# navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev- architecture

> Architecture diagram of the GitHub repository navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-06). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-
- Repository: https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-

## Overview

TALK is a voice-first decision assistant: a user speaks or enters a dilemma, the backend triages and frames it, Laya scores the choices, and the interface presents calibrated reasoning and can speak or export the result. Research-dependent decisions add LLM framing and web evidence; document grounding, configurable rules, provider settings, and voice personas are supporting capabilities. The README and source index establish the main calls and capabilities; some frontend-to-API wiring and unsampled subsystem internals are not shown, so those links are omitted.

Main entry points: [`frontend/src/App.tsx`](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/frontend/src/App.tsx) (Workspace controller), [`backend/app/main.py`](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/backend/app/main.py) (Backend API), [`backend/app/orchestrator.py`](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/backend/app/orchestrator.py) (Decision orchestrator), [`backend/app/llm_manager.py`](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/backend/app/llm_manager.py) (LLM framing)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_workspace["Decision workspace"]
  node_app["Workspace controller<br/>[App.tsx]"]
  node_orb["Liquid orb<br/>[LiquidOrb.tsx]"]
  node_voiceorb["Voice orb<br/>[VoiceOrb.tsx]"]
  node_orbview["Orb visualization<br/>[Orb.tsx]"]
  node_audio["Audio analyzer<br/>[audio.ts]"]
  node_resultpane["Decision results<br/>[RightPane.tsx]"]
  node_duel["Versus builder<br/>[VersusModal.tsx]"]
  node_settings["Provider settings<br/>[SettingsModal.tsx]"]
end

subgraph group_decision["Decision pipeline"]
  node_api["Backend API<br/>[main.py]"]
  node_orchestrator["Decision orchestrator<br/>[orchestrator.py]"]
  node_classification["Rule classification"]
  node_laya["Laya scoring<br/>[laya_service.py]"]
end

subgraph group_integrations["External services"]
  node_llm["LLM framing<br/>[llm_manager.py]"]
  node_voice["Voice synthesis<br/>[voice_service.py]"]
  node_llmproviders(("LLM providers"))
  node_web(("Web knowledge index"))
  node_tts(("Neural voice services"))
end

subgraph group_support["Grounding and output"]
  node_exporter["Badge exporter<br/>[cardExporter.ts]"]
  node_parser["Document parser<br/>[document_parser.py]"]
  node_models["API data models<br/>[models.py]"]
end

node_user(("Decision maker"))

node_user -->|"enters decision"| node_app
node_app -->|"renders"| node_orb
node_orb -->|"renders"| node_voiceorb
node_app -->|"uses audio"| node_audio
node_app -->|"renders results"| node_resultpane
node_app -->|"opens duel"| node_duel
node_app -->|"opens settings"| node_settings
node_resultpane -->|"exports badge"| node_exporter
node_app -.->|"submits decisions"| node_api
node_api -->|"routes decision"| node_orchestrator
node_api -->|"parses upload"| node_parser
node_api -->|"requests speech"| node_voice
node_orchestrator -->|"classifies query"| node_classification
node_orchestrator -->|"frames research"| node_llm
node_orchestrator -->|"scores choices"| node_laya
node_llm -->|"queries provider"| node_llmproviders
node_llm -->|"searches evidence"| node_web
node_voice -->|"streams speech"| node_tts
node_api -->|"validates payloads"| node_models
node_orchestrator -->|"builds responses"| node_models

click node_app "https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/frontend/src/App.tsx"
click node_orb "https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/frontend/src/components/LiquidOrb.tsx"
click node_voiceorb "https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/frontend/src/components/VoiceOrb.tsx"
click node_orbview "https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/frontend/src/components/Orb.tsx"
click node_audio "https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/frontend/src/utils/audio.ts"
click node_resultpane "https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/frontend/src/components/RightPane.tsx"
click node_duel "https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/frontend/src/components/VersusModal.tsx"
click node_settings "https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/frontend/src/components/SettingsModal.tsx"
click node_exporter "https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/frontend/src/utils/cardExporter.ts"
click node_api "https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/backend/app/main.py"
click node_orchestrator "https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/backend/app/orchestrator.py"
click node_classification "https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/backend/app/classification_service.py"
click node_laya "https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/backend/app/laya_service.py"
click node_llm "https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/backend/app/llm_manager.py"
click node_parser "https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/backend/app/document_parser.py"
click node_voice "https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/backend/app/voice_service.py"
click node_models "https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/backend/app/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_app,node_orb,node_voiceorb,node_orbview,node_audio,node_resultpane,node_duel,node_settings toneBlue
class node_api,node_orchestrator,node_classification,node_laya toneAmber
class node_llm,node_voice,node_llmproviders,node_web,node_tts toneMint
class node_exporter,node_parser,node_models toneRose
class node_user toneIndigo
```

## Components

### Decision workspace

- [Workspace controller](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/frontend/src/App.tsx): `frontend/src/App.tsx`
- [Liquid orb](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/frontend/src/components/LiquidOrb.tsx): `frontend/src/components/LiquidOrb.tsx`
- [Voice orb](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/frontend/src/components/VoiceOrb.tsx): `frontend/src/components/VoiceOrb.tsx`
- [Orb visualization](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/frontend/src/components/Orb.tsx): `frontend/src/components/Orb.tsx`
- [Audio analyzer](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/frontend/src/utils/audio.ts): `frontend/src/utils/audio.ts`
- [Decision results](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/frontend/src/components/RightPane.tsx): `frontend/src/components/RightPane.tsx`
- [Versus builder](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/frontend/src/components/VersusModal.tsx): `frontend/src/components/VersusModal.tsx`
- [Provider settings](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/frontend/src/components/SettingsModal.tsx): `frontend/src/components/SettingsModal.tsx`

### Decision pipeline

- [Backend API](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/backend/app/main.py): `backend/app/main.py`
- [Decision orchestrator](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/backend/app/orchestrator.py): `backend/app/orchestrator.py`
- [Rule classification](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/backend/app/classification_service.py): `backend/app/classification_service.py`
- [Laya scoring](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/backend/app/laya_service.py): `backend/app/laya_service.py`

### External services

- [LLM framing](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/backend/app/llm_manager.py): `backend/app/llm_manager.py`
- [Voice synthesis](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/backend/app/voice_service.py): `backend/app/voice_service.py`
- **LLM providers**
- **Web knowledge index**
- **Neural voice services**

### Grounding and output

- [Badge exporter](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/frontend/src/utils/cardExporter.ts): `frontend/src/utils/cardExporter.ts`
- [Document parser](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/backend/app/document_parser.py): `backend/app/document_parser.py`
- [API data models](https://github.com/navzar81-dev/talk---a-decision-making-model-leveraging-laya-and-jev-/blob/main/backend/app/models.py): `backend/app/models.py`

### Other components

- **Decision maker**

## Connections

- Decision maker → Workspace controller: enters decision (evidence: `README.md`)
- Workspace controller → Liquid orb: renders (evidence: `frontend/src/App.tsx`)
- Liquid orb → Voice orb: renders (evidence: `frontend/src/components/LiquidOrb.tsx`)
- Workspace controller → Audio analyzer: uses audio (evidence: `frontend/src/App.tsx`)
- Workspace controller → Decision results: renders results (evidence: `frontend/src/App.tsx`)
- Workspace controller → Versus builder: opens duel (evidence: `frontend/src/App.tsx`)
- Workspace controller → Provider settings: opens settings (evidence: `frontend/src/App.tsx`)
- Decision results → Badge exporter: exports badge (evidence: `frontend/src/components/RightPane.tsx`)
- Workspace controller → Backend API: submits decisions
- Backend API → Decision orchestrator: routes decision (evidence: `backend/app/main.py`)
- Backend API → Document parser: parses upload (evidence: `backend/app/main.py`)
- Backend API → Voice synthesis: requests speech (evidence: `backend/app/main.py`)
- Decision orchestrator → Rule classification: classifies query (evidence: `backend/app/orchestrator.py`)
- Decision orchestrator → LLM framing: frames research (evidence: `backend/app/orchestrator.py`)
- Decision orchestrator → Laya scoring: scores choices (evidence: `backend/app/orchestrator.py`)
- LLM framing → LLM providers: queries provider (evidence: `README.md`)
- LLM framing → Web knowledge index: searches evidence (evidence: `backend/app/llm_manager.py`)
- Voice synthesis → Neural voice services: streams speech (evidence: `README.md`)
- Backend API → API data models: validates payloads (evidence: `backend/app/main.py`)
- Decision orchestrator → API data models: builds responses (evidence: `backend/app/orchestrator.py`)
