Rerank Search Results Agent

The Rerank Search Results agent uses an LLM to combine one or more lists of search results and reorder them by relevance to the query. It also shortlists the top matches, so you can wire in raw search results from multiple upstream agents without a separate merge step.

Use Cases

Initial search results have good recall but poor ranking (relevant results are buried).
You have results from multiple search agents and want a single, intelligently ranked list.
The query is complex and simple similarity scores do not capture relevance well.

Inputs

Input	Type	Description
`search_results_lists`	List of Search Result Lists	One or more lists of search results to combine and rerank. Typically wired from Knowledge Search or other search agents.
`query`	Text with Sources	The query used to score relevance.

Outputs

Output	Type	Description
`reranked_results`	List of Search Results	The combined, reordered, and shortlisted results. Original result objects are preserved; the agent only changes their order and count.

Configurations

Parameter	Description	Default
`max_results`	Maximum number of results to return after reranking.	10
`user_instructions`	Additional guidance for ranking (e.g., "prefer recent documents").	None
`user_tags`	(Optional) Tags that describe the user or context (for example, `Location:India`). The agent prioritizes results that match these tag values.	None
`model_config`	(Advanced) Overrides the LLM used for reranking via the Model Config widget.	Platform default

How to Use This Agent

chat_trigger -> knowledge_search_1 ----\
 -> knowledge_search_2 -----> rerank_search_results -> respond_using_search_results -> workflow_output

Combine Search Results -- merges result lists without reranking, when original order should be preserved.
Knowledge Search -- the primary source of results to rerank.
Respond using Search Results -- the typical downstream consumer.

Last updated: Jul 3, 2026