SK

Author

Dr. Sarah Kim

ML Research Engineer

PhD in NLP, now building AI products. I explain the 'why' behind AI systems so you can make better engineering decisions, not just copy-paste code.

LLMs & ModelsRAG & SearchAI Agents

38 Articles by Dr. Sarah Kim

Hybrid Search RAG: Unifying Symbolic and Connectionist AI
RAG & Search

Hybrid Search RAG: Unifying Symbolic and Connectionist AI

Combine symbolic and connectionist AI with Hybrid Search RAG for more efficient and effective search capabilities, including vector search and knowledge graph querying

July 29, 202625 min
Monitoring AI API Performance with Prometheus and Grafana
DevOps & Deploy

Monitoring AI API Performance with Prometheus and Grafana

Monitor AI API performance using Prometheus and Grafana for efficient DevOps

July 27, 202625 min
Using Protocol Buffers for AI API Communication
AI Tooling

Using Protocol Buffers for AI API Communication

Learn how to use Protocol Buffers for efficient AI API communication and data serialization in production-grade AI engineering

July 26, 202625 min
API Documentation Best Practices with Swagger and OpenAPI
AI Tooling

API Documentation Best Practices with Swagger and OpenAPI

Learn API documentation best practices with Swagger and OpenAPI for AI tooling

July 25, 202625 min
Using GraphQL for AI APIs: Apollo Server Tutorial
AI Tooling

Using GraphQL for AI APIs: Apollo Server Tutorial

Learn to build production-grade AI APIs with GraphQL and Apollo Server, including schema design and query optimization

July 25, 202625 min
Advanced AI Agent Development with Meta-Learning
AI Agents

Advanced AI Agent Development with Meta-Learning

Discover how to develop advanced AI agents with meta-learning and few-shot learning, and improve their performance and adaptability

July 23, 202625 min
Developing AI Agents with Scikit-Learn: A Practical Guide
AI Agents

Developing AI Agents with Scikit-Learn: A Practical Guide

Use Scikit-Learn for AI agent development and learn how to create robust agents with this intermediate guide, covering key concepts and implementation details.

July 22, 202625 min
Machine Learning Simplified: Understanding the Basics
AI Tooling

Machine Learning Simplified: Understanding the Basics

Discover the fundamentals of machine learning and its applications in AI tooling, including key concepts and implementation techniques

July 19, 202625 min
Building MCP Server from Scratch for AI Tooling
AI Agents

Building MCP Server from Scratch for AI Tooling

Learn to implement an MCP server for AI tooling, enabling efficient communication between agents and tools.

July 17, 202625 min
LoRA Fine-Tuning for LLMs: Unlock Efficient Adaptation
LLMs & Models

LoRA Fine-Tuning for LLMs: Unlock Efficient Adaptation

Discover how LoRA fine-tuning enhances LLMs with efficient adaptation, improving performance without extensive retraining.

July 17, 202625 min
Model-Based Reinforcement Learning for AI Agents with RAG
RAG & Search

Model-Based Reinforcement Learning for AI Agents with RAG

Master model-based reinforcement learning for AI agents using RAG, enhancing decision-making and task execution.

July 17, 202625 min
Reasoning and Acting with ReAct Agent Pattern and LLMs
RAG & Search

Reasoning and Acting with ReAct Agent Pattern and LLMs

Learn ReAct Agent Pattern for LLMs and RAG, enabling reasoning and acting in AI systems, with a focus on production-grade implementation

July 17, 202625 min
LangGraph-Based Agentic RAG for Autonomous Agents
RAG & Search

LangGraph-Based Agentic RAG for Autonomous Agents

LangGraph-Based Agentic RAG enables autonomous agents to reason and act effectively, learn how to implement it

July 16, 202625 min
Serving LLM Predictions with RESTful API using Flask and Docker
LLMs & Models

Serving LLM Predictions with RESTful API using Flask and Docker

Serve Large Language Model predictions via RESTful API using Flask and Docker, streamlining model deployment and integration.

July 15, 202625 min
Streaming AI Data with Apache Flink and Cassandra
APIs & Backends

Streaming AI Data with Apache Flink and Cassandra

Learn how to stream AI-generated data with Apache Flink and Apache Cassandra for scalable and efficient data processing

July 15, 202625 min
LLMs & Models

Building Explainable AI with SHAP and LIME for Model Interpretability

Learn to build explainable AI systems with SHAP and LIME for model interpretability, improving transparency and trust in AI models.

July 15, 202625 min
AI Tooling

Serverless AI with AWS Lambda and TensorFlow

Learn to create a serverless AI function using AWS Lambda and TensorFlow, and deploy AI models efficiently

July 15, 202625 min
LLMs & Models

Automating LLM Testing with Pytest and Hypothesis

Automate LLM testing and validation with Pytest and Hypothesis for robust AI models

July 13, 202625 min
DevOps & Deploy

Building a Containerized AI Dev Environment with Docker and Jupyter

Create a robust AI development environment with Docker and Jupyter Notebook, streamlining your workflow and ensuring reproducibility

July 13, 202625 min
LLMs & Models

Monitoring AI Model Performance with Prometheus and Grafana

Monitor AI model performance using Prometheus and Grafana, key to scalable AI systems

July 12, 202625 min
LLMs & Models

Developing AI Content Generation with LLMs and SpaCy

Learn to develop AI-driven content generation systems using language models and spaCy, optimizing for production-grade environments.

July 12, 202625 min
LLMs & Models

Automating Hyperparameter Tuning for LLMs with Azure ML

Automate hyperparameter tuning for large language models using Azure Machine Learning, improving model performance and efficiency

July 12, 202625 min
LLMs & Models

Optimizing AI Model Serving with TensorFlow Serving and gRPC

Optimize AI model serving with TensorFlow Serving and gRPC for efficient deployment and management of machine learning models.

July 11, 202625 min
AI Tooling

Integrating AI Recommendation Systems with Redis and Python

Learn to build AI-powered recommendation systems with Redis and Python, improving user experience and engagement.

July 11, 202625 min
LLMs & Models

Visualize AI Model Performance with TensorBoard and Matplotlib

Learn to visualize AI model performance using TensorBoard and Matplotlib for better understanding and improvement of your models

July 11, 202620 min
DevOps & Deploy

Orchestrating AI Workflows with Apache Airflow and Kubernetes

Orchestrate AI workflows with Apache Airflow and Kubernetes for scalable and reliable deployments, including AI model training and natural language processing

July 11, 202625 min
LLMs & Models

Secure LLM APIs with OAuth 2.0 and AWS API Gateway

Secure Large Language Model APIs using OAuth 2.0 and AWS API Gateway, ensuring authenticated access to your AI models

July 11, 202625 min
AI Tooling

Natural Language Processing Pipeline with spaCy and scikit-learn

Develop a production-grade NLP pipeline using spaCy and scikit-learn for text classification and entity recognition

July 10, 202625 min
LLMs & Models

Deploying Large Language Models with AWS SageMaker and Docker

Learn to deploy large language models with AWS SageMaker and Docker for scalable AI solutions, improving model performance and reducing latency

July 10, 202625 min
AI Agents

Building Custom AI Agents with Python and Gym

Learn to create custom AI agents using Python and the Gym library, a key concept in AI engineering

July 10, 202625 min
AI Agents

Mastering Multi-Agent Orchestration with LangGraph

Learn multi-agent orchestration with LangGraph and tool calling for AI agent development, including key concepts and implementation details

July 10, 202625 min
APIs & Backends

Mastering JWT Authentication in Node.js

Learn JWT authentication in Node.js for secure APIs, including token generation and verification.

July 10, 202625 min
DevOps & Deploy

Mastering Git Branching Strategies for Teams in DevOps

Learn effective Git branching strategies for teams to streamline collaboration and improve code quality, a crucial aspect of DevOps and deployment.

July 9, 202625 min
DevOps & Deploy

Streaming AI Responses in Next.js with Vercel AI SDK

Stream AI responses in Next.js with Vercel AI SDK for scalable and efficient AI-powered applications

July 9, 202620 min
LLMs & Models

Fine-Tune Llama 3 with LoRA on Custom Data

Fine-tune Llama 3 with LoRA on custom datasets for improved performance, explore key concepts and implementations

July 9, 202625 min
APIs & Backends

PostgreSQL vs MySQL: Choosing the Right Database

Compare PostgreSQL and MySQL databases to determine which is best for your project, considering factors like scalability and performance.

July 9, 202625 min
AI Tooling

Introduction to Tailwind CSS for Beginners Tutorial

Learn Tailwind CSS basics for styling web applications with a utility-first approach and boost your web development skills

July 8, 202625 min
APIs & Backends

Building a REST API with Node.js and Express

Learn to build a REST API with Node.js and Express, covering fundamentals, implementation, and optimization

July 8, 202625 min