A ubiquitous public account for pirate enthusiasts, regularly sharing curated experiences, tech learning, and growth insights. Currently publishing articles on AI RAG customer service, AI MCP technology, and open-source design. Personal free Knowledge Planet: Awakening New World Programmer.
This article walks through creating a TypeScript‑based train‑ticket MCP Server that leverages the Qwen‑3 14B model and Model Context Protocol, detailing setup, configuration, the provided query and time tools, example interactions, and links to the open‑source repositories.
This article explains the Model Context Protocol (MCP), why it simplifies AI tool integration, and provides a step‑by‑step guide to create a Spring AI 1.0.0‑M7 Maven project, configure the MCP server with HTTP SSE, implement weather and Maoyan movie services, run the server, and test it with the MCP Inspector and Cherry Studio client.
The article explains how large language models extend their capabilities by using tool calls—detailing the need for external APIs, the three‑stage workflow, request/response formats, autonomous routing, parameter generation, error handling, and the relationship between Function Calling and Tool Use.
The article walks through creating a Retrieval‑Augmented Generation (RAG) based AI chatbot for Tongcheng Travel by preparing FAQ data, formatting it with L1/L2/Q/A tags, importing it into FastGPT knowledge bases, configuring a workflow with intent classification and prompt engineering, and validating the system with multiple test cases.
This tutorial walks through setting up a Node.js environment, creating a TypeScript project, writing a custom OpenAI client, and integrating either Zhipu AI or an Ollama‑deployed model to perform automated code reviews via GitLab CI, complete with build, run, and VS Code debugging steps.
This tutorial walks through privately deploying the DeepSeek R1 14B model on an AutoDL GPU server using Ollama, configuring systemd and ports, exposing the service, and integrating it with a GitLab CI pipeline to generate AI‑driven code review results sent via a Feishu bot.
This tutorial walks through upgrading Git on a GitLab server, using the Commit API to fetch recent changes, invoking an AI model for automated code review, posting the review as a commit comment, and notifying the team via a Feishu custom‑bot webhook.
This tutorial shows how to modify a GitLab CI pipeline to fetch changed files via the Merge Request API, extract the diff with jq, build a JSON request for the glm‑4‑flash model, and use AI to review code changes, including prompt engineering and result interpretation.
The article explains DeepSeek’s three core modes—V3, R1, and web‑search—details prompt‑engineering techniques for each mode, and demonstrates practical workplace applications such as data visualization, PPT generation, and new‑media copy creation, showing how tailored prompts can boost efficiency.
This article walks through the entire process of setting up an AI-powered customer service chatbot with FastGPT, covering the installation of Docker containers, configuring model keys, creating a knowledge base from Q&A pairs, indexing with RAG, building a simple application, testing queries, and publishing the bot for use.
