本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

Interactive CV with AI chat integration. Built with React 19, TypeScript, Claude API. Chat with my AI avatar about my experience.

This is a landscape of the infrastructure that powers the generative AI ecosystem

LLM/MLOps/LLMOps

环游世界旅游，创业做 AI 产品，一种比较新的方式和理念生活创业，欢迎订阅 RSS https://nsddd.top/zh/index.xml

This Agentic system is designed to handle complex data analysis tasks by breaking them down into smaller subtasks and delegating them to specialized agents. The system uses a multi-agent architecture to improve performance and scalability.

Monitoring and evaluating LLM apps with Langfuse. Presented at PyConZA 2024.

Code and experiment outputs for our DECLARE MOC2025 paper on an LLM-based labeling workflow with XAI (SHAP) and human-in-the-loop QA. Built from a technical-debt detection case study using LLMs and scikit-learn, focusing on avoiding shortcut learning, leakage, and handling imbalance.

AI Engineer building production-grade ML systems | LLMs, RAG, ML Pipelines | Python, TensorFlow, LangChain | Open to opportunities

A web scraping platform including Twitter, Instagram, Facebook and Youtube providing reports on sentimental Analysis for TN Election 2026

A curated showcase of small, on-premise models with great utility, enabling privacy-centered deployment and easy adaptation to bio-inspired use cases.

AI agent that generates accurate code parsing various sections of arxiv paper. (Paper2Code)

End-to-end Amazon Product Review RAG + LLMOps pipeline for product recommendations, combining collaborative filtering, FAISS retrieval, Gemini responses, and production observability (Prometheus/ Grafana/Evidently) with an SFT Qwen model for evaluation, plus CI/CD, drift monitoring, and guardrails.

Autonomous self-healing code agent that plans, writes, executes, debugs and remembers code locally. No cloud. No API keys.

Production-grade AI news intelligence dashboard built on Azure — combines live news with PDF document analysis using Azure OpenAI GPT-4.1, Document Intelligence, Content Safety, and AI Evaluation

Improve AI-generated code quality by breaking tasks into small, reviewable chunks with planned, stacked branches for easier code review and fewer bugs.

🧠 Enhance your AI prompts with proven techniques like Chain-of-Thought and ReAct for superior reasoning and accuracy in your applications.

An mdBook on building / monitoring / extending an intelligence gathering PAAS based on an Tauri/Rust/Svelte IDE client with an AI/ML Ops infrastructure using cloud compute resources.

An Agentic YouTube crewAI Scraper & Mapper - A Python tool that uses crewAI to scrape YouTube channel data and visualizes it geographically with interactive in maps.

E-commerce recommender system that builds personalized and “similar items” recommendations from catalog + user behavior data, with feature engineering, model training/evaluation, and GCP-based serving/storage components.