Text

Late Interaction Ranker

Ranks a list of documents against a query using late interaction models (e.g., ColBERT). Produces relevance scores.

0K 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

# model_name string

Required

The late interaction model architecture to use (e.g., ColBERT, ColPaLi, ColNomic).. Default: colbert-base

# query_text string

Required

The input query text for ranking.. Default: undefined

# candidate_documents array

Required

An array of candidate documents to be ranked. Each document object should have an 'id' (string) and 'text' (string) field.. Default: undefined

# top_k integer

Number of top documents to return from the ranked list.. Default: 10

# batch_size integer

Batch size for processing documents during ranking.. Default: 32

Output

{
  "ranked_results": [
    {
      "document_id": "doc_xyz",
      "score": 0.975,
      "rank": 1
    },
    {
      "document_id": "doc_abc",
      "score": 0.89,
      "rank": 2
    }
  ],
  "model_used": "colbert-base",
  "query_tokens": 23,
  "documents_ranked": 150,
  "processing_time_ms": 1200
}