How mdehghani86/appliedgenai works
Main Components
• Notebooks as Modules: Consider each Jupyter Notebook as a separate learning module or lab. Group them logically when possible. For example:
• ChatGPT_API_Tutorial.ipynb and CrewAI.ipynb could represent API integration and custom AI module examples.
• GenAI_BeerGame_V1_0.ipynb and Lab_7_HealthLLM.ipynb may illustrate domain-specific applications.
• The various LangChain_Lab*.ipynb files (including LangGraph_Tutorial_1.ipynb) focus on chaining language model operations.
• Underlying AI Infrastructure: Even though this is a lab collection, the notebooks interact with external AI models/APIs (e.g., OpenAI’s services). Represent the generative AI backends (ChatGPT/LLMs, LangChain framework) as core components.
• Execution Environment: Notebooks typically run in environments like Google Colab or Jupyter Notebook. Represent this as the “Interactive Notebook Environment.”
• External Dependencies: Include external APIs, libraries, or frameworks such as OpenAI’s API, any LangChain or LangGraph packages, and possibly other Python libraries for data handling.
Relationships and Interactions
• Each Notebook module serves as an entry point where users trigger experiments or demonstrations.
• From these modules, there is a clear data flow:
• The Notebook environment sends requests to the generative AI APIs.
• The AI backend processes the request and returns results.
• The notebooks then process these results for demonstration (e.g., displaying text, visualizations).
Architectural Patterns and Design Principles
• Modularity: Each notebook is self-contained and demonstrates focused concepts, which aligns with modular design.
• Layered Architecture: Although minimal, the flow can be seen as layered:
1. Presentation/Interaction layer (the notebook UI).
2. Application logic layer (coding examples and API calls within the notebooks).
3. External service layer (ChatGPT API, LangChain framework functions).
• Integration Points: Emphasize the clear use of external libraries and services (APIs), which is a key integration point in generative AI projects.
Relevant Technologies and Frameworks
• Jupyter Notebook / Google Colab as the interface.
• Python libraries and frameworks for generative AI.
• OpenAI’s API (for ChatGPT and related generative models).
• LangChain and potential LangGraph libraries to structure and chain AI tasks.
• “Flow of Data/Commands” – showing how a user’s action in one of the notebooks triggers a chain of events (API calls, model computations, result rendering).
• Notes indicating that these notebooks are primarily for educational/demonstrative purposes rather than production deployment.