# cranium-ai/demo_public_repo architecture

> Architecture diagram of the GitHub repository cranium-ai/demo_public_repo, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-07-05). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/cranium-ai/demo_public_repo
- Repository: https://github.com/cranium-ai/demo_public_repo

## Overview

##### Project type and purpose
- This is a multi-scenario demonstration library for machine learning tasks, organized into three pillars:
- LLM-based demos (chatbots, RAG, Q&A)
- Non-LLM ML tasks (CV, speech, image-to-text)
- Traditional data-science pipelines (regression, classification, scientific modeling)
- It’s not a single end-user application, but a reference toolkit illustrating various pipelines and integrations with external APIs (OpenAI, AWS Bedrock, Hugging Face, etc.).

##### File structure
- Top-level directories:
- data_science/ – classic ML pipelines
- llm/ – subfolders for each LLM provider or pattern
- non_llm/ – CV, ASR, random non-LLM model demos
- Each subfolder groups one scenario.
- requirements.txt lists shared Python dependencies.
- No central “orchestrator” code is provided, so assume usage via direct script invocation or an ad-hoc CLI.

##### README for additional insights
- README enumerates scenarios but does not specify a single integration layer.

a. Main components
- “Demo Runner” (could be a CLI or notebook launcher)
- Three module clusters:
1. Data Science Modules
2. LLM Modules
3. Non-LLM Modules
- Shared Utilities / Common Libraries
- External Services & APIs
- Data Sources (if any local CSV or scientific data)

b. Relationships & interactions
- Demo Runner → invokes individual scenario scripts in each module cluster
- Scenario scripts → import shared utilities
- LLM modules → call out to external LLM APIs (OpenAI, AWS Bedrock, Meta LLaMA endpoints, etc.)
- Non-LLM CV/ASR modules → load local model code or call hugging-face models
- Data Science modules → run scikit-learn or custom algorithms on local data

c. Architectural patterns & design principles
- Modular plugin-style structure: each scenario is isolated in its own package
- Separation of concerns: grouping by domain
- Dependency inversion for external services: scenario code depends on abstract interfaces in “shared” utilities, with concrete clients for each provider

d. Key technologies & frameworks
- Python 3.x, requirements.txt
- scikit-learn, statsmodels (data_science)
- langchain, pinecone, openai SDK, boto3 (llm/rag/aws_bedrock)
- pytorch/tensorflow, torchvision, blip-utils (non_llm/image_classification, image_to_text)
- torchaudio or Whisper wrapper (speech_recognition)

## Diagram (Mermaid)

```mermaid
flowchart TD
    %% Demo Runner
    DemoRunner["Demo Runner / CLI"]:::cli

    %% Data Science Cluster
    subgraph "Data Science Modules"
        direction TB
        DS1["Classification Scenario"]:::ds
        DS2["Regression Scenario"]:::ds
        DS3["Scientific Modeling Scenario"]:::ds
    end

    %% LLM Cluster
    subgraph "LLM Modules"
        direction TB
        LLM1["Anthropic PDF Summarization"]:::llm
        LLM2["AWS Bedrock Chatbot"]:::llm
        LLM3["Meta LLaMA Q&A Bot"]:::llm
        LLM4["MistralAI LLM App"]:::llm
        LLM5["OpenAI App"]:::llm
        LLM6["Retrieval-Augmented Generation (RAG)"]:::llm
        LLM7["Random LLM Models Demo"]:::llm
    end

    %% Non-LLM Cluster
    subgraph "Non-LLM Modules"
        direction TB
        subgraph "Image Classification"
            direction TB
            NLLM1["Model Definition"]:::nllm
            NLLM2["Inference Script"]:::nllm
            NLLM3["Processing Utilities"]:::nllm
        end
        NLLM4["Image-to-Text (BLIP Demo)"]:::nllm
        NLLM5["Object Detection Demo"]:::nllm
        NLLM6["Random Non-LLM Models Demo"]:::nllm
        NLLM7["Speech Recognition (ASR)"]:::nllm
    end

    %% Shared Utilities
    SharedUtils["Shared Utilities / Common Libraries"]:::shared

    %% External Services
    subgraph "External Services & APIs"
        direction TB
        Ext1["OpenAI Chat API"]:::external
        Ext2["AWS Bedrock Endpoint"]:::external
        Ext3["Anthropic API"]:::external
        Ext4["Meta LLaMA Endpoint"]:::external
        Ext5["MistralAI Endpoint"]:::external
        Ext6["Hugging Face Endpoints"]:::external
    end

    %% Data Sources
    DataStore["Local Data Store (CSV, Scientific Data)"]:::data

    %% Connections
    DemoRunner -->|runs| DS1
    DemoRunner -->|runs| DS2
    DemoRunner -->|runs| DS3

    DemoRunner -->|runs| LLM1
    DemoRunner -->|runs| LLM2
    DemoRunner -->|runs| LLM3
    DemoRunner -->|runs| LLM4
    DemoRunner -->|runs| LLM5
    DemoRunner -->|runs| LLM6
    DemoRunner -->|runs| LLM7

    DemoRunner -->|runs| NLLM1
    DemoRunner -->|runs| NLLM2
    DemoRunner -->|runs| NLLM3
    DemoRunner -->|runs| NLLM4
    DemoRunner -->|runs| NLLM5
    DemoRunner -->|runs| NLLM6
    DemoRunner -->|runs| NLLM7

    %% Shared utils usage
    DS1 -->|imports| SharedUtils
    DS2 -->|imports| SharedUtils
    DS3 -->|imports| SharedUtils

    LLM1 -->|uses| SharedUtils
    LLM2 -->|uses| SharedUtils
    LLM3 -->|uses| SharedUtils
    LLM4 -->|uses| SharedUtils
    LLM5 -->|uses| SharedUtils
    LLM6 -->|uses| SharedUtils
    LLM7 -->|uses| SharedUtils

    NLLM1 -->|uses| SharedUtils
    NLLM2 -->|uses| SharedUtils
    NLLM3 -->|uses| SharedUtils
    NLLM4 -->|uses| SharedUtils
    NLLM5 -->|uses| SharedUtils
    NLLM6 -->|uses| SharedUtils
    NLLM7 -->|uses| SharedUtils

    %% External calls
    LLM1 -->|calls| Ext3
    LLM2 -->|calls| Ext2
    LLM3 -->|calls| Ext4
    LLM4 -->|calls| Ext5
    LLM5 -->|calls| Ext1
    LLM6 -->|calls| Ext1
    LLM6 -->|calls| Ext6
    LLM7 -->|calls| Ext6

    NLLM1 -->|loads local model| DataStore
    NLLM2 -->|loads local model| DataStore
    NLLM3 -->|loads local model| DataStore
    NLLM5 -->|calls| Ext6
    NLLM6 -->|calls| Ext6

    DS1 -->|reads| DataStore
    DS2 -->|reads| DataStore
    DS3 -->|reads| DataStore

    %% Click Events
    click DS1 "https://github.com/cranium-ai/demo_public_repo/blob/main/data_science/classification/grade_classification.py"
    click DS2 "https://github.com/cranium-ai/demo_public_repo/blob/main/data_science/regression/predict.py"
    click DS3 "https://github.com/cranium-ai/demo_public_repo/blob/main/data_science/modeling/lotka_volterra.py"
    click LLM1 "https://github.com/cranium-ai/demo_public_repo/blob/main/llm/anthropic/pdf_summarization.py"
    click LLM2 "https://github.com/cranium-ai/demo_public_repo/blob/main/llm/aws_bedrock/aws_bedrock_chatbot.py"
    click LLM3 "https://github.com/cranium-ai/demo_public_repo/blob/main/llm/meta_llama/qa_bot.py"
    click LLM4 "https://github.com/cranium-ai/demo_public_repo/blob/main/llm/mistralai/llm_app.py"
    click LLM5 "https://github.com/cranium-ai/demo_public_repo/blob/main/llm/openai/app.py"
    click LLM6 "https://github.com/cranium-ai/demo_public_repo/blob/main/llm/rag/llm_rag.py"
    click LLM7 "https://github.com/cranium-ai/demo_public_repo/blob/main/llm/random_models/models.py"
    click NLLM1 "https://github.com/cranium-ai/demo_public_repo/blob/main/non_llm/image_classification/model.py"
    click NLLM2 "https://github.com/cranium-ai/demo_public_repo/blob/main/non_llm/image_classification/inference_image.py"
    click NLLM3 "https://github.com/cranium-ai/demo_public_repo/blob/main/non_llm/image_classification/processes.py"
    click NLLM4 "https://github.com/cranium-ai/demo_public_repo/blob/main/non_llm/image_to_text/blip.ipynb"
    click NLLM5 "https://github.com/cranium-ai/demo_public_repo/blob/main/non_llm/object_detection/detect_objects.py"
    click NLLM6 "https://github.com/cranium-ai/demo_public_repo/blob/main/non_llm/random_models/models.py"
    click NLLM7 "https://github.com/cranium-ai/demo_public_repo/blob/main/non_llm/speech_recognition/asr.py"

    %% Styles
    classDef ds fill:#D0E8FF,stroke:#009,stroke-width:1px
    classDef llm fill:#D0FFD8,stroke:#090,stroke-width:1px
    classDef nllm fill:#FFE9C5,stroke:#E67E00,stroke-width:1px
    classDef shared fill:#F0F0F0,stroke:#666,stroke-width:1px
    classDef external fill:#F2D7FF,stroke:#800080,stroke-width:1px
    classDef data fill:#FFF2CC,stroke:#CC9900,stroke-width:1px
    classDef cli fill:#E8E8E8,stroke:#444,stroke-width:1px,stroke-dasharray: 5 5
```
