# antonyathibana/smart-india-hackathon architecture

> Architecture diagram of the GitHub repository antonyathibana/smart-india-hackathon, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-01). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/antonyathibana/smart-india-hackathon
- Repository: https://github.com/antonyathibana/smart-india-hackathon

## Overview

SMART-INDIA-HACKATHON is a deterministic-first advisory application for rural MSMEs. A user submits information through the web frontend; the integration service combines outputs from geographic, market, financial, scheme, and opportunity/risk services. The assistant explains computed results using grounded government information, and the multilingual adapter can translate that prose. The README documents the service boundaries and HTTP relationships, but no source excerpts or implementation files were provided, so this map reflects documented behavior only.

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_experience["User experience"]
  node_frontend["Web frontend"]
end

subgraph group_orchestration["Integration and explanation"]
  node_integration["Integration API"]
  node_assistant["LLM assistant"]
  node_multilingual["Translation adapter"]
end

subgraph group_advisory["Deterministic advisory"]
  node_map["MSME map engine"]
  node_market["Market intelligence"]
  node_financial["Financial engine"]
  node_schemes["Scheme router"]
  node_opportunity["Opportunity risk"]
  node_rag["Government retrieval"]
end

subgraph group_data["Data foundation"]
  node_dataengine["Udyam data engine"]
  node_reconciliation["Geographic reconciliation"]
  node_database[("Postgres PostGIS")]
end

node_user(("MSME user"))
node_csv["Udyam CSV dump"]
node_nominatim["Nominatim"]
node_translationprovider["Translation provider"]

node_user -->|"uses"| node_frontend
node_frontend -->|"calls API"| node_integration
node_integration -->|"orchestrates"| node_map
node_integration -->|"orchestrates"| node_market
node_integration -->|"orchestrates"| node_financial
node_integration -->|"orchestrates"| node_schemes
node_integration -->|"orchestrates"| node_opportunity
node_market -->|"provides evidence"| node_opportunity
node_financial -->|"provides evidence"| node_opportunity
node_schemes -->|"provides evidence"| node_opportunity
node_assistant -->|"orchestrates"| node_market
node_assistant -->|"orchestrates"| node_financial
node_assistant -->|"orchestrates"| node_schemes
node_assistant -->|"explains output"| node_opportunity
node_assistant -->|"grounds facts"| node_rag
node_assistant -->|"looks up metadata"| node_schemes
node_multilingual -->|"translates prose"| node_assistant
node_multilingual -.->|"uses when configured"| node_translationprovider
node_dataengine -->|"loads data"| node_csv
node_dataengine -->|"writes records"| node_database
node_map -->|"queries geography"| node_database
node_market -->|"reads enterprise data"| node_database
node_market -->|"reads coordinates"| node_database
node_opportunity -->|"reads coordinates"| node_database
node_reconciliation -->|"enriches coordinates"| node_database
node_reconciliation -->|"geocodes locations"| node_nominatim

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_frontend,node_user toneBlue
class node_integration,node_assistant,node_multilingual toneAmber
class node_map,node_market,node_financial,node_schemes,node_opportunity,node_rag toneMint
class node_dataengine,node_reconciliation,node_database toneRose
class node_csv,node_nominatim,node_translationprovider toneIndigo
```

## Components

### User experience

- **Web frontend**

### Integration and explanation

- **Integration API**
- **LLM assistant**
- **Translation adapter**

### Deterministic advisory

- **MSME map engine**
- **Market intelligence**
- **Financial engine**
- **Scheme router**
- **Opportunity risk**
- **Government retrieval**

### Data foundation

- **Udyam data engine**
- **Geographic reconciliation**
- **Postgres PostGIS**

### Other components

- **MSME user**
- **Udyam CSV dump**
- **Nominatim**
- **Translation provider**

## Connections

- MSME user → Web frontend: uses (evidence: `README.md`)
- Web frontend → Integration API: calls API (evidence: `README.md`)
- Integration API → MSME map engine: orchestrates (evidence: `README.md`)
- Integration API → Market intelligence: orchestrates (evidence: `README.md`)
- Integration API → Financial engine: orchestrates (evidence: `README.md`)
- Integration API → Scheme router: orchestrates (evidence: `README.md`)
- Integration API → Opportunity risk: orchestrates (evidence: `README.md`)
- Market intelligence → Opportunity risk: provides evidence (evidence: `README.md`)
- Financial engine → Opportunity risk: provides evidence (evidence: `README.md`)
- Scheme router → Opportunity risk: provides evidence (evidence: `README.md`)
- LLM assistant → Market intelligence: orchestrates (evidence: `README.md`)
- LLM assistant → Financial engine: orchestrates (evidence: `README.md`)
- LLM assistant → Scheme router: orchestrates (evidence: `README.md`)
- LLM assistant → Opportunity risk: explains output (evidence: `README.md`)
- LLM assistant → Government retrieval: grounds facts (evidence: `README.md`)
- LLM assistant → Scheme router: looks up metadata (evidence: `README.md`)
- Translation adapter → LLM assistant: translates prose (evidence: `README.md`)
- Translation adapter → Translation provider: uses when configured (evidence: `README.md`)
- Udyam data engine → Udyam CSV dump: loads data (evidence: `README.md`)
- Udyam data engine → Postgres PostGIS: writes records (evidence: `README.md`)
- MSME map engine → Postgres PostGIS: queries geography (evidence: `README.md`)
- Market intelligence → Postgres PostGIS: reads enterprise data (evidence: `README.md`)
- Market intelligence → Postgres PostGIS: reads coordinates (evidence: `README.md`)
- Opportunity risk → Postgres PostGIS: reads coordinates (evidence: `README.md`)
- Geographic reconciliation → Postgres PostGIS: enriches coordinates (evidence: `README.md`)
- Geographic reconciliation → Nominatim: geocodes locations (evidence: `README.md`)
