{
  "id": "labeling",
  "type": "cluster_labeling",
  "modelId": "cluster_labeling_v1",
  "dataFormat": "solr",
  "trainingCollection": "searchhub_out",
  "fieldToVectorize": "body",
  "trainingDataFilterQuery": "*:*",
  "trainingDataSamplingPercentage": "1.0",
  "sourceFields": "",
  "analyzerConfig": "{
         \"analyzers\": [ { \"name\": \"StdTokLowerStop\",
               \"charFilters\": [ { \"type\": \"htmlstrip\" } ],
               \"tokenizer\": { \"type\": \"letter\" },
               \"filters\": [ 
                     { \"type\": \"lowercase\" },  
                     { \"type\": \"length\", \"min\": \"3\", \"max\": \"32767\" },
                     { \"type\": \"stop\", \"ignoreCase\": \"true\", \"format\": \"snowball\", \"words\": \"org/apache/lucene/analysis/snowball/english_stop.txt\" },
                     { \"type\": \"englishminimalstem\" }] }],
         \"fields\": [{ \"regex\": \".+\", \"analyzer\": \"StdTokLowerStop\" } ]}",
  "clusterIdField": "cluster_id",
  "clusterLabelField": "cluster_labeling",
  "freqTermField": "freq_terms_labeing",
  "outputCollection": "labeling_output",
  "minDF": "5.0",
  "maxDF": "0.75",
  "numKeywordsPerLabel": "5"
}