# vishal0205/google-photo-review-analyser- architecture

> Architecture diagram of the GitHub repository vishal0205/google-photo-review-analyser-, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-18). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/vishal0205/google-photo-review-analyser-
- Repository: https://github.com/vishal0205/google-photo-review-analyser-

## Overview

This repository analyses Google Photos Play Store reviews through two complementary stages: notebook-based LLM classification and evaluation, followed by a Streamlit app for exploring labelled results. In the app, dashboard code loads the labelled CSV through analytics helpers and presents summaries, filters, trends, complaints and review details. Its chatbot retrieves relevant reviews and answers questions, using Gemini for descriptive responses and exact dataset statistics for numerical questions. The notebook and classification workflow are documented but not excerpted, so their internal calls are not mapped.

Main entry points: [`Review_Analyser_Starter.ipynb`](https://github.com/vishal0205/google-photo-review-analyser-/blob/main/Review_Analyser_Starter.ipynb) (Classification notebook), [`streamlit_app/dashboard.py`](https://github.com/vishal0205/google-photo-review-analyser-/blob/main/streamlit_app/dashboard.py) (Streamlit dashboard), [`labelled_reviews.csv`](https://github.com/vishal0205/google-photo-review-analyser-/blob/main/labelled_reviews.csv) (Labelled reviews), [`streamlit_app/chatbot.py`](https://github.com/vishal0205/google-photo-review-analyser-/blob/main/streamlit_app/chatbot.py) (Review chatbot)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_classification["Classification and evaluation"]
  node_notebook["Classification notebook"]
  node_manual_labels[("Manual labels")]
end

subgraph group_data["Review data"]
  node_raw_reviews[("Source reviews")]
  node_labelled_reviews[("Labelled reviews")]
end

subgraph group_app["Dashboard analytics"]
  node_dashboard["Streamlit dashboard<br/>[dashboard.py]"]
  node_analytics["Review analytics<br/>[analytics.py]"]
end

subgraph group_assistant["AI assistant"]
  node_chatbot["Review chatbot<br/>[chatbot.py]"]
end

node_reviewer(("Dashboard user"))
node_gemini{{"Gemini API"}}

node_raw_reviews -.->|"analyses"| node_notebook
node_notebook -.->|"classifies"| node_labelled_reviews
node_notebook -.->|"evaluates against"| node_manual_labels
node_labelled_reviews -->|"loads"| node_analytics
node_dashboard -->|"calls"| node_analytics
node_reviewer -.->|"explores"| node_dashboard
node_dashboard -.->|"uses"| node_chatbot
node_chatbot -.->|"generates answers"| node_gemini

click node_notebook "https://github.com/vishal0205/google-photo-review-analyser-/blob/main/Review_Analyser_Starter.ipynb"
click node_raw_reviews "https://github.com/vishal0205/google-photo-review-analyser-/blob/main/google_photos_reviews.csv"
click node_labelled_reviews "https://github.com/vishal0205/google-photo-review-analyser-/blob/main/labelled_reviews.csv"
click node_manual_labels "https://github.com/vishal0205/google-photo-review-analyser-/blob/main/manual_labels_50.csv"
click node_dashboard "https://github.com/vishal0205/google-photo-review-analyser-/blob/main/streamlit_app/dashboard.py"
click node_analytics "https://github.com/vishal0205/google-photo-review-analyser-/blob/main/streamlit_app/analytics.py"
click node_chatbot "https://github.com/vishal0205/google-photo-review-analyser-/blob/main/streamlit_app/chatbot.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_notebook,node_manual_labels,node_reviewer toneBlue
class node_raw_reviews,node_labelled_reviews toneAmber
class node_dashboard,node_analytics,node_gemini toneMint
class node_chatbot toneRose
```

## Components

### Classification and evaluation

- [Classification notebook](https://github.com/vishal0205/google-photo-review-analyser-/blob/main/Review_Analyser_Starter.ipynb): `Review_Analyser_Starter.ipynb`
- [Manual labels](https://github.com/vishal0205/google-photo-review-analyser-/blob/main/manual_labels_50.csv): `manual_labels_50.csv`

### Review data

- [Source reviews](https://github.com/vishal0205/google-photo-review-analyser-/blob/main/google_photos_reviews.csv): `google_photos_reviews.csv`
- [Labelled reviews](https://github.com/vishal0205/google-photo-review-analyser-/blob/main/labelled_reviews.csv): `labelled_reviews.csv`

### Dashboard analytics

- [Streamlit dashboard](https://github.com/vishal0205/google-photo-review-analyser-/blob/main/streamlit_app/dashboard.py): `streamlit_app/dashboard.py`
- [Review analytics](https://github.com/vishal0205/google-photo-review-analyser-/blob/main/streamlit_app/analytics.py): `streamlit_app/analytics.py`

### AI assistant

- [Review chatbot](https://github.com/vishal0205/google-photo-review-analyser-/blob/main/streamlit_app/chatbot.py): `streamlit_app/chatbot.py`

### Other components

- **Dashboard user**
- **Gemini API**

## Connections

- Source reviews → Classification notebook: analyses (evidence: `README.md`)
- Classification notebook → Labelled reviews: classifies (evidence: `README.md`)
- Classification notebook → Manual labels: evaluates against (evidence: `README.md`)
- Labelled reviews → Review analytics: loads (evidence: `streamlit_app/analytics.py`)
- Streamlit dashboard → Review analytics: calls (evidence: `streamlit_app/dashboard.py`)
- Dashboard user → Streamlit dashboard: explores (evidence: `README.md`)
- Streamlit dashboard → Review chatbot: uses (evidence: `README.md`)
- Review chatbot → Gemini API: generates answers (evidence: `README.md`)
