BestHub
Sign in
Fun with Large Models
Author

Fun with Large Models

Master's graduate from Beijing Institute of Technology, published four top‑journal papers, previously worked as a developer at ByteDance and Alibaba. Currently researching large models at a major state‑owned enterprise. Committed to sharing concise, practical AI large‑model development experience, believing that AI large models will become as essential as PCs in the future. Let's start experimenting now!

113
Articles
0
Likes
0
Views
0
Comments
Recent Articles

Latest from Fun with Large Models

100 recent articles max
Fun with Large Models
Fun with Large Models
May 25, 2025 · Artificial Intelligence

A Complete Breakdown of Claude 4’s Core Features – How Close Are We to Programmer Unemployment?

Claude 4, released in May 2025 with Opus and Sonnet variants, combines hybrid inference, a 200 K context window, advanced code interpreter, RAG retrieval and MCP integration, delivering industry‑leading programming and AI‑agent performance at relatively low cost, as confirmed by multiple company and user evaluations.

AI agentsAnthropicClaude 4
0 likes · 10 min read
A Complete Breakdown of Claude 4’s Core Features – How Close Are We to Programmer Unemployment?
Fun with Large Models
Fun with Large Models
May 23, 2025 · Backend Development

Rapidly Build a Streamable HTTP MCP Server with the Official MCP SDK – Full End‑to‑End Guide

This article walks through the complete process of creating, testing, and publishing a streamable HTTP MCP server using the official MCP SDK, covering environment setup with Anaconda and uv, project structuring, code implementation, tool integration, Inspector testing, PyPI deployment, and client verification with CherryStudio.

ASGICherryStudioMCP
0 likes · 16 min read
Rapidly Build a Streamable HTTP MCP Server with the Official MCP SDK – Full End‑to‑End Guide
Fun with Large Models
Fun with Large Models
May 19, 2025 · Backend Development

Build a Streamable HTTP MCP Server from Scratch: Theory, Protocol Deep‑Dive and Full Python Implementation

This article explains the limitations of the original Stdio and HTTP SSE communication modes for MCP, introduces the Streamable HTTP protocol that resolves those issues, and provides a step‑by‑step Python implementation of both a Streamable HTTP MCP server and a matching client, complete with environment setup, FastAPI code, JSON‑RPC handling, and tool‑calling examples.

FastAPIJSON-RPCMCP protocol
0 likes · 28 min read
Build a Streamable HTTP MCP Server from Scratch: Theory, Protocol Deep‑Dive and Full Python Implementation
Fun with Large Models
Fun with Large Models
May 14, 2025 · Artificial Intelligence

Discover the mcp-server-chart MCP Server—Your One‑Click AI Chart Generator

This article introduces the AntV‑developed mcp-server-chart MCP Server, explains how to set up the VSCode + Cline + Node environment, configure the server via JSON, and demonstrates its ability to generate network and bar charts through large‑model function calls, while also discussing current limitations and future improvements.

AIAntVChart Generation
0 likes · 7 min read
Discover the mcp-server-chart MCP Server—Your One‑Click AI Chart Generator
Fun with Large Models
Fun with Large Models
Apr 25, 2025 · Artificial Intelligence

Why Your RAG System Underperforms and How to Boost Its Effectiveness by 20%

This article analyzes common shortcomings of RAG pipelines—data preparation, retrieval, and LLM generation—and provides concrete optimization techniques such as advanced chunking, embedding model selection, retrieval parameter tuning, rerank models, and prompt engineering, promising up to a 20% performance gain.

ChunkingEmbeddingRAG
0 likes · 17 min read
Why Your RAG System Underperforms and How to Boost Its Effectiveness by 20%
Fun with Large Models
Fun with Large Models
Apr 18, 2025 · Artificial Intelligence

How RAG Works: From Data Prep to LLM Generation Explained

This article breaks down Retrieval‑Augmented Generation (RAG) into its three core stages—data preparation, data retrieval, and LLM generation—showing how document chunking, embedding, vector databases, similarity search, and optional re‑ranking combine to let large language models produce more accurate, knowledge‑grounded answers.

EmbeddingLLMRAG
0 likes · 9 min read
How RAG Works: From Data Prep to LLM Generation Explained
Fun with Large Models
Fun with Large Models
Apr 12, 2025 · Artificial Intelligence

Build a No‑Code Travel‑Planning AI Assistant with VS Code, Cline, and Gaode MCP Server

This guide walks through setting up VS Code, installing the Cline plugin, configuring a Gaode Map MCP Server API key, and using the DeepSeek model to generate a personalized park‑recommendation agent and a visual HTML page, while also explaining the stdio‑based communication between Cline and the MCP Server.

AI AgentClineDeepSeek
0 likes · 15 min read
Build a No‑Code Travel‑Planning AI Assistant with VS Code, Cline, and Gaode MCP Server