Applied LLMs: From Theory to Production

A structured learning path and project portfolio for software engineers to master Large Language Models. This repository moves beyond theory, focusing on the practical application of LLMs through prompt engineering, API integration, and building scalable applications using frameworks like LangChain and LlamaIndex.

🚀 What's Inside?

• Structured Curriculum: A guide covering everything from NLP basics to advanced RAG and Agent systems.
• Project-Based Learning: Hands-on projects including chatbots, automation tools, and AI-assisted applications.
• Code & Examples: Practical implementations using OpenAI, Anthropic, and open-source models (LLaMA, Mistral).
• Engineering Focus: Lessons on vector databases, evaluation, deployment, and mitigating common LLM limitations.

🪜 Repository Structure:

applied-llms/
│
├── README.md
├── roadmap.md
│
├── 01-theory-foundations/
│   ├── README.md
│   ├── 01-what-are-llms.md
│   ├── 02-nlp-basics.md
│   ├── 03-llm-architectures.md
│   ├── 04-key-terminologies.md
│   ├── 05-paper-summaries/
│   │   ├── attention-is-all-you-need.md
│   │   └── other-key-papers.md
│   └── 06-visual-explanations.md
│
├── 02-prompt-engineering/
│   ├── README.md
│   ├── 09-prompting-basics.md
│   ├── 10-prompting-frameworks.md
│   ├── 11-prompt-tools/
│   │   ├── prompthero-examples.md
│   │   ├── flowgpt-examples.md
│   │   └── promptperfect-examples.md
│   ├── 12-prompt-library.md
│   └── exercises/
│       ├── basic-prompts.md
│       ├── zero-shot-prompting.md
│       └── few-shot-prompting.md
│
├── 03-practical-applications/
│   ├── README.md
│   ├── 13-use-cases/
│   │   ├── summarization.md
│   │   ├── brainstorming.md
│   │   ├── translation.md
│   │   └── coding-assistance.md
│   ├── 14-prompt-refinement.md
│   ├── 15-model-limitations.md
│   ├── 16-response-analysis.md
│   ├── 17-llm-apis/
│   │   ├── openai-api.md
│   │   ├── anthropic-api.md
│   │   └── cohere-api.md
│   └── 18-simple-apps/
│       ├── chatbot/
│       ├── assistant/
│       └── other-demos/
│
├── 04-advanced-topics/
│   ├── README.md
│   ├── 19-rag/
│   │   ├── introduction.md
│   │   └── implementation-guide.md
│   ├── 20-vector-databases/
│   │   ├── pinecone.md
│   │   ├── chroma.md
│   │   └── weaviate.md
│   ├── 21-open-source-llms/
│   │   ├── mistral.md
│   │   ├── llama.md
│   │   └── ollama.md
│   ├── 22-output-evaluation.md
│   ├── 23-agents/
│   │   ├── autogpt.md
│   │   ├── langgraph.md
│   │   └── crewai.md
│   ├── 24-ethics-safety.md
│   ├── 25-monetization.md
│   ├── 26-multimodal-models/
│   │   ├── gpt-4-vision.md
│   │   ├── gemini.md
│   │   └── claude.md
│   └── 27-sharing-work.md
│
├── 05-build-projects/
│   ├── README.md
│   ├── project-ideas.md
│   ├── langchain-projects/
│   ├── gradio-projects/
│   ├── streamlit-projects/
│   ├── rag-implementation/
│   └── agent-implementation/
│
├── 06-reflection-next-steps/
│   ├── README.md
│   ├── next-move.md
│   ├── learning-journal.md
│   └── skill-assessment.md
│
├── resources/
│   ├── cheatsheets.md
│   ├── recommended-reading.md
│   ├── video-resources.md
│   └── tools-list.md
│
└── quizzes/
    ├── flashcards/
    ├── weekly-quizzes/
    └── final-assessment.md

🔑 Key Features of This Repository Structure:

1. Progressive Learning Path: Organized from fundamentals to advanced topics
2. Theory + Practice Combination: Each concept includes both explanatory documentation and practical exercises
3. Project-Based Learning: Dedicated section for building actual applications
4. Comprehensive Coverage: Includes all 28 points of the curriculum
5. Assessment Tools: Quizzes and flashcards to test understanding
6. Resource Collection: Curated list of additional learning materials