# banh-van-hiep/vietnamese-legal-rag architecture

> Architecture diagram of the GitHub repository banh-van-hiep/vietnamese-legal-rag, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-30). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/banh-van-hiep/vietnamese-legal-rag
- Repository: https://github.com/banh-van-hiep/vietnamese-legal-rag

## Overview

The README identifies a Vietnamese-law question-answering assistant using RAG, but provides no source files or implementation details. The graph therefore shows only the documented user-facing purpose and the retrieval-then-generation stages implied by RAG; component paths and internal wiring are unavailable.

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_rag["RAG workflow"]
  node_retrieval["Legal retrieval"]
  node_generation["Answer generation"]
end

node_user(("Question asker"))

node_user -->|"asks question"| node_retrieval
node_retrieval -->|"provides context"| node_generation
node_generation -->|"returns answer"| node_user

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_retrieval,node_generation toneBlue
class node_user toneIndigo
```

## Components

### RAG workflow

- **Legal retrieval**
- **Answer generation**

### Other components

- **Question asker**

## Connections

- Question asker → Legal retrieval: asks question (evidence: `README.md`)
- Legal retrieval → Answer generation: provides context (evidence: `README.md`)
- Answer generation → Question asker: returns answer (evidence: `README.md`)
