# leonardltk/ragcipe architecture

> Architecture diagram of the GitHub repository leonardltk/ragcipe, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-05-22). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/leonardltk/ragcipe
- Repository: https://github.com/leonardltk/ragcipe

## Overview

##### Project type and purpose
- It provides a Gradio interface (images/interface.png) for users to upload a recipe image, applies mmocr for text extraction, computes embeddings, and retrieves similar recipes from a local CSV dataset.

##### File structure
- Top level:
- Jupyter notebooks (1_Self_querying_retriever.ipynb, 2_Ensemble_search.ipynb, 3_OCR_Recipe-*.ipynb) – exploratory/experimentation
- run.py – main entry point
- recipe_class_*.py – core modules (data loading, OCR, embedding, retrieval)
- data/recipes.csv – backing dataset
- images/ocr_images – sample input images
- requirements.txt / requirements-lite.txt – dependencies
- README.md – quick start + mmocr setup
- No separate “frontend” folder, but the Gradio UI is instantiated within run.py or one of the recipe_class_*.py modules.
- There is an external dependency on mmocr for OCR (cloned under mmocr/).

##### README for additional insights
- Instructions to install dependencies, clone mmocr, run OCR demo, then run python run.py to launch the app.

##### Detailed but not over-engineered
- You call out “run.py” as the orchestration entry point.
- Don’t forget to annotate configuration steps (e.g., “Must clone mmocr repo, set env variables for inference”).

## Diagram (Mermaid)

```mermaid
flowchart TB
    subgraph "Frontend"
        UI(["Gradio UI<br>(run.py)"]):::ui
    end

    subgraph "Backend Modules"
        OCRPre["Text Preprocessor<br>(recipe_class_ocr.py)"]:::custom
        Embedding["Embedding Generator<br>(recipe_class_embedding.py)"]:::custom
        Retriever["Retrieval Engine<br>(recipe_class_retriever.py)"]:::custom
        DataLoader["Data Loader<br>(recipe_class_data.py)"]:::custom
    end

    extMMOCR(["OCR Engine<br>(mmocr)"]):::external
    Store(["Recipe Dataset<br>(data/recipes.csv)"]):::database

    subgraph "Analysis / Experiments"
        style Analysis fill:none,stroke:#999,stroke-dasharray:5,stroke-width:2
        NB1["1_Self_querying_retriever.ipynb"]:::analysis
        NB2["2_Ensemble_search.ipynb"]:::analysis
        NB3["3_OCR_Recipe-backup.ipynb"]:::analysis
        NB4["3_OCR_Recipe-gpt4.ipynb"]:::analysis
    end

    subgraph "Configuration / Docs"
        style Config fill:none,stroke:#999,stroke-dasharray:5,stroke-width:2
        README["README.md"]:::config
        IMAGES["Sample Images<br>(images/ocr_images)"]:::config
        REQ["requirements.txt<br>requirements-lite.txt"]:::config
    end

    UI --> OCRPre
    OCRPre --> extMMOCR
    OCRPre --> Embedding
    Embedding --> Retriever
    Retriever --> DataLoader
    DataLoader --> Store
    Retriever --> UI

    UI -.-> README
    UI -.-> REQ
    UI -.-> IMAGES
    Analysis -.-> UI

    click UI "https://github.com/leonardltk/ragcipe/blob/main/run.py"
    click OCRPre "https://github.com/leonardltk/ragcipe/blob/main/recipe_class_ocr.py"
    click Embedding "https://github.com/leonardltk/ragcipe/blob/main/recipe_class_embedding.py"
    click Retriever "https://github.com/leonardltk/ragcipe/blob/main/recipe_class_retriever.py"
    click DataLoader "https://github.com/leonardltk/ragcipe/blob/main/recipe_class_data.py"
    click Store "https://github.com/leonardltk/ragcipe/blob/main/data/recipes.csv"
    click NB1 "https://github.com/leonardltk/ragcipe/blob/main/1_Self_querying_retriever.ipynb"
    click NB2 "https://github.com/leonardltk/ragcipe/blob/main/2_Ensemble_search.ipynb"
    click NB3 "https://github.com/leonardltk/ragcipe/blob/main/3_OCR_Recipe-backup.ipynb"
    click NB4 "https://github.com/leonardltk/ragcipe/blob/main/3_OCR_Recipe-gpt4.ipynb"
    click README "https://github.com/leonardltk/ragcipe/blob/main/README.md"
    click IMAGES "https://github.com/leonardltk/ragcipe/tree/main/images/ocr_images"
    click REQ "https://github.com/leonardltk/ragcipe/blob/main/requirements.txt"

    classDef ui fill:#fdd,stroke:#333,stroke-width:1px,shape:round
    classDef custom fill:#ccf,stroke:#333,stroke-width:1px
    classDef external fill:#cfc,stroke:#333,stroke-width:1px
    classDef database fill:#ffeb99,stroke:#333,stroke-width:1px
    classDef analysis fill:#eee,stroke:#333,stroke-width:1px
    classDef config fill:#eee,stroke:#333,stroke-width:1px
```
