Tags

Semantic tags are ranked entities, keywords, or concepts that are relevant to the content of the text.

See the Tag object reference for more details.

Sample Call

You can easily try it yourself:

cURL

curl -X POST https://api.geneea.com/v3/analysis \
-H 'Authorization: user_key <YOUR USER KEY>' \
-H 'Content-Type: application/json' \
-d '{
    "id": "1",
    "text": "The trip to London was great. Only the food was weird. Especially the pizza was terrible.",
    "analyses": ["tags"],
    "domain": "voc-hospitality"
}'

## On Windows, use \" instead of " and " instead of '

Python SDK

from geneeanlpclient import g3

requestBuilder = g3.Request.Builder(analyses=[g3.AnalysisType.TAGS])

with g3.Client.create(userKey=<YOUR USER KEY>) as analyzer:
    result = analyzer.analyze(requestBuilder.build(
        id=str(1),
        text='The trip to London was great. Only the food was weird. Especially the pizza was terrible.'
    ))

    for t in result.tags:
        print(f'{t.stdForm},  gkbId: {t.gkbId}, type: {t.type} relevance: {t.relevance}')

plain Python

import requests

def callGeneea(input):
    url = 'https://api.geneea.com/v3/analysis'
    headers = {
        'content-type': 'application/json',
        'Authorization': 'user_key <your user key>'
    }

    return requests.post(url, json=input, headers=headers).json()

responseObj = callGeneea({
    'id': '1',
    'text': 'The trip to London was great. Only the food was weird. Especially the pizza was terrible.',
    'analyses': ['tags'],
    'domain': 'voc-hospitality'
})

print(responseObj)

Sample Response

cURL

{
    "version": "3.2.1",
    "id": "1",
    "language": {"detected": "en"},
    "tags": [
        {"id": "t0", "stdForm": "food & drink > quality", "type": "TOPIC", "relevance": 10.534},
        {"id": "t1", "stdForm": "food & drink", "type": "TOPIC", "relevance": 10.422},
        {"id": "t2", "gkbId": "HSP-10210", "stdForm": "food", "type": "ENTITIES", "relevance": 6.5},
        {"id": "t3", "gkbId": "HSP-1091", "stdForm": "pizza", "type": "ENTITIES", "relevance": 6.5},
        {"id": "t4", "stdForm": "food: weird", "type": "RELATIONS", "relevance": 3.0},
        {"id": "t5", "stdForm": "pizza: terrible", "type": "RELATIONS", "relevance": 3.0},
        {"id": "t6", "stdForm": "trip: great", "type": "RELATIONS", "relevance": 3.0}
    ],
    "usedChars": 100
}

Python SDK

food & drink > quality,  gkbId: None, type: TOPIC relevance: 10.534
food & drink,  gkbId: None, type: TOPIC relevance: 10.422
food,  gkbId: HSP-10210, type: ENTITIES relevance: 6.5
pizza,  gkbId: HSP-1091, type: ENTITIES relevance: 6.5
food: weird,  gkbId: None, type: RELATIONS relevance: 3.0
pizza: terrible,  gkbId: None, type: RELATIONS relevance: 3.0
trip: great,  gkbId: None, type: RELATIONS relevance: 3.0

plain Python

{
    "version": "3.2.1",
    "id": "1",
    "language": {"detected": "en"},
    "tags": [
        {"id": "t0", "stdForm": "food & drink > quality", "type": "TOPIC", "relevance": 10.534},
        {"id": "t1", "stdForm": "food & drink", "type": "TOPIC", "relevance": 10.422},
        {"id": "t2", "gkbId": "HSP-10210", "stdForm": "food", "type": "ENTITIES", "relevance": 6.5},
        {"id": "t3", "gkbId": "HSP-1091", "stdForm": "pizza", "type": "ENTITIES", "relevance": 6.5},
        {"id": "t4", "stdForm": "food: weird", "type": "RELATIONS", "relevance": 3.0},
        {"id": "t5", "stdForm": "pizza: terrible", "type": "RELATIONS", "relevance": 3.0},
        {"id": "t6", "stdForm": "trip: great", "type": "RELATIONS", "relevance": 3.0}
    ],
    "usedChars": 100
}

Mentions

You can use "returnMentions": "true" to include tag mentions in the response.