Author of the rpcx microservice framework, original book author, and chair of Baidu's Go CMC committee.
This guide walks you through installing the LangChain library, adding model‑specific packages, verifying the setup with a Python script, configuring API keys via environment variables or a .env file, and preparing to use OpenAI‑compatible models such as DeepSeek or Qwen.
This repository offers a comprehensive, step‑by‑step LangChain tutorial series that walks developers through installation, the LangChain Expression Language, streaming, parallel execution, callbacks, serialization, model customization, prompt templates, memory, multimodal support, and advanced tools like LangGraph and LangSmith, enabling the creation of sophisticated AI applications.
Go 1.25 introduces Trace Flight Recorder, a lightweight circular‑buffer tracing tool that lets developers capture recent execution data in production with minimal overhead, and the article walks through its concepts, configuration, code demos, analysis workflow, and practical use cases.
The article analyzes the long‑standing issues of Go's original encoding/json package, explains the design and API of the experimental encoding/json/v2 and jsontext packages, and shows how the new implementation improves correctness, flexibility, and performance while preserving compatibility.
Go 1.25 introduces a container‑aware default for GOMAXPROCS that aligns the runtime’s parallelism with Kubernetes CPU limits, eliminating unnecessary throttling, improving tail‑latency, and making Go applications more production‑ready out of the box.
This article walks through constructing a stateful ReAct‑style LLM agent using LangGraph, detailing the core components—State, Nodes, Edges—defining a weather‑lookup tool with Open‑Meteo, configuring the graph’s nodes and conditional edges, and executing the workflow with streaming to observe each step in real time.
Go 1.25 introduces an experimental greenteagc garbage collector, container‑aware GOMAXPROCS, enhanced go vet analyzers, new go.mod ignore directive, work package mode, expanded standard library (including testing/synctest and experimental JSON v2), platform updates, and security hardening, all aimed at higher performance, developer productivity, and cloud‑native readiness.
This article explains why Go tests that rely on goroutine scheduling are flaky, demonstrates the problem with concrete code examples, and shows how the experimental synctest feature provides deterministic execution by controlling synthetic time, coordinating goroutine lifecycles, and offering a reliable Wait primitive.
Learn how to eliminate repetitive error checks in Go HTTP servers by returning errors from handlers, defining a custom HTTPError type, wrapping handlers with an error‑handling middleware, and using concise helper functions, resulting in cleaner, more maintainable code.
The article analyzes the challenges of manually deploying Model Context Protocol (MCP) servers for AI agents, compares them with Docker‑based deployment, and demonstrates step‑by‑step configurations, code snippets, and concrete benefits such as environment consistency, resource efficiency, and security.
