S
Web App2026CompletedFeatured Project

Flowmindmap

Welcome to your Lovable project Project info URL: https://lovable.dev/projects/4470f2ac-931e-4123-b8a5-cedb40bc0d2f How can I edit this code? There are several ways of editing your...

RoleSole Developer
Classificationhigh
Client / ContextOpen Source Project
Development TimelineCompleted

Technical Architecture & Engineering Overview

Detailed system design and core implementation

The front‑end is built as a single‑page application using React with React Router for navigation between the main index, roadmaps, and shortcuts pages. Global providers such as QueryClientProvider, ThemeProvider, and TooltipProvider wrap the component tree, establishing a consistent data‑fetching, theming, and UI‑feedback layer. Each page imports shared UI primitives from the components/ui library, ensuring a cohesive design system powered by TailwindCSS utilities.

AI generation is orchestrated through src/utils/aiProviderApi.ts. The module selects the appropriate endpoint based on the chosen provider, constructs a request payload that includes a system prompt (“You are a helpful AI assistant that creates detailed mindmaps in JSON format.”), and parses the response into a unified result shape. Error handling is explicit: non‑OK HTTP responses raise descriptive exceptions, and provider‑specific response validation (e.g., Gemini’s candidates[0].content.parts[0].text) guards against malformed data.

The Carousel component demonstrates advanced React patterns: it creates a context (CarouselContext) that exposes the Embla API, scroll controls, and orientation logic. Consumers invoke useCarousel() to access scrollPrev, scrollNext, and state flags (canScrollPrev, canScrollNext). Keyboard navigation is captured via onKeyDownCapture, mapping arrow keys to carousel actions, which improves accessibility.

User configuration for AI providers lives in AIProviderForm.tsx. The form dynamically renders fields based on the selected provider (e.g., API key input for Gemini/Grok, server URL for Ollama/LM Studio) and populates model options from a constant map. This modular UI enables seamless switching between cloud and local AI services without code changes.

The build pipeline leverages Vite (implicit from the React setup) and TypeScript compilation, with linting enforced by ESLint. No backend services are present in the repository; all AI calls are performed client‑side, relying on CORS‑enabled endpoints or local servers.

System Diagrams & Flow Visualizations

Interactive Mermaid architecture & execution flows

Architectural Visualizer · System Architecture

Core System Features

Key capabilities & architectural features

FEATURE 01

AI‑driven mind‑map generation in JSON format

AI‑driven mind‑map generation in JSON format

FEATURE 02

Support for multiple AI providers (Gemini, Grok, Ollama, LM Studio)

Support for multiple AI providers (Gemini, Grok, Ollama, LM Studio)

FEATURE 03

Responsive carousel UI with horizontal/vertical orientation

Responsive carousel UI with horizontal/vertical orientation

FEATURE 04

Keyboard navigation for carousel (Arrow keys) and shortcuts (Escape)

Keyboard navigation for carousel (Arrow keys) and shortcuts (Escape)

FEATURE 05

Dynamic form fields that adapt to selected AI provider

Dynamic form fields that adapt to selected AI provider

FEATURE 06

TailwindCSS‑styled components for consistent visual design

TailwindCSS‑styled components for consistent visual design

FEATURE 07

React Query caching and retry logic for API calls

React Query caching and retry logic for API calls

FEATURE 08

Theme switching via `next-themes` (system, light, dark)

Theme switching via `next-themes` (system, light, dark)

FEATURE 09

Shortcut reference page with common editor commands

Shortcut reference page with common editor commands

FEATURE 010

Modular component library (`ui` folder) for reuse

Modular component library (`ui` folder) for reuse

Engineering Challenges & Solutions

Problem statements & resolution strategies

Challenge #1

Balancing client‑side AI calls with CORS and authentication constraints

Balancing client‑side AI calls with CORS and authentication constraints

Challenge #2

Normalizing disparate response schemas from different AI services

Normalizing disparate response schemas from different AI services

Challenge #3

Ensuring carousel accessibility while maintaining performance

Ensuring carousel accessibility while maintaining performance

Challenge #4

Managing state synchronization between Embla API and React state flags

Managing state synchronization between Embla API and React state flags

Challenge #5

Providing a seamless UX when switching between cloud and local AI providers

Providing a seamless UX when switching between cloud and local AI providers

Key Code Modules & Architecture

Core file entrypoints and service responsibilities

SrcMODULE 01
src

Module component managing src source logic

ComponentsMODULE 02
src/components

Module component managing components source logic

UiMODULE 03
src/components/ui

Module component managing ui source logic

HooksMODULE 04
src/hooks

Module component managing hooks source logic

LibMODULE 05
src/lib

Module component managing lib source logic

PagesMODULE 06
src/pages

Module component managing pages source logic

StoreMODULE 07
src/store

Module component managing store source logic

TypesMODULE 08
src/types

Module component managing types source logic

UtilsMODULE 09
src/utils

Module component managing utils source logic

User Journey Pipeline

  1. 1User Access & Preset Selection: User opens client interface and configures request parameters or task workflow presets.
  2. 2Client Payload Dispatch: Front-end components (React, TailwindCSS) serialize input objects and send HTTP/WebSocket requests to `/api/analyze`.
  3. 3Middleware & Validation Check: API Gateway evaluates CORS headers, authorization tokens, and input validation schemas.
  4. 4Service & Inference Execution: Service controllers dispatch request frames to model inference engine (Local Engine) or storage layer.
  5. 5Response Delivery & State Synchronization: Serialized output payload is returned to the client and rendered in the visual workspace.

Execution Code Flow

  1. 1Entrypoint Invocation: Request enters network interface layer via `POST /api/analyze`.
  2. 2Schema & Guardrail Verification: Middleware sanitizes payload parameters and checks rate-limiting limits.
  3. 3Controller Dispatch: Router delegates validated object to `Src` service controller.
  4. 4Engine Execution & Storage Operations: Controller executes business logic, queries database models (Persistence), and invokes ML workers.
  5. 5Response Serialization: Result model is formatted into standard JSON response frame and delivered with HTTP 200 OK.

System FAQ & Technical Specifications

Frequently asked questions and core architecture details

Q: What technologies are used in Flowmindmap?

Flowmindmap is engineered using modern full-stack frameworks.

Q: What core engineering problem does Flowmindmap solve?

Welcome to your Lovable project Project info URL: https://lovable.dev/projects/4470f2ac-931e-4123-b8a5-cedb40bc0d2f How can I edit this code? There are several ways of editing your...

Q: How is 'Balancing client‑side AI calls with CORS and authentication constraints' resolved in Flowmindmap?

Resolved through specialized system architecture and resilient state handling.

Related Systems & Case Studies

Explore similar technical architectures and projects

View All Systems