# KodeKloud: Beta Courses Introduction to Amazon Bedrock ## Introduction to Amazon Bedrock ### Introduction to Gen AI and LLMs - [Course Introduction](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Introduction-to-Gen-AI-and-LLMs/Course-Introduction/page.md): Hands-on course introducing Amazon Bedrock, covering foundation models, access methods, prompt engineering, integrations with AWS, security, RAG, agents, observability, and practical labs. - [Gen AI and LLMs Introduction Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Introduction-to-Gen-AI-and-LLMs/Gen-AI-and-LLMs-Introduction-Part-1/page.md): Overview of generative AI and large language models, their differences from traditional ML, enterprise use cases, and adaptation methods like prompt engineering, RAG, and fine tuning - [Gen AI and LLMs Introduction Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Introduction-to-Gen-AI-and-LLMs/Gen-AI-and-LLMs-Introduction-Part-2/page.md): Overview of hosting, tool integration, and use cases for pre-trained generative AI models, including retrieval-augmented patterns and governance for up-to-date private data - [Gen AI and LLMs Introduction Part 3](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Introduction-to-Gen-AI-and-LLMs/Gen-AI-and-LLMs-Introduction-Part-3/page.md): Overview of generative AI and large language models covering modalities, multimodal applications, developer code assistance, creative content generation, and selecting models for enterprise use with Amazon Bedrock context ### Introduction to Amazon Bedrock - [Amazon Bedrock Introduction Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Introduction-to-Amazon-Bedrock/Amazon-Bedrock-Introduction-Part-1/page.md): Introduction to Amazon Bedrock explaining how AWS provides a single managed API to access multiple foundation models, simplifying hosting, governance, privacy, and model selection - [Amazon Bedrock Introduction Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Introduction-to-Amazon-Bedrock/Amazon-Bedrock-Introduction-Part-2/page.md): Overview of Amazon Bedrock usage patterns, managed service features, model selection, request flow, privacy considerations, and extensibility for integrating foundation models via a single API - [Basic Bedrock Architecture Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Introduction-to-Amazon-Bedrock/Basic-Bedrock-Architecture-Part-1/page.md): Overview of Amazon Bedrock architecture, runtime request flow, managed responsibilities, optional features like Guardrails RAG and agents, and operational responsibilities for secure scalable GenAI deployments - [Basic Bedrock Architecture Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Introduction-to-Amazon-Bedrock/Basic-Bedrock-Architecture-Part-2/page.md): Describes Amazon Bedrock hosting options including serverless, provisioned throughput, and marketplace dedicated hosting with trade offs, billing, and deployment guidance for GenAI - [Supported Foundation Models](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Introduction-to-Amazon-Bedrock/Supported-Foundation-Models/page.md): Guide to choosing foundation models in Amazon Bedrock, comparing modalities, model sizes, costs, availability, token limits, and practical steps for selecting and evaluating models ### Getting Started With Amazon Bedrock - [Accessing the Bedrock Console Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Getting-Started-With-Amazon-Bedrock/Accessing-the-Bedrock-Console-Part-1/page.md): Guide to using the Amazon Bedrock console to explore models, test prompts in the Playground, compare behavior and pricing, and iterate safely before building applications - [Accessing the Bedrock Console Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Getting-Started-With-Amazon-Bedrock/Accessing-the-Bedrock-Console-Part-2/page.md): Guide to using Amazon Bedrock console to discover, test, and run image and video models via the Model Catalog and Playground, including region availability and permissions - [Accessing Bedrock With Command Line Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Getting-Started-With-Amazon-Bedrock/Accessing-Bedrock-With-Command-Line-Part-1/page.md): How to use the AWS CLI to access Amazon Bedrock, covering control plane versus runtime commands, authentication methods, examples, and best practices for secure, scriptable model inference - [Accessing Bedrock With Command Line Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Getting-Started-With-Amazon-Bedrock/Accessing-Bedrock-With-Command-Line-Part-2/page.md): Explains four AWS CLI authentication methods for accessing Amazon Bedrock and Bedrock Runtime, comparing long lived keys, CLI v2 browser login, IAM Identity Center SSO, and CloudShell. - [Demo Accessing Bedrock With Command Line Part 3](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Getting-Started-With-Amazon-Bedrock/Demo-Accessing-Bedrock-With-Command-Line-Part-3/page.md): Tutorial showing how to use the AWS CLI to call Amazon Bedrock, demonstrating invoke-model and converse examples, payloads, outputs, and credential best practices. - [Inference Profiles](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Getting-Started-With-Amazon-Bedrock/Inference-Profiles/page.md): Explains Amazon Bedrock inference profiles, why some model IDs need prefixes like us., how to add them in code, and routing and capacity tradeoffs. - [Bedrock API Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Getting-Started-With-Amazon-Bedrock/Bedrock-API-Part-1/page.md): Explains connecting applications to Amazon Bedrock, compares control plane and runtime APIs, recommends using AWS SDKs, and provides examples for model invocation and configuration. - [Bedrock API Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Getting-Started-With-Amazon-Bedrock/Bedrock-API-Part-2/page.md): Compares Bedrock InvokeModel low-level model-specific API with Converse high-level message-based API, explaining use cases, examples, and best practices for invoking foundation models. - [Demo Bedrock API Part 3](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Getting-Started-With-Amazon-Bedrock/Demo-Bedrock-API-Part-3/page.md): Demonstrates using Amazon Bedrock with Boto3 in two Python examples, model-specific prompt invocation and a vendor-agnostic unified messages approach. ### Foundation Models in Amazon Bedrock - [Available Models](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Foundation-Models-in-Amazon-Bedrock/Available-Models/page.md): Practical guidance for choosing and evaluating foundation models in Amazon Bedrock, addressing modality, context window, cost, latency, testing, provisioning, and routing ### Basic Concepts of Prompt Engineering - [What Is a prompt](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Basic-Concepts-of-Prompt-Engineering/What-Is-a-prompt/page.md): Explains what prompts are and how to write structured instructions—role, context, task, audience, constraints—to obtain consistent, high-quality outputs from large language models. - [Components of a Prompt](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Basic-Concepts-of-Prompt-Engineering/Components-of-a-Prompt/page.md): Explains building effective prompts with context, instructions, inputs, and output schemas to produce predictable, machine-usable responses and avoid common prompt mistakes. ### Introduction to Text Generation With Amazon Bedrock - [Bedrock Playground and API Demonstrations](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Introduction-to-Text-Generation-With-Amazon-Bedrock/Bedrock-Playground-and-API-Demonstrations/page.md): Guide to exploring Amazon Bedrock models in the console Playground and calling Bedrock programmatically from Python using boto3, with examples and best practices ### How Foundation Models Process Input - [Understanding Tokens](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/How-Foundation-Models-Process-Input/Understanding-Tokens/page.md): Describes tokenization, token impact on context limits cost and performance, and practical prompt and workflow strategies to manage token usage - [Understanding Context Window](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/How-Foundation-Models-Process-Input/Understanding-Context-Window/page.md): Explains model context windows, causes of truncated outputs, and practical strategies like token tracking, chunking, summarization, and model choice to avoid truncation. - [Controlling Model Parameters](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/How-Foundation-Models-Process-Input/Controlling-Model-Parameters/page.md): Explains how to use temperature, topP, and maxTokens to control model output randomness, diversity, and length. ### Extract Insights Using Prompt Engineering - [Demonstration of Prompt Engineering Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Extract-Insights-Using-Prompt-Engineering/Demonstration-of-Prompt-Engineering-Part-1/page.md): Introduction to iterative prompt engineering using Amazon Bedrock, demonstrating techniques and constrained JSON outputs to produce consistent, machine‑readable classifications for IT support tickets - [Demonstration of Prompt Engineering Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Extract-Insights-Using-Prompt-Engineering/Demonstration-of-Prompt-Engineering-Part-2/page.md): Guide to prompt engineering showing role, strict JSON schema, few-shot examples, and a Python Amazon Bedrock example to produce consistent machine-readable outputs ### Working With Different Task Types - [Exploring Text Summarization](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Working-With-Different-Task-Types/Exploring-Text-Summarization/page.md): Using foundation models and prompt design to create concise audience-specific summaries that reduce report overload and improve decision making while minimizing hallucinations - [Implementing Question Answering](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Working-With-Different-Task-Types/Implementing-Question-Answering/page.md): Guide to implementing context-based question answering with foundation models, covering RAG, prompt patterns, best practices, and examples to produce grounded, auditable answers from internal documents. - [Obtaining Sentiment Analysis](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Working-With-Different-Task-Types/Obtaining-Sentiment-Analysis/page.md): Guide to performing sentiment analysis using Amazon Bedrock, designing prompts, and operational workflows to classify feedback as positive negative or neutral for analytics and automation - [Understanding Code Generation](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Working-With-Different-Task-Types/Understanding-Code-Generation/page.md): Explains using foundation models and Amazon Bedrock to generate code, design prompts, integrate into workflows, and address risks, testing, and governance to accelerate development ### Integrating Amazon Bedrock With Other AWS Services - [Integrating Bedrock With Amazon S3 Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Integrating-Amazon-Bedrock-With-Other-AWS-Services/Integrating-Bedrock-With-Amazon-S3-Part-1/page.md): Using Amazon Bedrock with S3 to automate and scale generative AI processing of files, including code examples, workflow patterns, and production considerations. - [Integrating Bedrock With Amazon S3 Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Integrating-Amazon-Bedrock-With-Other-AWS-Services/Integrating-Bedrock-With-Amazon-S3-Part-2/page.md): Guide showing a compact Python example that reads text from S3, uses Amazon Bedrock to generate concise summaries, and writes results back to S3 for automation - [Integrating Bedrock With AWS Lambda](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Integrating-Amazon-Bedrock-With-Other-AWS-Services/Integrating-Bedrock-With-AWS-Lambda/page.md): Event-driven integration of AWS Lambda with Amazon Bedrock to automatically process S3 uploads using generative AI, producing summaries or other outputs and storing results securely - [Exposing Your Bedrock App Using API Gateway Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Integrating-Amazon-Bedrock-With-Other-AWS-Services/Exposing-Your-Bedrock-App-Using-API-Gateway-Part-1/page.md): Shows how to build a serverless event driven pipeline using S3, Lambda, and Amazon Bedrock to automatically process incoming data with generative AI and store results - [Exposing Your Bedrock App Using API Gateway Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Integrating-Amazon-Bedrock-With-Other-AWS-Services/Exposing-Your-Bedrock-App-Using-API-Gateway-Part-2/page.md): Guide for routing API Gateway requests to AWS Lambda that call Amazon Bedrock foundation models, covering integration patterns, routing behavior, security, and practical tips for secure serverless generative APIs - [Combining Bedrock With Amazon Lex](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Integrating-Amazon-Bedrock-With-Other-AWS-Services/Combining-Bedrock-With-Amazon-Lex/page.md): Describes integrating Amazon Lex with Bedrock via Lambda to combine structured dialog management with generative responses for conversational applications. ### Build a Marketing Email Generation Application - [Application Development Requirements Marketing Email Generator](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Build-a-Marketing-Email-Generation-Application/Application-Development-Requirements-Marketing-Email-Generator/page.md): Serverless application design for generating marketing emails using Amazon Bedrock, with secure Lambda invocation, predictable JSON output, and frontend integration via API Gateway and S3 ### Introduction to Retrieval Augmentation With Bedrock Knowledge Bases - [Extending a Model With Knowledge](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Introduction-to-Retrieval-Augmentation-With-Bedrock-Knowledge-Bases/Extending-a-Model-With-Knowledge/page.md): Explains retrieval augmented generation to augment foundation models with private documents at inference time, using embeddings, vector stores, chunking, and semantic search to reduce hallucinations. - [Embeddings and Vector Stores Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Introduction-to-Retrieval-Augmentation-With-Bedrock-Knowledge-Bases/Embeddings-and-Vector-Stores-Part-1/page.md): Covers embeddings and vector stores for semantic search in RAG systems, including how embeddings work, storage and hosting options, ingestion patterns, and chunking best practices. - [Embeddings and Vector Stores Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Introduction-to-Retrieval-Augmentation-With-Bedrock-Knowledge-Bases/Embeddings-and-Vector-Stores-Part-2/page.md): Explains chunking, embeddings, vector stores and RAG workflows to enable semantic retrieval and integrate retrieved text with foundation models for accurate, scalable search - [RAG End to End Workflow](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Introduction-to-Retrieval-Augmentation-With-Bedrock-Knowledge-Bases/RAG-End-to-End-Workflow/page.md): Explains end to end Retrieval Augmented Generation workflow from document ingestion and vectorization to query retrieval, prompt augmentation, and grounded LLM answer generation. - [Bedrock Knowledge Bases Introduction Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Introduction-to-Retrieval-Augmentation-With-Bedrock-Knowledge-Bases/Bedrock-Knowledge-Bases-Introduction-Part-1/page.md): Explains Amazon Bedrock Knowledge Bases and how they simplify building managed retrieval augmented generation pipelines by handling ingestion, embeddings, vector storage, retrieval, and prompt augmentation. - [Bedrock Knowledge Bases Introduction Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Introduction-to-Retrieval-Augmentation-With-Bedrock-Knowledge-Bases/Bedrock-Knowledge-Bases-Introduction-Part-2/page.md): Tutorial on building and configuring Amazon Bedrock knowledge bases, covering naming, IAM roles, data sources, parsing strategies, embedding models, vector stores, and cost versus quality tradeoffs. - [Bedrock Knowledge Bases Introduction Part 3](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Introduction-to-Retrieval-Augmentation-With-Bedrock-Knowledge-Bases/Bedrock-Knowledge-Bases-Introduction-Part-3/page.md): Explains chunking strategies, modes, and best practices for Amazon Bedrock Knowledge Bases to improve retrieval in RAG systems and manage embeddings, overlap, and cost. ### Best Practices and Optimization - [Managing Costs and Optimizing Performance Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Best-Practices-and-Optimization/Managing-Costs-and-Optimizing-Performance-Part-1/page.md): Strategies to reduce costs and latency for GenAI on Amazon Bedrock using model selection, prompt trimming, caching, retrieval, hosting choices, and monitoring - [Managing Costs and Optimizing Performance Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Best-Practices-and-Optimization/Managing-Costs-and-Optimizing-Performance-Part-2/page.md): Guide to reducing Amazon Bedrock costs and improving performance by choosing hosting models, using caching, and routing tasks to appropriate models. - [Managing Costs and Optimizing Performance Part 3](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Best-Practices-and-Optimization/Managing-Costs-and-Optimizing-Performance-Part-3/page.md): Guidance on reducing cost and latency by choosing appropriate model sizes, constraining outputs, optimizing prompts and RAG chunking for efficient inference and knowledge base costs. - [Managing Costs and Optimizing Performance Part 4](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Best-Practices-and-Optimization/Managing-Costs-and-Optimizing-Performance-Part-4/page.md): Guidance on reducing costs and boosting performance for Amazon Bedrock knowledge bases through incremental syncs, limited retrieval, caching, batching, precomputed embeddings, and appropriate model choice - [Handling Errors Troubleshooting and Edge Cases Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Best-Practices-and-Optimization/Handling-Errors-Troubleshooting-and-Edge-Cases-Part-1/page.md): Guidance on error handling, retries, input and output validation, guardrails, and observability for building resilient Amazon Bedrock GenAI applications, with a Python retry example - [Handling Errors Troubleshooting and Edge Cases Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Best-Practices-and-Optimization/Handling-Errors-Troubleshooting-and-Edge-Cases-Part-2/page.md): Practical patterns for robust Amazon Bedrock runtime usage including retries with exponential backoff, validating model outputs, RAG fallbacks, managing token limits, and handling safety and guardrails. - [Handling Errors Troubleshooting and Edge Cases Part 3](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Best-Practices-and-Optimization/Handling-Errors-Troubleshooting-and-Edge-Cases-Part-3/page.md): Guidance for handling Bedrock safety blocks, reducing hallucinations, validating outputs, improving observability, and operationalizing model integrations for production ### Governance, Safety in Responsible AI - [Ethical AI Introduction Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Governance-Safety-in-Responsible-AI/Ethical-AI-Introduction-Part-1/page.md): Guidelines for designing, implementing, and monitoring ethical, safe generative AI systems with principles, controls, and governance to prevent harm, bias, misuse, and sensitive data exposure. - [Ethical AI Introduction Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Governance-Safety-in-Responsible-AI/Ethical-AI-Introduction-Part-2/page.md): Guide to designing and operating ethical, safe generative AI with principles, layered controls, monitoring, and continuous risk management - [Data Privacy and Protection Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Governance-Safety-in-Responsible-AI/Data-Privacy-and-Protection-Part-1/page.md): Guidance on protecting sensitive data in Amazon Bedrock GenAI applications using redaction, input/output filtering, scoped RAG retrievals, and least privilege controls. - [Data Privacy and Protection Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Governance-Safety-in-Responsible-AI/Data-Privacy-and-Protection-Part-2/page.md): Guidance on protecting Bedrock AI workflows by identifying sensitive data, filtering/masking inputs and RAG context, limiting model context, and safely logging and monitoring to prevent data leaks. - [Compliance Features Including Guardrails Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Governance-Safety-in-Responsible-AI/Compliance-Features-Including-Guardrails-Part-1/page.md): Explains Amazon Bedrock Guardrails for centralized content policy enforcement, input and output filtering, auditability, and best practices to scale safe generative AI across applications - [Compliance Features Including Guardrails Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Governance-Safety-in-Responsible-AI/Compliance-Features-Including-Guardrails-Part-2/page.md): Explains Amazon Bedrock guardrails for versioned input and output content filtering, centralized policy enforcement, prompt injection protection, and code examples for applying guardrails to model calls - [Compliance Features Including Guardrails Part 3](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Governance-Safety-in-Responsible-AI/Compliance-Features-Including-Guardrails-Part-3/page.md): Configuring Amazon Bedrock guardrails to enforce safety, PII masking, profanity filters, versioned policies, and deployment patterns for centralized compliance ### Security - [Controlling Access to Bedrock Using IAM Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Security/Controlling-Access-to-Bedrock-Using-IAM-Part-1/page.md): Using AWS IAM to enforce least privilege for Amazon Bedrock, restricting which foundation models, knowledge bases, and guardrails principals can access with example allow and explicit deny policies - [Controlling Access to Bedrock Using IAM Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Security/Controlling-Access-to-Bedrock-Using-IAM-Part-2/page.md): Guide to securely granting and scoping IAM roles and policies for applications and Bedrock service roles to access Amazon Bedrock and related AWS resources. - [Controlling Access to Bedrock Using IAM Part 3](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Security/Controlling-Access-to-Bedrock-Using-IAM-Part-3/page.md): Guidance for using IAM policies to enforce least privilege and fine grained allow and deny controls for Amazon Bedrock model invocation, knowledge base access, region restrictions, and guardrails - [Ensuring Encryption in Transit Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Security/Ensuring-Encryption-in-Transit-Part-1/page.md): Guides protecting sensitive data in transit and at rest for Amazon Bedrock, covering TLS, configurable encryption, KMS key choices, threat surface, and defense in depth - [Ensuring Encryption in Transit Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Security/Ensuring-Encryption-in-Transit-Part-2/page.md): Guidance on encrypting data in transit and at rest for Amazon Bedrock deployments, covering KMS, IAM, key management, storage and logging best practices - [Integrating Bedrock With VPC](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Security/Integrating-Bedrock-With-VPC/page.md): Guide to privately integrating Amazon Bedrock with an AWS VPC using VPC interface endpoints (PrivateLink), covering architecture, provisioning steps, security, IAM, IP planning, and costs. ### Monitoring and Logging - [Observability for Bedrock What You Need](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Monitoring-and-Logging/Observability-for-Bedrock-What-You-Need/page.md): Guidance on instrumenting and monitoring Amazon Bedrock to track token usage, performance, errors, and safety signals for reliable cost effective GenAI operation - [Using Amazon CloudWatch With Bedrock Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Monitoring-and-Logging/Using-Amazon-CloudWatch-With-Bedrock-Part-1/page.md): Using Amazon CloudWatch with Amazon Bedrock to gain observability by combining metrics and logs for diagnostics, dashboards, alarms, and controlled invocation logging - [Using Amazon CloudWatch With Bedrock Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Monitoring-and-Logging/Using-Amazon-CloudWatch-With-Bedrock-Part-2/page.md): Guide to configuring CloudWatch alarms and Bedrock model invocation logging, viewing invocation logs, and operational best practices for monitoring, alerting, and securing model usage. - [Using Amazon CloudWatch With Bedrock Part 3](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Monitoring-and-Logging/Using-Amazon-CloudWatch-With-Bedrock-Part-3/page.md): Guide to using Amazon CloudWatch Logs Insights with Bedrock, showing queries, event names, Lambda structured logging examples, and best practices for monitoring and troubleshooting model invocations. - [Using Amazon CloudWatch With Bedrock Part 4](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Monitoring-and-Logging/Using-Amazon-CloudWatch-With-Bedrock-Part-4/page.md): Guidance for logging Bedrock applications from EC2 using CloudWatch Logs via the SDK, covering sequence tokens, IAM roles, Boto3 example, and best practice comparisons. - [Using Amazon CloudWatch With Bedrock Part 5](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Monitoring-and-Logging/Using-Amazon-CloudWatch-With-Bedrock-Part-5/page.md): Guides enabling and analyzing Amazon Bedrock model invocation logs in CloudWatch, querying with Logs Insights, and correlating those logs with application logs such as AWS Lambda. - [Using Amazon CloudWatch With Bedrock Part 6](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Monitoring-and-Logging/Using-Amazon-CloudWatch-With-Bedrock-Part-6/page.md): Guide to integrating Amazon Bedrock with CloudWatch for Lambda logging, metrics, alarms, dashboards, and structured logging to monitor model invocations, performance, and cost. - [Understanding and Optimizing Cost Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Monitoring-and-Logging/Understanding-and-Optimizing-Cost-Part-1/page.md): Guide to identifying and reducing Amazon Bedrock GenAI costs by diagnosing cost drivers, using CloudWatch and Cost Explorer, and applying model selection, prompt tuning, caching, and RAG optimizations. - [Understanding and Optimizing Cost Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Monitoring-and-Logging/Understanding-and-Optimizing-Cost-Part-2/page.md): Practical techniques to monitor and reduce Amazon Bedrock costs using AWS Budgets, CloudWatch metrics and Logs Insights, with diagnostic scenarios and remediation guidance ### Taking action with Bedrock Agents - [Bedrock Agents Introduction Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Taking-action-with-Bedrock-Agents/Bedrock-Agents-Introduction-Part-1/page.md): Introduction to Amazon Bedrock Agents that combine foundation models, managed orchestration, and tools so applications can invoke agents to perform multi step external actions - [Bedrock Agents Introduction Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Taking-action-with-Bedrock-Agents/Bedrock-Agents-Introduction-Part-2/page.md): Explains differences between calling foundation models directly and using Bedrock Agents, covering orchestration, InvokeAgent usage, session scoping, action groups, and Lambda integrations. - [Bedrock Agents Introduction Part 3](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Taking-action-with-Bedrock-Agents/Bedrock-Agents-Introduction-Part-3/page.md): Explains Amazon Bedrock Agents that orchestrate foundation models to call APIs, use tools, and execute multi-step workflows so applications avoid custom orchestration code. - [Managed Abstraction With Bedrock Agents Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Taking-action-with-Bedrock-Agents/Managed-Abstraction-With-Bedrock-Agents-Part-1/page.md): Explains using Amazon Bedrock Agents with AWS Lambda to abstract and securely call external REST APIs, handling validation, auth, error handling, and response shaping. - [Managed Abstraction With Bedrock Agents Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Taking-action-with-Bedrock-Agents/Managed-Abstraction-With-Bedrock-Agents-Part-2/page.md): Guide explaining how to configure Amazon Bedrock agents, wire tools and Lambda invocations, and how the Bedrock runtime orchestrates model reasoning and API calls. - [Managed Abstraction With Bedrock Agents Part 3](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Taking-action-with-Bedrock-Agents/Managed-Abstraction-With-Bedrock-Agents-Part-3/page.md): Describes Amazon Bedrock Agents integrating foundation models with tools and knowledge bases to orchestrate multi-step workflows, use RAG, and reduce orchestration code for grounded intelligent assistants. - [Comparison With MCP](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Taking-action-with-Bedrock-Agents/Comparison-With-MCP/page.md): Comparison of Amazon Bedrock Agents and the Model Context Protocol, outlining trade offs, orchestration responsibilities, portability, and practical recommendations ### Advanced Topics (Optional) - [Fine Tuning Models Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Advanced-Topics-Optional/Fine-Tuning-Models-Part-1/page.md): Explains fine-tuning foundation models, when to use it, benefits over prompting, example workflow for customer support tone, alternatives, and deployment considerations. - [Fine Tuning Models Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Advanced-Topics-Optional/Fine-Tuning-Models-Part-2/page.md): Guide to creating and running fine-tuning jobs in Amazon Bedrock, covering model discovery, customization techniques, console workflow, dataset format, S3 storage, and IAM prerequisites. - [Fine Tuning Models Part 3](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Advanced-Topics-Optional/Fine-Tuning-Models-Part-3/page.md): Guide to fine-tuning models with Amazon Bedrock, covering JSONL training data, boto3 customization jobs, hyperparameters, hosting and inference options, expected outcomes and multimodal next steps. - [Multimodal Capabilities Text and Images Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Advanced-Topics-Optional/Multimodal-Capabilities-Text-and-Images-Part-1/page.md): Overview of multimodal foundation model usage, covering supported modalities, request and response formats, streaming, code examples, and integration best practices - [Multimodal Capabilities Text and Images Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Advanced-Topics-Optional/Multimodal-Capabilities-Text-and-Images-Part-2/page.md): Explains streaming multimodal responses and image generation workflows, including handling image bytes, Base64 decoding, and choosing appropriate API endpoints for low latency and image creation. - [Implementing Conversational AI Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Advanced-Topics-Optional/Implementing-Conversational-AI-Part-1/page.md): Guide to implementing multi-turn conversational AI with stateless foundation models, using structured message schemas, session state management, chat workflow, storage options, and example code. - [Implementing Conversational AI Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Advanced-Topics-Optional/Implementing-Conversational-AI-Part-2/page.md): Best practices for session storage, context window management, and scaling conversational AI using DynamoDB, summarization, and sliding window strategies - [Implementing Conversational AI Part 3](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Advanced-Topics-Optional/Implementing-Conversational-AI-Part-3/page.md): Shows using DynamoDB to persist chat session history and supply context to stateless Bedrock model calls, including trimming history and example Python code - [Release Management With Shadow Release](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Advanced-Topics-Optional/Release-Management-With-Shadow-Release/page.md): Explains using shadow releases to evaluate new generative AI models on real traffic safely by routing requests to primary and shadow models and analyzing offline metrics. - [Bedrock AgentCore Introduction Part 1](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Advanced-Topics-Optional/Bedrock-AgentCore-Introduction-Part-1/page.md): Introduces Amazon Bedrock AgentCore, a serverless platform for custom agent orchestration, MCP compatible adapters, and long running multi step workflows when managed agents fall short - [Bedrock AgentCore Introduction Part 2](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Advanced-Topics-Optional/Bedrock-AgentCore-Introduction-Part-2/page.md): Guide comparing Amazon Bedrock AgentCore and Bedrock Agents for building complex AIOps orchestration, workflow mapping, architecture, and decision criteria - [Bedrock AgentCore Introduction Part 3](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Advanced-Topics-Optional/Bedrock-AgentCore-Introduction-Part-3/page.md): Explains Amazon Bedrock AgentCore for orchestrating foundation models, integrating tools and memory, and authoring serverless multi-step workflows with routing, sequencing, and dynamic or predefined control. ### Final Project - [Requirements for Final Project](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Final-Project/Requirements-for-Final-Project/page.md): Guide to building a Flask-based internal support assistant using Amazon Bedrock, knowledge retrieval, safety filters, and source-attributed JSON responses deployed on a VM with IAM authentication. ### Wrap Up - [Wrap Up](https://notes.kodekloud.com/docs/Introduction-to-Amazon-Bedrock/Wrap-Up/Wrap-Up/page.md): Summary of building safe production-ready generative AI applications using Amazon Bedrock covering model selection, token management, prompt engineering, SDK integration, safety guardrails, RAG, and agents.