โ— Shell
clean mode source โ†—

wachoo - Overview

Typing SVG

Bridging the gap between Big Data Engineering and Artificial Intelligence

English | ไธญๆ–‡

Profile Views GitHub followers GitHub User's stars

๐Ÿง‘โ€๐Ÿ’ป About Me

class Wachoo:
    def __init__(self):
        self.role = "AI Engineer & Data Architect"
        self.location = "China ๐Ÿ‡จ๐Ÿ‡ณ"
        self.github_since = 2015
        self.motto = "I believe the best code tells a story ๐Ÿ“–"

    def core_competencies(self):
        return {
            "AI Applications": [
                "ML/NLP model fine-tuning, deployment & evaluation",
                "LangChain / LangGraph LLM framework",
                "RAG design & development",
                "Agent context engineering, lifecycle orchestration & toolchain",
                "Enterprise-grade AI solutions",
            ],
            "Data Engineering": [
                "Hadoop / Flink / Spark / OLAP / BI",
                "Data warehouse, feature engineering & knowledge graphs",
                "DCMM & ontology-driven data governance",
                "Corpus cleaning & multimodal data pipelines",
                "Data mining with Sklearn & PyTorch",
            ],
            "System Engineering": [
                "OOP / SOLID / DDD architecture design",
                "Python/FastAPI ยท Java/SpringBoot",
                "SQL / NoSQL / VectorDB ยท MQ",
                "Docker / K8S ยท Cloud-native (Alibaba Cloud)",
                "Distributed systems: BASE, observability & scalability",
            ],
        }

    def professional_skills(self):
        return {
            "Project Management": "Agile ยท scope analysis ยท risk-driven decisions ยท stakeholder coordination",
            "Quality & Compliance": "Security compliance ยท cost optimization ยท process efficiency",
            "Tools": "HuggingFace ยท GitHub ยท JetBrains ยท Claude/Codex ยท Vibe Coding/SDD ยท npm ยท conda",
            "Languages": "Chinese (native) ยท English (professional reading & writing)",
        }

    def philosophy(self):
        return "Clean architecture + robust data pipelines = AI that delivers real business value ๐Ÿš€"

๐Ÿ›  Tech Stack

๐Ÿ“Š GitHub Analytics

๐Ÿ“ˆ Contribution Overview

Metric Value
๐Ÿ“ฆ Public Repos 123
๐Ÿ—๏ธ Original Projects 12
๐Ÿ“ Commits (this year) 9
๐Ÿ”€ Pull Requests 7
๐Ÿ› Issues 1
โญ Stars Received 5
๐Ÿ‘ฅ Followers 4
๐Ÿ‘ค Following 15
๐Ÿ“… Member Since 2015

๐Ÿ’ป Top Languages (Overall)

Java           โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘  67.7%
Python         โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘  20.2%
TypeScript     โ–ˆยฝโ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘   4.9%
HTML           โ–ˆยฝโ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘   4.6%
JavaScript     โ–Œโ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘   2.0%
Dockerfile     โ–Œโ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘   1.7%
Jupyter NB     โ–Œโ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘   1.6%
Shell          โ–โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘   0.9%

Below is the distribution:

Python         โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘  39.5%
Java           โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘  27.8%
HTML           โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘  26.7%
Jupyter NB     โ–ˆโ–ˆโ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘   6.4%
JavaScript     โ–ˆโ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘   2.3%
TypeScript     โ–โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘โ–‘   1.2%

๐Ÿš€ Featured Projects

๐ŸŽ“ ZhiYuan โ€” AI ้ซ˜่€ƒๅฟ—ๆ„ฟๅŠฉๆ‰‹

AI-powered college admission recommendation system

Stack

FastAPI Next.js PostgreSQL Redis LLM Tool Calling

Highlights

ๅ…ญ็ปด็”ปๅƒๅˆ†ๆž ยท SSE ๆตๅผๅฏน่ฏ ยท ใ€Œๅ†ฒ็จณไฟใ€ๆ™บ่ƒฝๆŽจ่

Data Scale

๐Ÿ“Š 342 ๆ‰€้ซ˜ๆ ก ยท 126 ไธชไธ“ไธš ยท 379K+ ๅฝ•ๅ–ๆ•ฐๆฎ

GitHub

๐Ÿค– Hermes Agent

Self-improving AI agent with a built-in learning loop

Stack

Python OpenAI Anthropic Docker Multi-platform

Highlights

่‡ชไธปๅญฆไน ้—ญ็Žฏ ยท 40+ ๅทฅๅ…ท้›†ๆˆ ยท 20+ ๆถˆๆฏๅนณๅฐ็ฝ‘ๅ…ณ

Features

๐Ÿง  ่ทจไผš่ฏ่ฎฐๅฟ† ยท ๆŠ€่ƒฝ่‡ชๅˆ›ๅปบ/่‡ชไผ˜ๅŒ– ยท MCP ้›†ๆˆ ยท Cron ่ฐƒๅบฆ

GitHub

๐Ÿ“Š RAGAS Evaluation

RAG system evaluation toolkit

Stack

Python LLM APIs Evaluation Metrics

Focus

RAG ๆตๆฐด็บฟ่ดจ้‡่ฏ„ไผฐ ยท ่‡ชๅŠจๅŒ–ๆต‹่ฏ• ยท ๅคš็ปดๅบฆๆŒ‡ๆ ‡

GitHub

๐ŸŒŠ Pulsar Flink Connector

Elastic data processing bridging Apache Pulsar & Apache Flink

Stack

Java Apache Flink Apache Pulsar Maven

Highlights

Stream Source/Sink ยท Table API/SQL ยท Pulsar Catalog

Features

๐Ÿ“ก ่‡ชๅŠจๅˆ†ๅŒบๅ‘็Žฐ ยท ๅคš็งๅๅบๅˆ—ๅŒ–๏ผˆJSON/Avro๏ผ‰ยท ็ฒพ็กฎไธ€ๆฌก่ฏญไน‰

GitHub

๐ŸŒฑ Currently Exploring

Learning Learning Learning Learning

๐Ÿ“ซ Let's Connect

GitHub Email Feishu