close

DEV Community

James Lee profile picture

James Lee

🚀 Senior LLM Engineer | RAG · AI Agents · LLMOps | Python · AWS · K8s

Location hangzhou, China Joined Joined on  Email address lijames193@gmail.com Personal website https://github.com/muzinan123 github website

Work

Senior LLM Engineer — RAG · AI Agents · LLMOps

Part 6 — RAG Recall Quality from 60% to 93%: Building a Continuous Evaluation Loop (Not Gut Feeling)
jamesli profile

Part 6 — RAG Recall Quality from 60% to 93%: Building a Continuous Evaluation Loop (Not Gut Feeling)

#llm #performance #rag #softwareengineering
Image Image Image 7
Comments 2
10 min read

Want to connect with James Lee?

Create an account to connect with James Lee. You can also sign in below to proceed if you already have an account.

Create Account
Already have an account? Sign in
Part 5 — Installing a Black Box Recorder in Your RAG System: 4-Layer Metadata + 3-Level Verification, Root Cause in 5 Minutes
jamesli profile

Part 5 — Installing a Black Box Recorder in Your RAG System: 4-Layer Metadata + 3-Level Verification, Root Cause in 5 Minutes

#ai #architecture #monitoring #rag
Image Image Image 6
Comments
9 min read
Part 4 — High Semantic Similarity Correct Business Conclusion: A Three-Layer Judgment Engine from Retrieval to Quantifiable Decisions
jamesli profile

Part 4 — High Semantic Similarity Correct Business Conclusion: A Three-Layer Judgment Engine from Retrieval to Quantifiable Decisions

#ai #architecture #llm #rag
Image Image Image 6
Comments
10 min read
Part 3 — Vector Retrieval in Domain-Specific Terminology Scenarios: From Model Selection to Dual Validation
jamesli profile

Part 3 — Vector Retrieval in Domain-Specific Terminology Scenarios: From Model Selection to Dual Validation

#ai #architecture #nlp #rag
Image Image Image 6
Comments
10 min read
Part 2 — Why Does One System Need Three Chunking Strategies? And One Document Type Shouldn't Be Chunked At All
jamesli profile

Part 2 — Why Does One System Need Three Chunking Strategies? And One Document Type Shouldn't Be Chunked At All

#ai #architecture #llm #rag
Image Image Image 6
Comments
9 min read
Part 1 — How Do Unstructured Documents Become a Searchable Knowledge Base? Five Key Engineering Decisions in the Ingestion Pipeline
jamesli profile

Part 1 — How Do Unstructured Documents Become a Searchable Knowledge Base? Five Key Engineering Decisions in the Ingestion Pipeline

#ai #architecture #dataengineering #rag
Image Image Image 5
Comments
9 min read
I Shipped a Strict-Source RAG System to Production in 8 Weeks: A Full-Stack Engineering Retrospective
jamesli profile

I Shipped a Strict-Source RAG System to Production in 8 Weeks: A Full-Stack Engineering Retrospective

#showdev #ai #rag #softwareengineering
Image Image Image 5
Comments
4 min read
How We Replaced Gut Feeling with Data: A Production Evaluation Framework for LLM Systems (Text2SQL Case Study)
jamesli profile

How We Replaced Gut Feeling with Data: A Production Evaluation Framework for LLM Systems (Text2SQL Case Study)

#ai #llm #machinelearning #testing
Image Image Image 7
Comments 9
9 min read
Serverless Best Practices: Production Architecture, Stateless Design & Cost Optimization
jamesli profile

Serverless Best Practices: Production Architecture, Stateless Design & Cost Optimization

#architecture #aws #serverless #systemdesign
Comments
10 min read
Serverless Workflows: Orchestrating Multi-Step Pipelines with AWS Step Functions
jamesli profile

Serverless Workflows: Orchestrating Multi-Step Pipelines with AWS Step Functions

#aws #python #serverless #tutorial
Comments
5 min read
Event-Driven Automation: Building a Serverless Maintenance Bot with Lambda & EventBridge
jamesli profile

Event-Driven Automation: Building a Serverless Maintenance Bot with Lambda & EventBridge

#automation #aws #devops #serverless
Comments
8 min read
Traffic Routing in AWS Lambda: Canary Deployments, Weighted Aliases & Blue/Green
jamesli profile

Traffic Routing in AWS Lambda: Canary Deployments, Weighted Aliases & Blue/Green

#aws #cicd #devops #serverless
Comments
7 min read
Auto Scaling in AWS Lambda: Concurrency, Throttling & Scale-to-Zero
jamesli profile

Auto Scaling in AWS Lambda: Concurrency, Throttling & Scale-to-Zero

#architecture #aws #performance #serverless
Comments
7 min read
Lambda Triggers Explained: S3, EventBridge, API Gateway & SQS
jamesli profile

Lambda Triggers Explained: S3, EventBridge, API Gateway & SQS

#architecture #aws #serverless #tutorial
Comments
8 min read
Cold Start in AWS Lambda: Causes, Phases & How to Fix It
jamesli profile

Cold Start in AWS Lambda: Causes, Phases & How to Fix It

#architecture #aws #performance #serverless
Comments
7 min read
Kubernetes Data Access Flow: How Network Traffic Moves Inside and Outside the Cluster
jamesli profile

Kubernetes Data Access Flow: How Network Traffic Moves Inside and Outside the Cluster

#infrastructure #kubernetes #linux #networking
Comments
5 min read
Kubernetes Resource Orchestration: How kubelet Prepares Storage, Network & Compute for Every Pod
jamesli profile

Kubernetes Resource Orchestration: How kubelet Prepares Storage, Network & Compute for Every Pod

#architecture #devops #infrastructure #kubernetes
Comments
5 min read
Kubernetes Resource Scheduling: Filtering, Scoring & Priority Preemption
jamesli profile

Kubernetes Resource Scheduling: Filtering, Scoring & Priority Preemption

#architecture #devops #kubernetes #systemdesign
Comments
4 min read
Kubernetes Control Flow: How Resources Are Created, Deleted, Modified & Queried
jamesli profile

Kubernetes Control Flow: How Resources Are Created, Deleted, Modified & Queried

#architecture #devops #kubernetes #tutorial
Comments
4 min read
Kubernetes Logical Architecture: Control Plane vs Worker Nodes & Why the Control Plane Runs kubelet Too
jamesli profile

Kubernetes Logical Architecture: Control Plane vs Worker Nodes & Why the Control Plane Runs kubelet Too

#architecture #beginners #devops #kubernetes
Comments
3 min read
Kubernetes Architecture Overview: Control Plane, Worker Nodes & the Container Stack
jamesli profile

Kubernetes Architecture Overview: Control Plane, Worker Nodes & the Container Stack

#architecture #devops #infrastructure #kubernetes
Comments
3 min read
Go Garbage Collection: Tri-Color Mark & Sweep, Write Barriers & STW Optimization
jamesli profile

Go Garbage Collection: Tri-Color Mark & Sweep, Write Barriers & STW Optimization

#algorithms #computerscience #go #performance
Comments
5 min read
Go Compiler & defer: Bootstrap, Three defer Implementations, panic/recover & Closures
jamesli profile

Go Compiler & defer: Bootstrap, Three defer Implementations, panic/recover & Closures

#architecture #computerscience #go #programming
Image 1
Comments
6 min read
Goroutine Scheduling: GMP Model, Schedule Loop, Preemption & Stack Management
jamesli profile

Goroutine Scheduling: GMP Model, Schedule Loop, Preemption & Stack Management

#architecture #computerscience #go #performance
Comments
6 min read
Go System Calls & Blocking: syscall Wrapping, Async vs Sync & GMP Separation
jamesli profile

Go System Calls & Blocking: syscall Wrapping, Async vs Sync & GMP Separation

#architecture #computerscience #go #programming
Comments
5 min read
Go I/O Optimization: goroutine-per-connection, netpoller & the Reader/Writer Interface
jamesli profile

Go I/O Optimization: goroutine-per-connection, netpoller & the Reader/Writer Interface

#computerscience #go #networking #performance
Comments 1
5 min read
Go Heap Memory Allocation: tcmalloc, Mutator/Allocator & Multi-Level Cache
jamesli profile

Go Heap Memory Allocation: tcmalloc, Mutator/Allocator & Multi-Level Cache

#architecture #computerscience #go #performance
Comments
5 min read
Go Performance Optimization: pprof, Flame Graphs & Hotspot Profiling
jamesli profile

Go Performance Optimization: pprof, Flame Graphs & Hotspot Profiling

#go #performance #tooling #tutorial
Image 1
Comments
4 min read
Tekton + Argo CD: Building a Complete GitOps Pipeline End-to-End
jamesli profile

Tekton + Argo CD: Building a Complete GitOps Pipeline End-to-End

#cicd #devops #kubernetes #tutorial
Comments
4 min read
Argo CD Application Updates & Rollbacks: GitOps-Driven Version Control in Practice
jamesli profile

Argo CD Application Updates & Rollbacks: GitOps-Driven Version Control in Practice

#cicd #devops #git #kubernetes
Comments
5 min read
Argo CD Application Management: Deploy to Multiple Clusters with a Unified View
jamesli profile

Argo CD Application Management: Deploy to Multiple Clusters with a Unified View

#automation #devops #kubernetes #tutorial
Comments
6 min read
Argo CD Installation & Configuration: From Zero to Running in 10 Minutes
jamesli profile

Argo CD Installation & Configuration: From Zero to Running in 10 Minutes

#beginners #devops #kubernetes #tutorial
Comments
5 min read
Argo CD Core Concepts & Architecture: The GitOps CD Engine for Kubernetes
jamesli profile

Argo CD Core Concepts & Architecture: The GitOps CD Engine for Kubernetes

#architecture #cicd #devops #kubernetes
Comments
4 min read
Tekton in Practice: Building a Java CI/CD Pipeline from Scratch
jamesli profile

Tekton in Practice: Building a Java CI/CD Pipeline from Scratch

#cicd #java #kubernetes #tutorial
Comments
6 min read
Tekton Concept Model: Steps, Tasks, Pipelines and How They Actually Run
jamesli profile

Tekton Concept Model: Steps, Tasks, Pipelines and How They Actually Run

#cicd #devops #kubernetes #tutorial
Comments
5 min read
Tekton Components & Resource Objects: A Complete Overview
jamesli profile

Tekton Components & Resource Objects: A Complete Overview

#cicd #devops #kubernetes #tutorial
Comments
4 min read
GitOps Continuous Delivery: Immutable Infrastructure, Pull Pipelines & Observability
jamesli profile

GitOps Continuous Delivery: Immutable Infrastructure, Pull Pipelines & Observability

#cicd #devops #git #infrastructure
Comments
4 min read
GitOps vs DevOps: What's the Difference and How Do They Relate?
jamesli profile

GitOps vs DevOps: What's the Difference and How Do They Relate?

#automation #cicd #devops #git
Comments
3 min read
What is GitOps? IaC, Git, and the Future of Cloud-Native CD
jamesli profile

What is GitOps? IaC, Git, and the Future of Cloud-Native CD

#cicd #devops #git #infrastructure
Comments
5 min read
Python Object Model: How CPython Represents Everything as an Object
jamesli profile

Python Object Model: How CPython Represents Everything as an Object

#computerscience #programming #python #tutorial
Comments
5 min read
Python list Internals: How Dynamic Arrays Work Under the Hood
jamesli profile

Python list Internals: How Dynamic Arrays Work Under the Hood

#algorithms #computerscience #performance #python
Comments
5 min read
Python dict Internals: Hash Tables, Collision Resolution, and Hash Attacks
jamesli profile

Python dict Internals: Hash Tables, Collision Resolution, and Hash Attacks

#algorithms #computerscience #python #security
Image 1
Comments 6
6 min read
Python GIL: Why One Lock Rules the Entire Interpreter
jamesli profile

Python GIL: Why One Lock Rules the Entire Interpreter

#architecture #computerscience #programming #python
Image 1
Comments
5 min read
Python Memory Optimization: How CPython's Memory Pool Works
jamesli profile

Python Memory Optimization: How CPython's Memory Pool Works

#architecture #computerscience #performance #python
Comments
6 min read
Building a Production-Grade LLM Application in 8 Weeks: Architecture Decisions, Pitfalls, and Best Practices
jamesli profile

Building a Production-Grade LLM Application in 8 Weeks: Architecture Decisions, Pitfalls, and Best Practices

#ai #architecture #llm #systemdesign
Image Image Image 8
Comments 2
13 min read
Production Optimization: Inference Cost and Performance Control
jamesli profile

Production Optimization: Inference Cost and Performance Control

#ai #architecture #llm #performance
Image Image Image 5
Comments
10 min read
Hybrid Knowledge Retrieval: Combining Neo4j Graph Queries, GraphRAG and Vector Search for Enterprise LLM Applications
jamesli profile

Hybrid Knowledge Retrieval: Combining Neo4j Graph Queries, GraphRAG and Vector Search for Enterprise LLM Applications

#neo4j #graphrag #rag #llm
Image Image Image 5
Comments
12 min read
Building Safety Guardrails for LLM Applications That Actually Work in Production
jamesli profile

Building Safety Guardrails for LLM Applications That Actually Work in Production

#ai #llm
Image Image Image 5
Comments
9 min read
From Single-Agent to Multi-Agent: Designing and Deploying an Enterprise-Grade LLM Application with LangGraph
jamesli profile

From Single-Agent to Multi-Agent: Designing and Deploying an Enterprise-Grade LLM Application with LangGraph

#multiagent #langgraph #llm #ai
Image Image Image 5
Comments
11 min read
Engineering GraphRAG for Production: API Design, Query Optimization, and Service Reliability
jamesli profile

Engineering GraphRAG for Production: API Design, Query Optimization, and Service Reliability

#graphrag #rag #python #llm
Image Image Image 5
Comments
6 min read
Production-Grade GraphRAG Data Pipeline: End-to-End Construction from PDF Parsing to Knowledge Graph
jamesli profile

Production-Grade GraphRAG Data Pipeline: End-to-End Construction from PDF Parsing to Knowledge Graph

#rag #graphrag #pdf #llm
Image Image Image 5
Comments 1
9 min read
From 0 to MVP in 2 Weeks: Building a Production-Grade LLM Application from Scratch
jamesli profile

From 0 to MVP in 2 Weeks: Building a Production-Grade LLM Application from Scratch

#ai #llm #architecture #mvp
Image Image Image 7
Comments
9 min read
MCP Framework: The "Swiss Army Knife" for AI System Integration — A GraphRAG Case Study
jamesli profile

MCP Framework: The "Swiss Army Knife" for AI System Integration — A GraphRAG Case Study

#mcp #llm #rag
Image Image Image 6
Comments
5 min read
OpenManus Architecture Deep Dive: Enterprise AI Agent Development with Real-World Case Studies
jamesli profile

OpenManus Architecture Deep Dive: Enterprise AI Agent Development with Real-World Case Studies

#llm #ai #manus
Image Image Image 13
Comments
8 min read
CrewAI for Marketing Research: Building a Multi-Agent Collaboration System
jamesli profile

CrewAI for Marketing Research: Building a Multi-Agent Collaboration System

#llm #agents #crewai
Image Image Image 11
Comments 4
5 min read
Breaking Limitations: Advanced Customization Guide for Dify Platform
jamesli profile

Breaking Limitations: Advanced Customization Guide for Dify Platform

#llm #ai #llmops
Image Image Image 8
Comments
8 min read
Multi-Agent Hybrid Knowledge Base Retrieval: Building a High-Precision Legal Case Analysis Platform
jamesli profile

Multi-Agent Hybrid Knowledge Base Retrieval: Building a High-Precision Legal Case Analysis Platform

#llm #agents #langgraph #ai
Image Image Image 7
Comments 1
7 min read
Building LLM-Powered Real Estate Intelligent Agents: Technical Implementation and Business Value
jamesli profile

Building LLM-Powered Real Estate Intelligent Agents: Technical Implementation and Business Value

#ai #llm #langchain #agents
Image Image Image 16
Comments 6
8 min read
n8n and AI Agents: Breaking Boundaries in Enterprise-Grade Consulting
jamesli profile

n8n and AI Agents: Breaking Boundaries in Enterprise-Grade Consulting

#ai #n8n #llm #agents
Image Image Image 12
Comments 3
6 min read
Building a Medical Literature Assistant: RAG System Practice Based on LangChain
jamesli profile

Building a Medical Literature Assistant: RAG System Practice Based on LangChain

#llm #ai #langchain #rag
Image Image Image 15
Comments
14 min read
loading...