to Use It, and Cost
What Is Amazon S3 Vectors? Use Cases, When to Use It, and Cost Amazon S3 Vectors is AWS’s managed service for storing and searching vector embeddings inside the S3 ecosystem. In simple terms, it …
Chameera Dulanga · · 8 min read
AI & ML
How to Build a RAG Knowledge Base with Amazon S3 Vectors and Amazon Bedrock
How to Build a RAG Knowledge Base with Amazon S3 Vectors and Amazon Bedrock Amazon Bedrock Knowledge Bases Explained: How Managed RAG Works on AWS Building AI for a business is not just about picking …
Chameera Dulanga · · 9 min read
AI & ML
How I Built a Full-Stack Application Using Kiro, Kiro Powers, and MCP Servers
How I Built a Full-Stack Application Using Kiro, Kiro Powers, and MCP Servers A Chrome Extension Backed by an AWS Serverless Architecture As a Solutions Architect, one of my day-to-day tasks is …
Manoj Fernando · · 9 min read
AI & ML
How to Build a Smart Personal Chatbot with Assistant API
How to Build a Smart Personal Chatbot with Assistant API Interested in building your own intelligent personal chatbot that’s fully under your control? With OpenAI’s Assistant API, you can develop …
Bhathiya Ranasinghe · · 3 min read