← Voltar a studyAI — Documentação do Projeto

📋 Visão Geral — studyAI

studyAI — Documentação do Projeto

Apresentação

studyAI

AI-powered study platform — Generate structured learning material, practice questions, and get feedback from your own documents. Any domain, any topic.


Overview

studyAI turns your documents into a personalized study system. Upload PDFs and notes, define what you want to learn, and the system generates structured content, practice questions, and answers your doubts—all grounded in your material.

A carregar diagrama…

Value Proposition

UserUse case
ProfessionalUpload guidelines, articles. "I want to study X." → Structured material + practice questions + Q&A.
StudentUpload notes, legislation. "Develop on civil liability." → Organized content with evaluation.
Interview prepUpload job description + docs. "Create material on RAG." → Study, practice, clarify via chat.

Differentiator: Content is grounded in your documents. No generic curricula—your knowledge base, your study path.


User Journey

A carregar diagrama…

Architecture

A carregar diagrama…
LayerTechnology
FrontendNext.js (App Router)
BackendFastAPI
AuthJWT + refresh tokens (own backend)
DBPostgreSQL
Vectorpgvector
StorageS3-compatible (MinIO, R2)
QueueCelery + Redis
LLMOpenAI
OrchestrationLangGraph

Agent Graph

A carregar diagrama…
AgentRole
RouterClassifies intent, routes to the right agent
Content PlannerPlans structure from RAG retrieval
Content WriterWrites sections grounded in chunks
Question GeneratorCreates practice questions
Question EvaluatorScores answers, gives feedback
RAG QA AgentAnswers questions from your material

RAG Pipeline

3 estágios: Hybrid search (dense + BM25) → RRF (fusão por rank) → Cross-encoder rerank.

A carregar diagrama…
  • Scope: One index per project. Isolation by project_id.
  • Chunking: 500–1200 chars, paragraph/header boundaries.
  • Retrieval: Dense + BM25 → RRF → cross-encoder → top-5 a 20 per agent.

Implementation Phases

PhaseFocusDuration
0 — FoundationAuth, DB, Docker2–3 wk
1 — CoreProjects, upload, ingest, RAG2–3 wk
2 — AgentsRouter, Planner, Writer, QA, Evaluator3–4 wk
3 — LearningSM-2, user profile, memory2–3 wk
4 — ProductionRate limit, cost control, deploy1–2 wk

Documentation

DocumentDescription
ARCHITECTURELayers, components, data flow
API_SPECREST API specification
DATA_MODELDatabase schema
AGENTSAgent graph, intents, RAG per agent
RAG_DESIGNChunking, indexing, retrieval
FLOWSUser flows, sequences
ROADMAPSprints, timeline, checklists
DIAGRAMSIndex of all diagrams

Full index: docs/INDEX.md


Quick Start (planned)

# Clone
git clone https://github.com/your-org/studyAI.git
cd studyAI

# Dev
docker-compose up -d
# API: http://localhost:8000
# Web: http://localhost:3000

References

Zona de prática

Sem perguntas. Clica em Editar para adicionar.