Danny's Blog

📊 Amazon Bedrock & CloudWatch📌 What is CloudWatch?Amazon CloudWatch is a monitoring service for AWS resources and applications.It provides: Logs – Detailed records of events and invocations Metrics – Numerical measurements of system performance Alarms – Notifications when thresholds are crossed Dashboards – Visualizations for monitoring 🔑 Bedrock & CloudWatch Integration1. Model Invocation Logging Logs all inputs and outputs from Bedrock model invocations. Data can inclu...

🤖 Amazon Bedrock – Agents📌 What Are Agents?Agents in Amazon Bedrock are advanced components that can think, plan, and act on multi-step tasks.Unlike regular models that only provide answers, agents can perform real actions such as: Provisioning infrastructure Deploying applications Executing operations on systems Interacting with APIs, databases, and knowledge bases 🔑 Key Features of Bedrock Agents Multi-step task execution: Agents can follow a sequence of steps to complete...

🛡️ Amazon Bedrock – Guardrails📌 What Are Guardrails?Guardrails in Amazon Bedrock are a way to control and filter interactions between users and Foundation Models (FMs).They help ensure that AI responses are safe, reliable, and compliant with your requirements. 🔑 Key Features of Guardrails Filter harmful content: Block hate speech, insults, sexual, violent, or misconduct content. Block specific topics: Deny responses related to sensitive or restricted subjects (e.g., recipes, medic...

📚 GenAI Core Concepts – Tokenization, Context Window, EmbeddingsThese are foundational concepts in Generative AI.They appear frequently in exams and are critical to understanding how LLMs work. 1. 🔹 TokenizationDefinitionThe process of converting raw text into a sequence of smaller units called tokens.Tokens are what the model processes internally. Types of Tokenization Word-based tokenization Splits text into words. Example: "The cat sat" → ["The", "cat", ...

📚 Amazon Bedrock – Setting up RAG & Knowledge Base (Hands-on)This guide explains how to set up a Retrieval-Augmented Generation (RAG) pipeline and a Knowledge Base in Amazon Bedrock, using Amazon S3 for storage and Amazon OpenSearch Serverless as the vector database. 1. 🔍 Prerequisites IAM User (not root user) Administrator Access policy for the IAM user AWS services: Amazon Bedrock Amazon S3 Amazon OpenSearch Serverless (or external vector DB) PDF or text document to upload (e.g., e...

📚 Amazon Bedrock – RAG & Knowledge Base1. 🔍 What is RAG?RAG (Retrieval-Augmented Generation) = Retrieve information from an external data source → Augment the prompt → Generate a more accurate answer. Retrieval: Searches for latest or domain-specific data outside the model’s training set. Augmented Generation: Combines retrieved data with the original query before sending it to the model. No Fine-tuning Required: Can inject up-to-date information without retraining the model. ...

📊 Amazon Bedrock – Model Evaluation GuideEvaluating a Foundation Model (FM) is essential for quality control, business impact measurement, and bias detection. Amazon Bedrock offers multiple ways to evaluate models—both automatically and through human feedback—along with technical and business metrics. 1. 🔄 Automatic EvaluationAmazon Bedrock can automatically score a model’s performance on predefined tasks. Built-in Task Types Text summarization Question answering Text classification Open-...

📚 Amazon Bedrock Fine-Tuning & Model Selection 1. Different Providers & Model Capabilities Providers: Anthropic, Amazon, DeepSeek, Stability AI, etc. Models vary in strengths: Claude 3.5 Haiku → Best for text tasks. Amazon Nova Reel → Text-to-video / Image-to-video. Exam Tip: You will not be tested on which is best, only on what each can or cannot do. 2. Comparing Models Compare Mode: Test models side-by-side in Bedrock playground. Compare by: ✅ Capabilities (text, image, vi...

🧠 Generative AI & Amazon Bedrock1. What is Generative AI? Generative AI (Gen-AI): A type of deep learning that creates new data similar to what it learned. Can generate: Text Images Audio Code Video Example: ChatGPT generating human-like text. 2. Foundation Models (FM) Large AI models trained on diverse datasets. Expensive to build (can cost tens of millions of dollars). Examples: OpenAI (GPT-4o) Meta (LLaMA) Google (BERT) Amazon (Titan) Anthropic (Claude) Some are open-source (fre...

💰 AWS Cost and Budget Setup1. Access for IAM Users To let an IAM user view Billing and Cost Management,the administrator must enable:“IAM user and role access to Billing information”. --- 2. Key Billing Tools Bills: Shows a detailed breakdown of usage and charges. Free Tier: Displays remaining Free Tier usage on a dashboard. Budgets: Sends email alerts if your spending exceeds the set budget.