---
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


---

# Add a retriever

# Add a retriever {#ariaid-title1}

Release version: Brazil  
Updated September 23, 2026  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 minute to read  
Add a retriever to your skill to augment your prompts with relevant context from AI Search results.

## Before you begin

Role required: sn_skill_builder.admin

## About this task

Using a retriever in a skill enhances the relevance and coherence of a response by pulling relevant information from a source and then feeding it to a large language model (LLM) to create the final output. This process
doesn't require model fine-tuning.

A retriever enables the chatbot to access external knowledge by fetching relevant background information, resulting in more factual, in-depth, and informed responses.

## Procedure

1. Navigate to AllAI Skill KitHome.
2. Create a skill or select the skill that you want to add a retriever to.
3. Select the Tool editor tab.
4. Select the (+) icon to add a node.
5. Select Tool node.
6. Select Retriever from the drop-down menu.
7. Select Configure retriever.
8. On the form, fill in the fields.  
   {#add-retriever__table_bzy_5jv_ddc__entry__2}

   | Field | Description |
   |-|-|
   | Name | Name of the retriever. |
   | Search query | Information to search for. The value can be static text or a skill input. |
   | Search space type | * Table-based * Search-profile-based {#add-retriever__ul_uvn_pjw_dfc} |
   | Search profile | A group of search sources. |
   | Search sources | Tables in ServiceNow that have been indexed and can be used for search. |
   | Fields returned | Fields to return from the search sources and send to the LLM. |
   | Limit | Maximum number of results to return. |
   | Search criteria | * Hybrid * Semantic * Keyword {#add-retriever__ul_q5z_xdw_2dc} Note: If you choose Hybrid or Semantic, you can make selections for chunking and reranking. To learn more about chunking and reranking, see [Configure retriever chunking and reranking](https://www.servicenow.com/docs/e6C3QCqRWhNTsPt6od_dCQ "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."). |
   [Table 1. Add tool form]

   {#add-retriever__table_bzy_5jv_ddc}
9. Select Next.
10. Select an embedding model.  
    To learn about embedding models, see [Configuring your embedding model](https://www.servicenow.com/docs/access?context=setting-up-3p-embedding-models&version=brazil&pubname=brazil-platform-administration&ft:locale=en-US).
11. If you selected Hybrid or Semantic search criteria, select a semantic index.  
    A semantic index enables you to search for data based on contextual meaning.
12. **Optional:** If you selected Hybrid or Semantic search criteria, select Advanced to change the document matching threshold.  
    The document matching threshold is the threshold for semantic matching. The default value is 0. You can input any value from 0 to 1. You can get more precise results with a higher value.
13. Select Next.  
    Note:  
    If you selected Hybrid or Semantic search criteria, see [Configure retriever chunking and reranking](https://www.servicenow.com/docs/e6C3QCqRWhNTsPt6od_dCQ "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.") to complete setting up your retriever.
14. Review the retriever tool information.
15. Select Add tool.
* **[Configure retriever chunking and reranking](https://www.servicenow.com/docs/e6C3QCqRWhNTsPt6od_dCQ)**   
  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.

*[\>]: and then