# mansipatel42/smart-travel architecture

> Architecture diagram of the GitHub repository mansipatel42/smart-travel, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-05-16). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/mansipatel42/smart-travel
- Repository: https://github.com/mansipatel42/smart-travel

## Overview

##### Project type and purpose
- From the file tree and README, this is a full-stack “smart travel” chatbot application:
- A React/TypeScript front end (chatbot/ui)
- A Python FastAPI back end (chatbot/server) that exposes chat endpoints
- Fine-tuning scripts (fine-tuning/) to train a Mistral 7B travel companion model
- A web scraper (scraper/) to gather travel data for training/knowledge

##### File structure
- Top-level directories:
- chatbot/server – FastAPI service, test harness, “travel_agent” business logic
- chatbot/ui – Single-page application built with Vite + React + TypeScript
- fine-tuning – Python scripts to merge and tune models on travel prompts/data
- scraper – Data-collection tooling (scraper.py, main.py, config.json)
- Key configs: package.json, tsconfig*, eslint.config.js in UI; REQUIREMENTS.txt for Python deps

##### README for additional insights
- Confirms “Fine tuned Mistral 7B-v0.3 for travel companion”
- Implies
- A pipeline: scrape → preprocess → fine-tune → deploy as API → UI consumption

a. Main components
1. UI (React SPA)
2. API Server (FastAPI)
3. Travel Agent module (encapsulates LLM calls, prompt logic)
4. Fine-tuning pipeline (merge-models.py, tuning-travel.py)
5. Web Scraper (scraper.py, data_eda.py)
6. Model Storage (local disk or S3 bucket)
7. External LLM base model repository (Mistral 7B)
b. Relationships & data flow
- User → UI: chat input
- UI → API Server: JSON over HTTP
- API Server ↔ Travel Agent: function calls
- Travel Agent → LLM runtime (loads fine-tuned weights from Model Storage)
- Scraper → Raw travel data → Preproces­sor → Training dataset
- Fine-tuning scripts read training dataset + base model → produce new model → store in Model Storage
c. Architectural patterns & design principles
- Separation of concerns: UI vs API vs AI logic vs data collection vs model training
- Stateless API server; state (models, data) is externalized to storage
- Pipeline pattern: scraping → data preparation → model tuning → deployment
d. Key technologies & libraries
- Frontend: React, Vite, TypeScript, ESLint
- Backend: Python, FastAPI, Uvicorn
- AI: Mistral 7B, transformers (or similar), custom “travel_agent” logic
- Data tooling: pandas/EDA (data_eda.py), custom scraper
- Deployment: Docker (implied), model artifact storage

## Diagram (Mermaid)

```mermaid
flowchart TB
    subgraph "User Interface Layer"
        UI["React SPA"]:::frontend
        pkg["package.json"]:::frontend
        ts["tsconfig.json"]:::frontend
        vite["vite.config.ts"]:::frontend
        App["App.tsx"]:::frontend
        Chat["Chat.tsx"]:::frontend
        MainUI["main.tsx"]:::frontend
    end

    subgraph "API & Business Logic Layer"
        API["FastAPI Server"]:::backend
        Agent["Travel Agent Module"]:::backend
        Test["API Test Harness"]:::backend
    end

    subgraph "AI Model Layer"
        Runtime["LLM Runtime"]:::backend
    end

    subgraph "Data Pipeline Layer"
        ScrapeMain["scraper/main.py"]:::datapipe
        ScraperLogic["scraper/scraper.py"]:::datapipe
        EDA["scraper/data_eda.py"]:::datapipe
        Config["scraper/config.json"]:::datapipe
        Merge["merge-models.py"]:::datapipe
        Tune["tuning-travel.py"]:::datapipe
    end

    subgraph "Storage & External"
        Storage["Model Storage"]:::storage
        External["Mistral 7B Repo"]:::storage
        Dataset["Training Dataset"]:::storage
    end

    User((User)) 
    User -->|"chat input"| UI
    UI -->|"HTTP/JSON"| API
    API -->|"calls functions"| Agent
    Agent -->|"load weights"| Runtime
    Runtime -->|"reads checkpoint"| Storage

    ScrapeMain -->|"scrape data"| ScraperLogic
    ScraperLogic -->|"raw data"| EDA
    EDA -->|"processed data"| Merge
    EDA -->|"processed data"| Tune
    External -->|"base model"| Merge
    Merge -->|"merged model"| Tune
    Tune -->|"fine-tuned model"| Storage
    EDA -->|"output dataset"| Dataset
    Merge -->|"reads dataset"| Dataset
    Tune -->|"reads dataset"| Dataset

    click UI "https://github.com/mansipatel42/smart-travel/tree/main/chatbot/ui/"
    click pkg "https://github.com/mansipatel42/smart-travel/blob/main/chatbot/ui/package.json"
    click ts "https://github.com/mansipatel42/smart-travel/blob/main/chatbot/ui/tsconfig.json"
    click vite "https://github.com/mansipatel42/smart-travel/blob/main/chatbot/ui/vite.config.ts"
    click App "https://github.com/mansipatel42/smart-travel/blob/main/chatbot/ui/src/App.tsx"
    click Chat "https://github.com/mansipatel42/smart-travel/blob/main/chatbot/ui/src/Chat.tsx"
    click MainUI "https://github.com/mansipatel42/smart-travel/blob/main/chatbot/ui/src/main.tsx"
    click API "https://github.com/mansipatel42/smart-travel/blob/main/chatbot/server/fast_api.py"
    click Agent "https://github.com/mansipatel42/smart-travel/blob/main/chatbot/server/travel_agent.py"
    click Test "https://github.com/mansipatel42/smart-travel/blob/main/chatbot/server/test.py"
    click Merge "https://github.com/mansipatel42/smart-travel/blob/main/fine-tuning/merge-models.py"
    click Tune "https://github.com/mansipatel42/smart-travel/blob/main/fine-tuning/tuning-travel.py"
    click ScrapeMain "https://github.com/mansipatel42/smart-travel/blob/main/scraper/main.py"
    click ScraperLogic "https://github.com/mansipatel42/smart-travel/blob/main/scraper/scraper.py"
    click EDA "https://github.com/mansipatel42/smart-travel/blob/main/scraper/data_eda.py"
    click Config "https://github.com/mansipatel42/smart-travel/blob/main/scraper/config.json"

    classDef frontend fill:#D6E9FF,stroke:#4682B4,color:#000
    classDef backend fill:#D6F5D6,stroke:#2E8B57,color:#000
    classDef datapipe fill:#FFE2B3,stroke:#DAA520,color:#000
    classDef storage fill:#E0E0E0,stroke:#808080,color:#000
```
