docker restart Does Not Re-apply Volumes — Debugging a Bind Mount Failure
docker restart does not recreate the container, so changes to volumes in docker-compose.yml only take effect after running docker-compose down && up.
All posts
Page 125 of 128
Multi-Agent RAG: Distributed Retrieval Architecture with Specialized Agent Collaboration
A single RAG Agent handling all queries hits knowledge boundaries and performance bottlenecks. Multi-Agent RAG dispatches retrieval tasks to multiple specialized Agents, each with its own knowledge base and retrieval strategy, coordinated by a central Orchestrator that merges results.
Claude Code Permission Modes Explained: Five Modes from Default to Auto
Claude Code has five permission modes: default (confirm each step), acceptEdits (auto-accept edits), plan (read-only planning), auto (background AI classifier review), and bypassPermissions (YOLO, skip everything). Switch with Shift+Tab or configure via settings.json. Auto mode is the sweet spot — no step-by-step confirmations, but with safety guardrails.
nginx 502: Debugging Cross-Compose Container DNS Resolution
Service names aren't resolvable across Compose projects — you need to add a network alias so nginx can find the container.
Installing and Verifying Superpowers for GitHub Copilot CLI: Implementation, Diagnostics, and Validation
A hands-on log of installing Superpowers (packaged by DwainTR) for Copilot CLI on a local machine — including the diagnostic process when skills didn't appear after installation, the fix, and practical tips.
Docker DNS Resolution: container_name vs network alias
Cross-project DNS resolution requires container_name or a network alias — and only aliases support horizontal scaling.
LongRAG: Rethinking RAG Chunking Strategy with Long-Context Models
Traditional RAG splits documents into small chunks for retrieval, but this causes information fragmentation. LongRAG leverages 100K+ token long-context models to retrieve larger document segments (entire sections or even whole documents), reducing fragmentation while maintaining retrieval efficiency.
Speculative RAG: Small Models Draft in Parallel, Large Model Verifies at Once
Speculative RAG uses small specialist models to generate multiple answer drafts from different document subsets in parallel, then a large model verifies and selects the best answer in one pass. The paper reports +12.97 points accuracy and -50.83% latency on PubHealth — but that is the best cell in the table; other benchmarks gain far less.
nginx Restarted Fine, but Cloudflare Keeps Returning 502 — Even Though the Origin Is Healthy
A brief error during nginx restart caused Cloudflare to mark the origin as unhealthy and stop forwarding requests, returning 502 on its own. The key clues: localhost hits to the origin return 200, and nginx access logs are completely empty. Just wait for Cloudflare to automatically re-check the origin — it recovers on its own.
Managing Multi-Service Reverse Proxy with nginx conf.d: A Daodao Case Study
A monolithic nginx.conf becomes unwieldy as services grow. Splitting it into per-service files under conf.d/ via include is the standard solution.
nginx First Request Always 502, All Subsequent Requests Fine
When nginx uses the `set $variable` pattern for dynamic upstreams, the DNS cache expires every 30 seconds — the first request after expiry hits a 502 because no IP is available. Upgrading to nginx 1.27.3 and switching to an upstream block with the resolve parameter fixes this: DNS updates happen asynchronously in the background.
Downloading Files from a VPS Using SSH Config Aliases
Once SSH config is set up, scp works directly with aliases — no need to type out the full IP every time
The Complete Ollama Guide: Run LLMs Locally with One Command
Ollama wraps llama.cpp in a Docker-style CLI + REST API, letting you run LLMs locally with a single command. This post covers core concepts, installation, API, hardware requirements, Modelfile customization, and what this tool is — and isn't — good for.
The Complete Guide to RAG System Patterns: A Ten-Generation Evolution from Naive to Multi-Agent with Practical Navigation
RAG has evolved far beyond simple 'search + generate' into a technology ecosystem spanning ten generations — and since 2025 into an Agentic/Reasoning era. This article is a systematic navigation guide: from Naive RAG to Multi-Agent/LongRAG across ten generations, the post-ten Agentic Era (Search-R1/RL search, MCP, GraphRAG 3.x, vision-native retrieval), retrieval strategies, chunking, embedding, reranking, evaluation frameworks, observability, and cost optimization. Each topic has a dedicated deep-dive article.
vLLM — From PagedAttention to a Production-Grade LLM Inference Engine
vLLM uses PagedAttention to eliminate KV cache memory waste, combining continuous batching and prefix caching to become the most widely adopted open-source LLM inference engine today.
Ghostty vs cmux: A Guide to Choosing Your Modern Terminal
Ghostty is a fast, native, general-purpose terminal emulator. cmux is a terminal built on top of Ghostty, specifically designed for AI coding agents. They're not competitors — they operate at different layers.
Complete Chatbot Development Guide: State Management, Memory Strategies, and Tech Stack Selection
Building a chatbot is more than just calling an API. Conversation state management, memory mechanisms, streaming, guardrails, observability, and tech stack selection — every layer affects the user experience.
Prompt Engineering in Practice: Iteration Methodology, Common Mistakes, and Few-shot Optimization
Good prompts aren't written in one go — they're iterated into existence. Start with the simplest prompt, test with real cases, classify error types, and make targeted fixes. This article covers the three-part System Prompt structure, reasoning framework selection, few-shot optimization, token budget management, and six common mistakes.
Cloudflare Free Plan Maintenance Page: Custom Error Pages Unavailable, Use a Worker Instead
Cloudflare Custom Error Pages require a paid plan. On the Free Plan, use a Worker with inline HTML to intercept 5xx responses instead.
Managing Personal and Work GitHub Accounts with Git Conditional Includes
Use includeIf + SSH Host aliases to let Git automatically switch accounts based on directory path — no more manual switching.