Sort
Rerank
Rerank documents using cross-encoder models for accurate relevance
Note: This playground provides simulated output to showcase functionality. No data is processed on our servers. Use this demo to explore the stage's configuration options before integrating it into your retriever pipeline.
Configuration
string
Reranking inference service name.
string
Query text template to compare against documents.
string
Document field containing text to rerank against.
integer | null
Number of top documents to keep after reranking. Null returns all.
string
Field path to store reranking scores.
integer
Batch size for reranking inference calls.
Output
No output yet
Configure the stage parameters and click "Run Stage" to see the simulated output.
Related to rerank
Pages on the same stages, extractors and patterns.
Retriever
Sort Relevance
Sort documents by relevance score
Learn more
Retriever
Sort Attribute
Sort documents by any metadata field value
Learn more
Retriever
Mmr
Reorder results using Maximal Marginal Relevance for diversity
Learn more
Retriever
Score Normalize
Rescale document scores to a common range for consistent comparison
Learn more