staceyampaire/group-g-university-student-support-case-agent

How staceyampaire/group-g-university-student-support-case-agent works

This repository is a university student-support assistant prototype. Its principal demonstrated workflow loads approved university documents with provenance, chunks and embeds them, ranks chunks against a student question, and uses retrieved evidence to generate a grounded answer, with Groq as a generation fallback. Separate scripts demonstrate case-information prompting and prompt evaluation. The graph reflects the sampled scripts and README; it does not assume a persistent index or application service. The demo currently uses a hard-coded question rather than an interactive student interface.

Main entry points: rag_demo.py RAG workflow · ingestion.py Document ingestion · main.py Case response demo · evaluate_prompt.py Prompt evaluation

Components 12

Approved knowledge

University documents knowledge
Corpus register docs/corpus_register.csv

RAG demo

Document ingestion src/ingestion.py
RAG workflow src/rag_demo.py
Embedding and ranking src/rag_demo.py
Evidence context src/rag_demo.py
Grounded generation src/rag_demo.py

Case prompts

Case response demo src/main.py
Prompt evaluation src/evaluate_prompt.py

Other components

Student question
Gemini API
Groq API

Connections 12

RAG workflow → Document ingestion: loads documents src/rag_demo.py
Document ingestion → University documents: reads documents src/ingestion.py
Document ingestion → Corpus register: reads provenance src/ingestion.py
Student question → RAG workflow: asks src/rag_demo.py
RAG workflow → Embedding and ranking: embeds corpus src/rag_demo.py
RAG workflow → Embedding and ranking: embeds question src/rag_demo.py
Embedding and ranking → Evidence context: ranks chunks src/rag_demo.py
Evidence context → Grounded generation: provides evidence src/rag_demo.py
Grounded generation → Gemini API: generates answer src/rag_demo.py
Grounded generation → Groq API: fallback generation src/rag_demo.py
Case response demo → Gemini API: generates response src/main.py
Prompt evaluation → Gemini API: evaluates prompt src/evaluate_prompt.py

More Python diagrams: hheydaroff/rooflow-cookiecutter · hj91/pyaiml-xmpp-chat-bot · huntingphi/voice-to-note · iamamanporwal/resume-ranker · idogalil/people-counting-system

Drawn by GitDiagram on September 30, 2026 from the repository's file tree, README and source files. Read as Markdown ·