# dev-harsh01/capstone_project architecture

> Architecture diagram of the GitHub repository dev-harsh01/capstone_project, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-03). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/dev-harsh01/capstone_project
- Repository: https://github.com/dev-harsh01/capstone_project

## Overview

This metadata-first recommender turns a natural-language dataset request into structured requirements, fetches Kaggle metadata, retrieves likely candidates, then scores and explains the top five. Users can run that workflow through either the CLI or Streamlit; both expose the ranked results. The core stages are supported by excerpts and README descriptions. The graph omits a persistent store because discovery uses metadata only; Kaggle is the external metadata source.

Main entry points: [`rag_dataset_recommender/cli.py`](https://github.com/dev-harsh01/capstone_project/blob/main/rag_dataset_recommender/cli.py) (CLI), [`rag_dataset_recommender/streamlit_app.py`](https://github.com/dev-harsh01/capstone_project/blob/main/rag_dataset_recommender/streamlit_app.py) (Streamlit explorer), [`rag_dataset_recommender/kaggle_client.py`](https://github.com/dev-harsh01/capstone_project/blob/main/rag_dataset_recommender/kaggle_client.py) (Metadata client), [`rag_dataset_recommender/requirements_parser.py`](https://github.com/dev-harsh01/capstone_project/blob/main/rag_dataset_recommender/requirements_parser.py) (Requirement parser)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_entry["User interfaces"]
  node_cli["CLI<br/>[cli.py]"]
  node_streamlit["Streamlit explorer<br/>[streamlit_app.py]"]
end

subgraph group_workflow["Recommendation workflow"]
  node_parser["Requirement parser"]
  node_kaggle_client["Metadata client<br/>[kaggle_client.py]"]
  node_retriever["Hybrid retrieval<br/>[retrieval.py]"]
  node_ranker["Ranking and explanations<br/>[recommender.py]"]
  node_scorer["Suitability scoring<br/>[scoring.py]"]
end

subgraph group_contracts["Domain models"]
  node_models["Dataset and request models<br/>[models.py]"]
end

subgraph group_external["External services"]
  node_kaggle{{"Kaggle API"}}
end

node_user(("Dataset requester"))

node_user -->|"submits request"| node_cli
node_user -->|"enters request"| node_streamlit
node_cli -->|"parses request"| node_parser
node_streamlit -->|"parses request"| node_parser
node_cli -->|"fetches metadata"| node_kaggle_client
node_streamlit -->|"fetches metadata"| node_kaggle_client
node_kaggle_client -->|"lists datasets"| node_kaggle
node_cli -->|"retrieves candidates"| node_retriever
node_streamlit -->|"retrieves candidates"| node_retriever
node_cli -->|"ranks candidates"| node_ranker
node_streamlit -->|"ranks candidates"| node_ranker
node_ranker -->|"scores datasets"| node_scorer
node_kaggle_client -->|"creates records"| node_models
node_parser -->|"creates requirements"| node_models

click node_cli "https://github.com/dev-harsh01/capstone_project/blob/main/rag_dataset_recommender/cli.py"
click node_streamlit "https://github.com/dev-harsh01/capstone_project/blob/main/rag_dataset_recommender/streamlit_app.py"
click node_parser "https://github.com/dev-harsh01/capstone_project/blob/main/rag_dataset_recommender/requirements_parser.py"
click node_kaggle_client "https://github.com/dev-harsh01/capstone_project/blob/main/rag_dataset_recommender/kaggle_client.py"
click node_retriever "https://github.com/dev-harsh01/capstone_project/blob/main/rag_dataset_recommender/retrieval.py"
click node_ranker "https://github.com/dev-harsh01/capstone_project/blob/main/rag_dataset_recommender/recommender.py"
click node_scorer "https://github.com/dev-harsh01/capstone_project/blob/main/rag_dataset_recommender/scoring.py"
click node_models "https://github.com/dev-harsh01/capstone_project/blob/main/rag_dataset_recommender/models.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_cli,node_streamlit toneBlue
class node_parser,node_kaggle_client,node_retriever,node_ranker,node_scorer toneAmber
class node_models,node_user toneMint
class node_kaggle toneRose
```

## Components

### User interfaces

- [CLI](https://github.com/dev-harsh01/capstone_project/blob/main/rag_dataset_recommender/cli.py): `rag_dataset_recommender/cli.py`
- [Streamlit explorer](https://github.com/dev-harsh01/capstone_project/blob/main/rag_dataset_recommender/streamlit_app.py): `rag_dataset_recommender/streamlit_app.py`

### Recommendation workflow

- [Requirement parser](https://github.com/dev-harsh01/capstone_project/blob/main/rag_dataset_recommender/requirements_parser.py): `rag_dataset_recommender/requirements_parser.py`
- [Metadata client](https://github.com/dev-harsh01/capstone_project/blob/main/rag_dataset_recommender/kaggle_client.py): `rag_dataset_recommender/kaggle_client.py`
- [Hybrid retrieval](https://github.com/dev-harsh01/capstone_project/blob/main/rag_dataset_recommender/retrieval.py): `rag_dataset_recommender/retrieval.py`
- [Ranking and explanations](https://github.com/dev-harsh01/capstone_project/blob/main/rag_dataset_recommender/recommender.py): `rag_dataset_recommender/recommender.py`
- [Suitability scoring](https://github.com/dev-harsh01/capstone_project/blob/main/rag_dataset_recommender/scoring.py): `rag_dataset_recommender/scoring.py`

### Domain models

- [Dataset and request models](https://github.com/dev-harsh01/capstone_project/blob/main/rag_dataset_recommender/models.py): `rag_dataset_recommender/models.py`

### External services

- **Kaggle API**

### Other components

- **Dataset requester**

## Connections

- Dataset requester → CLI: submits request (evidence: `README.md`)
- Dataset requester → Streamlit explorer: enters request (evidence: `rag_dataset_recommender/streamlit_app.py`)
- CLI → Requirement parser: parses request (evidence: `rag_dataset_recommender/cli.py`)
- Streamlit explorer → Requirement parser: parses request (evidence: `rag_dataset_recommender/streamlit_app.py`)
- CLI → Metadata client: fetches metadata (evidence: `rag_dataset_recommender/cli.py`)
- Streamlit explorer → Metadata client: fetches metadata (evidence: `rag_dataset_recommender/streamlit_app.py`)
- Metadata client → Kaggle API: lists datasets (evidence: `rag_dataset_recommender/kaggle_client.py`)
- CLI → Hybrid retrieval: retrieves candidates (evidence: `rag_dataset_recommender/cli.py`)
- Streamlit explorer → Hybrid retrieval: retrieves candidates (evidence: `rag_dataset_recommender/streamlit_app.py`)
- CLI → Ranking and explanations: ranks candidates (evidence: `rag_dataset_recommender/cli.py`)
- Streamlit explorer → Ranking and explanations: ranks candidates (evidence: `rag_dataset_recommender/streamlit_app.py`)
- Ranking and explanations → Suitability scoring: scores datasets (evidence: `rag_dataset_recommender/recommender.py`)
- Metadata client → Dataset and request models: creates records (evidence: `rag_dataset_recommender/kaggle_client.py`)
- Requirement parser → Dataset and request models: creates requirements (evidence: `rag_dataset_recommender/requirements_parser.py`)
