> ## Documentation Index
> Fetch the complete documentation index at: https://dingguoliang.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# AI Engineering Portfolio: Agent, RAG & LLM Systems

> A personal knowledge base covering AI agent architecture, RAG pipelines, LLM infrastructure, and multimodal AI — built from real engineering experience.

Welcome to my AI Engineering Portfolio — a living knowledge base documenting practical patterns, architectures, and hard-won lessons from building production AI systems. This site covers the full stack of modern LLM application engineering: from agent design with LangGraph to RAG pipelines, inference infrastructure, and multimodal AI.

<CardGroup cols={2}>
  <Card title="About Me" icon="user" href="/about">
    My background, engineering philosophy, and the journey from AI Application Engineer to AI Agent / Runtime Engineer.
  </Card>

  <Card title="AI Agents" icon="robot" href="/agents/overview">
    Agent architecture, LangGraph workflows, multi-agent orchestration, and tool-use patterns.
  </Card>

  <Card title="RAG Engineering" icon="magnifying-glass" href="/rag/overview">
    End-to-end retrieval-augmented generation: embeddings, vector search, reranking, and advanced patterns.
  </Card>

  <Card title="LLM Infrastructure" icon="server" href="/llm-infra/overview">
    Deploying and serving LLMs at scale: inference optimization, SaaS architecture, and multi-tenant design.
  </Card>

  <Card title="Multimodal AI" icon="microphone" href="/multimodal/overview">
    ASR, TTS, vision-language models, and building systems that combine multiple modalities.
  </Card>

  <Card title="Projects" icon="folder-open" href="/projects/overview">
    Real projects showcasing end-to-end AI system design and implementation.
  </Card>
</CardGroup>

## What You'll Find Here

This portfolio is organized as a technical reference for AI engineers, backend engineers, and developers building with LLMs. Each section combines conceptual explanations with working code examples drawn from real systems.

<CardGroup cols={3}>
  <Card title="Architecture Patterns" icon="diagram-project" href="/introduction">
    Reusable designs for agents, RAG, and LLM services — with diagrams and trade-off analysis.
  </Card>

  <Card title="Code Examples" icon="code" href="/projects/overview">
    Practical Python and TypeScript snippets you can copy-paste into your own projects.
  </Card>

  <Card title="Engineering Notes" icon="pen-to-square" href="/notes/lessons-learned">
    Honest write-ups of what worked, what didn't, and what I'd do differently.
  </Card>
</CardGroup>

<Note>
  This site is continuously updated as I build new systems and deepen my understanding of AI engineering. Check the **Engineering Notes** section for the latest lessons learned.
</Note>

## Quick Navigation

<CardGroup cols={2}>
  <Card title="LangGraph Workflows" icon="share-nodes" href="/agents/langgraph">
    Design and implement stateful agent workflows using LangGraph's graph-based primitives.
  </Card>

  <Card title="Embeddings & Vector Search" icon="database" href="/rag/embeddings">
    Choose embedding models, configure vector stores, and optimize retrieval quality.
  </Card>

  <Card title="LLM Deployment" icon="cloud" href="/llm-infra/deployment">
    Serve open-source and proprietary LLMs efficiently with vLLM, Ollama, and cloud APIs.
  </Card>

  <Card title="ASR & TTS Systems" icon="waveform-lines" href="/multimodal/asr-tts">
    Integrate speech recognition and synthesis into AI applications and voice agents.
  </Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.