Yingjie's Blog

Circuit breakers traditionally protect against downstream failures.

MinHash+LSH is the textbook answer for document deduplication.

instrumentWorkflowWithSentry automatically reports every step retry to Sentry, flooding dashboards with false alarms.

This article provides a comprehensive introduction to the MCP (Model Context Protocol), covering its core principles, Agent-MCP interaction mechanisms, and a comparative analysis of stdio and SSE transport protocols.

This article systematically explores the three-generation architecture evolution from bare LLM to Workflow to Agent, deeply analyzing the core working principles of Agents, their relationship with RAG, whether model fine-tuning is needed, and demonstrates…

When developing applications integrated with Large Language Models (LLMs), streaming responses are a key technology for enhancing user experience.

In React application development, the top-down rendering pattern of component trees (parent components render before children) is a fundamental paradigm.

This article introduces how to implement a simple RAG system using LangChain, covering key steps including document loading, splitting, vectorization, storage, retrieval, and prompt assembly.

This article delves deep into the essence of RAG (Retrieval Augmented Generation), covering everything from basic concepts to practical implementations, including implementations using different frameworks like LangChain, LlamaIndex, and detailed examples…

When building a blog with VitePress, a common requirement is to automatically generate sidebar navigation based on articles.

Data synchronization is a common requirement in iOS app development.

This is my 2024 annual summary as a backend/algorithm/iOS developer.

Investigation into combining Java thread pools with semaphores, analyzing issues in controlling task submission rates.

MapReduce is a distributed computing model for processing large datasets.