Text

Keyword Extraction

Identify and extract key phrases and important terms from text

615K runs

Note: This playground provides simulated output to showcase functionality. No input data is processed or stored on our servers. Use this demo to explore the feature extractor's capabilities before integrating it into your application.

Input

Text Input string

Enter the text you want to process

# min_score number

Minimum score threshold for keywords. Default: 0.7

# max_keywords integer

Maximum number of keywords to extract. Default: 10

# ngram_range array

Range of n-grams to consider. Default: 1,3

# include_positions boolean

Whether to include keyword positions. Default: true

Output

{
  "keywords": [
    {
      "text": "artificial intelligence",
      "score": 0.89,
      "count": 7,
      "positions": [
        45,
        89,
        120
      ],
      "context": "The field of artificial intelligence has seen rapid growth"
    },
    {
      "text": "machine learning",
      "score": 0.82,
      "count": 5,
      "positions": [
        67,
        134
      ],
      "context": "Machine learning algorithms are becoming more sophisticated"
    },
    {
      "text": "neural networks",
      "score": 0.77,
      "count": 4,
      "positions": [
        92,
        156
      ],
      "context": "Deep neural networks have revolutionized the field"
    }
  ],
  "language": "en",
  "min_score": 0.7,
  "max_keywords": 10,
  "ngram_range": [
    1,
    3
  ]
}

Ready to run Keyword Extraction on your data? Spin it up in Studio — no infra to host.

Run this in Studio

Already have embeddings? Skip extraction — search your own vectors with MVS. First 1M vectors free.

Try MVS →