vedlegendary/gdg-askutd

How vedlegendary/gdg-askutd works

AskUTD is a UTD-information question-answering app: a browser submits a question, the API retrieves relevant official-source passages, and answer generation returns concise cited text or abstains. The graph preserves the UI/API, retrieval and generation stages, plus storage, catalog and feedback capabilities. Corpus ingestion is an offline supporting workflow, not part of answering a request. Several links rely on the README because their implementation excerpts were not provided.

Main entry points: main.py FastAPI app · generation.py Answer generator · chat.py Chat route · retrieval.py Retrieval service

Components 22

Browser experience

AskUTD interface components/ask-utd-app.tsx
Web API client lib/api.ts

API service

FastAPI app backend/app/main.py
Chat route backend/app/routes/chat.py
Catalog route backend/app/routes/catalog.py
Feedback route backend/app/routes/feedback.py
Health route backend/app/routes/health.py
Rate limiter backend/app/ratelimit.py
Shared answer types backend/app/types.py

Evidence retrieval

Retrieval service backend/app/retrieval.py
Lexical index backend/app/retrieval_support/index.py
Query resolution backend/app/retrieval_support/query.py
Intent and scope backend/app/retrieval_support/focus.py
Evidence checks backend/app/retrieval_support/precision.py

Answer generation

Answer generator backend/app/generation.py
Answer prompts backend/app/prompts.py
Extractive fallback backend/app/llm/extractive.py
Model providers backend/app/llm

Corpus and records

SQLite records backend/app/db.py
PDF ingestion add_documents.py
PDF text extraction pdf_to_text.py

Other components

Student

Connections 29

Student → AskUTD interface: asks README.md
AskUTD interface → Web API client: submits questions components/ask-utd-app.tsx
Web API client → FastAPI app: calls API README.md
FastAPI app → Chat route: routes requests backend/app/main.py
FastAPI app → Catalog route: routes requests backend/app/main.py
FastAPI app → Feedback route: routes requests backend/app/main.py
FastAPI app → Health route: routes requests backend/app/main.py
FastAPI app → Rate limiter: configures backend/app/main.py
FastAPI app → SQLite records: initializes backend/app/main.py
Chat route → Retrieval service: requests passages README.md
Chat route → Answer generator: requests answer README.md
Retrieval service → Lexical index: searches chunks backend/app/retrieval.py
Retrieval service → Query resolution: resolves and checks backend/app/retrieval.py
Retrieval service → Evidence checks: reranks evidence backend/app/retrieval.py
Query resolution → Intent and scope: uses intent rules backend/app/retrieval_support/query.py
Evidence checks → Intent and scope: uses scope rules backend/app/retrieval_support/precision.py
Answer generator → Answer prompts: uses prompts backend/app/generation.py
Answer generator → Extractive fallback: selects fallback backend/app/generation.py
Answer generator → Model providers: selects provider README.md
Answer generator → Intent and scope: checks answer focus backend/app/generation.py
Answer generator → Evidence checks: checks evidence backend/app/generation.py
Chat route → Shared answer types: uses shared types backend/app/routes/chat.py
Retrieval service → Shared answer types: returns passages backend/app/retrieval.py
Answer generator → Shared answer types: returns answer backend/app/generation.py
Feedback route → SQLite records: stores feedback README.md
Chat route → SQLite records: records requests README.md
AskUTD interface → Feedback route: sends ratings components/ask-utd-app.tsx
Catalog route → SQLite records: reads catalog
PDF ingestion → PDF text extraction: extracts text add_documents.py

Drawn by GitDiagram on November 12, 2026 from the repository's file tree, README and source files. Read as Markdown ·