Text

Topic Modeling

Discover abstract topics and themes across document collections

490K 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

# num_topics integer

Number of topics to extract. Default: 10

# method string

Topic modeling method to use. Default: LDA

# min_topic_weight number

Minimum weight for topic inclusion. Default: 0.1

Output

{
  "topics": [
    {
      "id": 0,
      "words": [
        "finance",
        "market",
        "stocks",
        "trading"
      ],
      "weight": 0.25,
      "coherence_score": 0.78,
      "representative_docs": [
        "doc1",
        "doc2"
      ]
    },
    {
      "id": 1,
      "words": [
        "health",
        "medical",
        "patient",
        "treatment"
      ],
      "weight": 0.18,
      "coherence_score": 0.82,
      "representative_docs": [
        "doc3",
        "doc4"
      ]
    }
  ],
  "method": "LDA",
  "num_topics": 10,
  "perplexity": 45.2,
  "topic_diversity": 0.85
}

Ready to run Topic Modeling 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 →