WebRetriever — Deterministic Web Retrieval Agent

WebRetriever is an autonomous web information retrieval agent built for AMD AI League Match 4: Intelligent Web Information Retrieval. Ask in plain English and get back the specific information you asked for, with the exact source URLs behind it — or an honest refusal when no verifiable answer exists. How it works — five-stage pipeline with a deterministic core: Understand — parses the request into intent (price, contact, hours, spec, definition, how-to, date, fact), entities, and 2–4 search query variants. No ML model required. Search — provider chain with automatic fallback: TinyFish Search for the best quality (JS-aware), and DuckDuckGo HTML as the keyless fallback with no signup needed. Fetch + navigate — fetches top hits, then follows promising in-page links within a fixed budget (8 pages, 2 hops) when the answer looks like it is one click deeper. Extract — structure-aware parsing: JSON-LD (Product, Organization, FAQPage), HTML tables such as spec sheets, intent-specific patterns for prices, phone numbers, emails, hours and dates, plus ranked text spans. Verify — every candidate is checked against its own source text; independent multi-source agreement boosts confidence. If nothing is supported by evidence, the agent refuses instead of guessing. The core pipeline uses no LLM, so results are reproducible and cheap. Citations are mandatory, and the agent runs on the free tier with no paid APIs. MIT licensed and Docker-ready, with 12 unit tests.