3 Commits

Author SHA1 Message Date
30957cbea0 docs: add Gradio UI demo screenshot and context disclaimer 2026-09-12 10:32:05 -03:00
Demo User
f9a68ee335 feat: add Gradio web UI
- app.py: Gradio Interface wrapping BoschProductRAG.query()
- Index built once at startup (not per-request)
- Markdown output: answer + linked sources + latency
- Example prompts included for quick demo
- Verified: launches on :7860, returns correct answers

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-09-11 17:31:08 -03:00
Demo User
9c31117553 init: Bosch HVAC Product Knowledge Bot - RAG system with CLI
RAG pipeline using Google Gemini (single free-tier API key) for both
embeddings and generation, FAISS for local retrieval.

- Product catalog: 6 Bosch HVAC systems with specs (mock data based on
  real Bosch product pages)
- RAG core: query -> embed (gemini-embedding-001) -> retrieve (FAISS,
  k=3) -> generate (gemini-flash-lite-latest) -> answer + sources
- CLI: python -m src.cli "question" with text/JSON output
- Evaluation: latency + accuracy spot-check benchmarking (evaluate.py)

Verified metrics (actual run):
- Mean latency: 1908ms
- Accuracy: 100% (5/5 spot-checks)

Tech stack: LangChain, FAISS, Google Gemini API, uv package manager.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-09-11 16:53:37 -03:00