---
sourceDocument: Brazil Enable AI
sourceDocumentLink: https://www.servicenow.com/docs/r/intelligent-experiences

 Release :

    - brazil

ft:locale :

    - en-US

ft:publication_title :

    - Brazil Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Configure retriever chunking and reranking

# Configure retriever chunking and reranking {#ariaid-title1}

Release version: Brazil  
Updated September 10, 2026  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 minute to read  
Configure chunking and reranking for a retriever that uses hybrid or semantic search to control how retrieved content is split, ranked, and passed to the LLM.

## Before you begin

Role required: sn_skill_builder.admin

## About this task

To set up the chunking and reranking options for a retriever, you must have a retriever tool added to your skill with the Hybrid or Semantic search criteria. The following steps
come after the semantic configuration in [Add a retriever](https://www.servicenow.com/docs/XefK5OaYpgXsakJFTqdzTg "Add a retriever to your skill to augment your prompts with relevant context from AI Search results.").

## Procedure

1. Navigate to AllAI Skill KitHome.
2. Select the skill that you're adding a retriever to.
3. [Add a retriever](https://www.servicenow.com/docs/XefK5OaYpgXsakJFTqdzTg "Add a retriever to your skill to augment your prompts with relevant context from AI Search results.").
4. On the form, fill in the fields.  
   {#retriever-chunking__table_zcj_zmc_fdc__entry__2}

   | Field | Description |
   |-|-|
   | Max number of chunks per document | Maximum number of chunks to return per document. The default value is 10. |
   | Chunking strategy | * Fixed size Fixed size breaks down the full text into smaller passages. You can choose the passage size limit in number of words or number of sentences. * Small to big Small to big enables you to choose the top K best-matched indexed chunks and expand them to include surrounding chunks. Then the expanded chunks are linked together into a large text and broken into smaller passages. Don't use the small to big chunking strategy if you're using full text or truncate index chunking configuration. {#retriever-chunking__ul_a2y_x4c_fdc} |
   | Chunking unit | * Words * Sentences {#retriever-chunking__ul_zsb_z4c_fdc} |
   | Chunk size | Size of the returned chunks. The default value for word size is 750. The default value for sentence size is 40. |
   | Expanded snippet size | Size of the expanded chunks included when you select the small to big chunking strategy. |
   | Top K results | Number of chunks that the reranker returns. If this field is empty, the reranker returns the number of results set in the retriever Limit field. |
   [Table 1. Chunking and reranking form]

   {#retriever-chunking__table_zcj_zmc_fdc}
5. Select Next.
6. Select the type of condition to evaluate when the tool runs.
7. Select Next.
8. Review the selections that you made for the tool and select Add tool.

*[\>]: and then