# aroojkhan192/university-rag-recommender architecture

> Architecture diagram of the GitHub repository aroojkhan192/university-rag-recommender, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-02). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/aroojkhan192/university-rag-recommender
- Repository: https://github.com/aroojkhan192/university-rag-recommender

## Overview

This is a compact RAG university recommender: a student query enters through the Streamlit demo or command line, retrieves relevant university records from a FAISS index, and produces a language-model recommendation grounded in retrieved context. Index construction is a separate data-preparation stage. The README documents these stages and dependencies, but no source excerpts were available, so the Streamlit-to-pipeline connection is shown as unverified.

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_interfaces["User interfaces"]
  node_streamlit["Streamlit demo"]
end

subgraph group_rag["Recommendation pipeline"]
  node_recommend["RAG recommender"]
  node_langchain["RAG orchestration"]
  node_generator["Flan-T5 model"]
end

subgraph group_knowledge["University knowledge"]
  node_dataset["University dataset"]
  node_indexer["Index builder"]
  node_embedder["Sentence embedder"]
  node_faiss[("FAISS vector index")]
end

node_student(("Student"))

node_student -->|"enters query"| node_streamlit
node_student -->|"runs command"| node_recommend
node_streamlit -.->|"submits query"| node_recommend
node_dataset -->|"provides records"| node_indexer
node_indexer -->|"embeds records"| node_embedder
node_indexer -->|"stores vectors"| node_faiss
node_recommend -->|"retrieves matches"| node_faiss
node_recommend -->|"uses orchestration"| node_langchain
node_recommend -->|"generates from context"| node_generator

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_streamlit toneBlue
class node_recommend,node_langchain,node_generator toneAmber
class node_dataset,node_indexer,node_embedder,node_faiss toneMint
class node_student toneIndigo
```

## Components

### User interfaces

- **Streamlit demo**

### Recommendation pipeline

- **RAG recommender**
- **RAG orchestration**
- **Flan-T5 model**

### University knowledge

- **University dataset**
- **Index builder**
- **Sentence embedder**
- **FAISS vector index**

### Other components

- **Student**

## Connections

- Student → Streamlit demo: enters query (evidence: `README.md`)
- Student → RAG recommender: runs command (evidence: `README.md`)
- Streamlit demo → RAG recommender: submits query
- University dataset → Index builder: provides records (evidence: `README.md`)
- Index builder → Sentence embedder: embeds records (evidence: `README.md`)
- Index builder → FAISS vector index: stores vectors (evidence: `README.md`)
- RAG recommender → FAISS vector index: retrieves matches (evidence: `README.md`)
- RAG recommender → RAG orchestration: uses orchestration (evidence: `README.md`)
- RAG recommender → Flan-T5 model: generates from context (evidence: `README.md`)
