# susheel-op/veritas-neural architecture

> Architecture diagram of the GitHub repository susheel-op/veritas-neural, 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/susheel-op/veritas-neural
- Repository: https://github.com/susheel-op/veritas-neural

## Overview

Veritas Neural is a local-first multimodal media-forensics application. The principal workflow is a user submitting text or an asset through the React interface, the FastAPI analysis endpoint dispatching analysis by modality, and the interface presenting a verdict and forensic breakdown. README capabilities include image and face signals, sparse video-frame analysis, audio spectral analysis, and text classification. The sampled backend excerpt confirms model loading and image/video processing details, but omits much of endpoint dispatch and frontend request code; those relationships are shown only where the README documents them.

Main entry points: [`main.py`](https://github.com/susheel-op/veritas-neural/blob/clean-main/main.py) (Ensemble Scoring), [`frontend/src/App.jsx`](https://github.com/susheel-op/veritas-neural/blob/clean-main/frontend/src/App.jsx) (React Interface)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_interface["User Interface"]
  node_web_app["React Interface<br/>[App.jsx]"]
end

subgraph group_service["Analysis Service"]
  node_api["Analyze API<br/>[main.py]"]
end

subgraph group_forensics["Forensic Analysis"]
  node_image_analysis["Image Analysis<br/>[main.py]"]
  node_siglip["SigLIP Scoring<br/>[main.py]"]
  node_face_vit["Face ViT Scoring<br/>[main.py]"]
  node_exif["EXIF Signals<br/>[main.py]"]
  node_video_sampling["Video Sampling<br/>[main.py]"]
  node_audio_analysis["Audio Analysis<br/>[main.py]"]
  node_text_analysis["Text Analysis<br/>[main.py]"]
end

subgraph group_results["Verdict"]
  node_ensemble["Ensemble Scoring<br/>[main.py]"]
  node_response["Forensic Result<br/>[main.py]"]
end

node_user(("User"))

node_user -->|"submits asset"| node_web_app
node_web_app -->|"sends analysis"| node_api
node_api -->|"dispatches image"| node_image_analysis
node_api -->|"dispatches video"| node_video_sampling
node_api -->|"dispatches audio"| node_audio_analysis
node_api -->|"dispatches text"| node_text_analysis
node_image_analysis -->|"scores image"| node_siglip
node_image_analysis -->|"scores face crops"| node_face_vit
node_image_analysis -->|"checks metadata"| node_exif
node_video_sampling -->|"scores sampled frames"| node_siglip
node_siglip -->|"contributes score"| node_ensemble
node_face_vit -->|"contributes score"| node_ensemble
node_exif -->|"contributes signal"| node_ensemble
node_audio_analysis -->|"contributes score"| node_ensemble
node_text_analysis -->|"contributes score"| node_ensemble
node_ensemble -->|"produces verdict"| node_response
node_response -->|"returns breakdown"| node_web_app

click node_web_app "https://github.com/susheel-op/veritas-neural/blob/clean-main/frontend/src/App.jsx"
click node_api "https://github.com/susheel-op/veritas-neural/blob/clean-main/main.py"
click node_image_analysis "https://github.com/susheel-op/veritas-neural/blob/clean-main/main.py"
click node_siglip "https://github.com/susheel-op/veritas-neural/blob/clean-main/main.py"
click node_face_vit "https://github.com/susheel-op/veritas-neural/blob/clean-main/main.py"
click node_exif "https://github.com/susheel-op/veritas-neural/blob/clean-main/main.py"
click node_video_sampling "https://github.com/susheel-op/veritas-neural/blob/clean-main/main.py"
click node_audio_analysis "https://github.com/susheel-op/veritas-neural/blob/clean-main/main.py"
click node_text_analysis "https://github.com/susheel-op/veritas-neural/blob/clean-main/main.py"
click node_ensemble "https://github.com/susheel-op/veritas-neural/blob/clean-main/main.py"
click node_response "https://github.com/susheel-op/veritas-neural/blob/clean-main/main.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_web_app,node_user toneBlue
class node_api toneAmber
class node_image_analysis,node_siglip,node_face_vit,node_exif,node_video_sampling,node_audio_analysis,node_text_analysis toneMint
class node_ensemble,node_response toneRose
```

## Components

### User Interface

- [React Interface](https://github.com/susheel-op/veritas-neural/blob/clean-main/frontend/src/App.jsx): `frontend/src/App.jsx`

### Analysis Service

- [Analyze API](https://github.com/susheel-op/veritas-neural/blob/clean-main/main.py): `main.py`

### Forensic Analysis

- [Image Analysis](https://github.com/susheel-op/veritas-neural/blob/clean-main/main.py): `main.py`
- [SigLIP Scoring](https://github.com/susheel-op/veritas-neural/blob/clean-main/main.py): `main.py`
- [Face ViT Scoring](https://github.com/susheel-op/veritas-neural/blob/clean-main/main.py): `main.py`
- [EXIF Signals](https://github.com/susheel-op/veritas-neural/blob/clean-main/main.py): `main.py`
- [Video Sampling](https://github.com/susheel-op/veritas-neural/blob/clean-main/main.py): `main.py`
- [Audio Analysis](https://github.com/susheel-op/veritas-neural/blob/clean-main/main.py): `main.py`
- [Text Analysis](https://github.com/susheel-op/veritas-neural/blob/clean-main/main.py): `main.py`

### Verdict

- [Ensemble Scoring](https://github.com/susheel-op/veritas-neural/blob/clean-main/main.py): `main.py`
- [Forensic Result](https://github.com/susheel-op/veritas-neural/blob/clean-main/main.py): `main.py`

### Other components

- **User**

## Connections

- User → React Interface: submits asset (evidence: `README.md`)
- React Interface → Analyze API: sends analysis (evidence: `README.md`)
- Analyze API → Image Analysis: dispatches image (evidence: `README.md`)
- Analyze API → Video Sampling: dispatches video (evidence: `README.md`)
- Analyze API → Audio Analysis: dispatches audio (evidence: `README.md`)
- Analyze API → Text Analysis: dispatches text (evidence: `README.md`)
- Image Analysis → SigLIP Scoring: scores image (evidence: `main.py`)
- Image Analysis → Face ViT Scoring: scores face crops (evidence: `main.py`)
- Image Analysis → EXIF Signals: checks metadata (evidence: `main.py`)
- Video Sampling → SigLIP Scoring: scores sampled frames (evidence: `README.md`)
- SigLIP Scoring → Ensemble Scoring: contributes score (evidence: `README.md`)
- Face ViT Scoring → Ensemble Scoring: contributes score (evidence: `README.md`)
- EXIF Signals → Ensemble Scoring: contributes signal (evidence: `README.md`)
- Audio Analysis → Ensemble Scoring: contributes score (evidence: `README.md`)
- Text Analysis → Ensemble Scoring: contributes score (evidence: `README.md`)
- Ensemble Scoring → Forensic Result: produces verdict (evidence: `README.md`)
- Forensic Result → React Interface: returns breakdown (evidence: `README.md`)
