Overview

Built for a Generative AI course: students can ask about their final-year project rules, which are buried in a 62-page handbook. The assistant answers from the handbook itself and declines to answer when the handbook doesn't cover the question.

Pipeline

| Stage | Choice | Why | |---|---|---| | Chunking | 300 words, 30% overlap, 50-word minimum | Enough context per chunk; the overlap keeps rules that span a boundary intact | | Embeddings | all-MiniLM-L6-v2 (384-dim) | Small and fast (~50 ms per query) with strong semantic matching | | Vector store | FAISS flat index, L2-normalised (cosine) | Exact search; the whole index is under 1 MB | | Retrieval | Top-5 chunks, similarity ≥ 0.25 | Rejects weak matches instead of guessing | | Generation | GPT-4o-mini, temperature 0.3 | Low temperature keeps answers factual and close to the source |

Engineering decisions

• Refuse rather than hallucinate: if no chunk clears the 0.25 similarity threshold, the assistant says the handbook doesn't cover the question instead of improvising.
• Measure it: every prompt and retrieval is logged, and a technical report records the configuration, retrieval scores and example results so the choices can be checked and tuned.

Tech stack

Python · Sentence-Transformers · FAISS · OpenAI GPT-4o-mini · Streamlit · PyPDF

Python

OpenAI

Hugging Face

View project