anno-cli 0.8.0

CLI for anno: extract entities, coreference chains, relations, and PII from text, HTML, and URLs
{
  "description": "Expected entity counts and key entities per fixture document. Used by regression tests.",
  "note": "Counts are approximate minimums (model may find more). Key entities must appear.",
  "documents": {
    "news": {
      "min_entities": 5,
      "must_find_PER": ["Jerome Powell", "Janet Yellen"],
      "must_find_LOC": ["New York"],
      "must_find_ORG": ["Federal Reserve"]
    },
    "biotech": {
      "min_entities": 5,
      "must_find_PER": ["Stephane Bancel", "Anthony Fauci"],
      "must_find_LOC": ["United States"],
      "must_find_ORG": ["Moderna", "Pfizer"]
    },
    "geopolitics": {
      "min_entities": 8,
      "must_find_PER": ["Josep Borrell", "Jens Stoltenberg", "Rustem Umerov"],
      "must_find_LOC": ["Brussels", "Russia"],
      "must_find_ORG": ["European Union", "NATO"]
    },
    "tech": {
      "min_entities": 8,
      "must_find_PER": ["Jensen Huang"],
      "must_find_ORG": ["NVIDIA", "Microsoft", "Google"]
    },
    "legal": {
      "min_entities": 6,
      "must_find_PER": ["Merrick Garland"],
      "must_find_ORG": ["Google", "Apple", "Department of Justice"]
    },
    "science": {
      "min_entities": 5,
      "must_find_PER": ["Kaiming He", "Ashish Vaswani"],
      "must_find_ORG": ["Microsoft Research", "Google Brain"]
    },
    "sports": {
      "min_entities": 6,
      "must_find_PER": ["Robert Lewandowski", "Lamine Yamal"],
      "must_find_ORG": ["Barcelona", "Real Madrid"]
    },
    "international": {
      "min_entities": 6,
      "must_find_PER": ["Fumio Kishida", "Morris Chang"],
      "must_find_LOC": ["Seoul", "Taipei"]
    },
    "press_release": {
      "min_entities": 4,
      "must_find_PER": ["Bill Nelson"],
      "must_find_ORG": ["NASA"],
      "must_not_contain": ["Home", "About", "Copyright"]
    }
  }
}