From 3bc12cdc57cd91d98b102d479df650e4779dc146 Mon Sep 17 00:00:00 2001 From: Jeffrey Sperling Date: Mon, 13 Apr 2026 11:52:55 -0700 Subject: [PATCH] feat: add eval_topics.json fixture for offline quality evaluation evaluate_search_quality.py and e2e_comparison.py both reference fixtures/eval_topics.json with hardcoded fallbacks. Supply the actual fixture: 8 topics spanning all intent types, selected via MMR dispersion across domains (tech, health, sports, finance, consumer products). --- fixtures/eval_topics.json | 42 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) create mode 100644 fixtures/eval_topics.json diff --git a/fixtures/eval_topics.json b/fixtures/eval_topics.json new file mode 100644 index 0000000..c98fb4f --- /dev/null +++ b/fixtures/eval_topics.json @@ -0,0 +1,42 @@ +[ + { + "topic": "OpenClaw vs NanoClaw vs ZeroClaw", + "query_type": "comparison", + "rationale": "Multi-entity extraction, 3-way split across AI agent frameworks." + }, + { + "topic": "how to set up a GLP-1 supplement routine", + "query_type": "how_to", + "rationale": "Trending health topic. Tests non-tech how_to." + }, + { + "topic": "2026 March Madness", + "query_type": "breaking_news", + "rationale": "Live sporting event. Tests broad breaking news recall." + }, + { + "topic": "best budget noise cancelling headphones 2026", + "query_type": "product", + "rationale": "Evergreen consumer query. Tests product review aggregation." + }, + { + "topic": "thoughts on OpenAI Codex pricing", + "query_type": "opinion", + "rationale": "Active developer debate. Tests opinion mining." + }, + { + "topic": "odds of US recession 2026", + "query_type": "prediction", + "rationale": "Major macro topic. Tests prediction market + news synthesis." + }, + { + "topic": "what is retrieval augmented generation", + "query_type": "concept", + "rationale": "Widely discussed AI concept. Tests explanation quality." + }, + { + "topic": "Google Wiz acquisition price and timeline", + "query_type": "factual", + "rationale": "Completed event ($32B). Tests factual precision." + } +]