如何部署自然语言处理 (NLP)：命名实体识别 (NER) 示例

git clone git@github.com:elastic/eland.git
cd eland
docker build -t elastic/eland .

Copy

docker run -it --rm elastic/eland \
    eland_import_hub_model \
      --url $ELASTICSEARCH_URL \
      --hub-model-id elastic/distilbert-base-uncased-finetuned-conll03-english \
      --task-type ner \
      --start

Copy

POST _ml/trained_models/elastic__distilbert-base-uncased-finetuned-conll03-english/deployment/_infer
{
  "docs": [
    {
      "text_field": "Hi my name is Josh and I live in Berlin"
    }
  ]
}

Copy

{
  "predicted_value" : "Hi my name is [Josh](PER&Josh) and I live in [Berlin](LOC&Berlin)",   
    "entities" :     {
      "entity" : "Josh",
      "class_name" : "PER",
      "class_probability" : 0.9977303419824,
      "start_pos" : 14,
      "end_pos" : 18
    },
    {
      "entity" : "Berlin",
      "class_name" : "LOC",
      "class_probability" : 0.9992474323902818,
      "start_pos" : 33,
      "end_pos" : 39
    }
  ]
}

Copy

PUT _ingest/pipeline/ner
{
  "description": "NER pipeline",
  "processors": [
    {
      "inference": {
        "model_id": "elastic__distilbert-base-uncased-finetuned-conll03-english",
        "target_field": "ml.ner",
        "field_map": {
          "paragraph": "text_field"
        }
      }
    },
    {
      "script": {
        "lang": "painless",
        "if": "return ctx['ml']['ner'].containsKey('entities')",
        "source": "Map tags = new HashMap(); for (item in ctx['ml']['ner']['entities']) { if (!tags.containsKey(item.class_name)) tags[item.class_name] = new HashSet(); tags[item.class_name].add(item.entity);} ctx['tags'] = tags;"
      }
    }
  ],
  "on_failure": [
    {
      "set": {
        "description": "Index document to 'failed-<index>'",
        "field": "_index",
        "value": "failed-{{{ _index }}}"
      }
    },
    {
      "set": {
        "description": "Set error message",
        "field": "ingest.failure",
        "value": "{{_ingest.on_failure_message}}"
      }
    }
  ]
}

Copy

{
    "paragraph": "Father Gillenormand did not do it intentionally, but inattention to proper names was an aristocratic habit of his.",
    "line": 12700
}

Copy

{
    "paragraph": "Father Gillenormand did not do it intentionally, but inattention to proper names was an aristocratic habit of his.",
    "@timestamp": "2020-01-01T17:38:25",
    "line": 12700,
    "ml": {
        "ner": {
            "predicted_value": "Father [Gillenormand](PER&Gillenormand) did not do it intentionally, but inattention to proper names was an aristocratic habit of his.",
            "entities": [{
                "entity": "Gillenormand",
                "class_name": "PER",
                "class_probability": 0.9806354093873283,
                "start_pos": 7,
                "end_pos": 19
            }],
            "model_id": "elastic__distilbert-base-cased-finetuned-conll03-english"
        }
    },
    "tags": {
        "PER": [
            "Gillenormand"
        ]
    }
}

Copy

POST _ml/trained_models/elastic__distilbert-base-uncased-finetuned-conll03-english/deployment/_stop?force=true

Copy

POST _ml/trained_models/elastic__distilbert-base-uncased-finetuned-conll03-english/deployment/_start?inference_threads=4

Copy