---
schema_version: "1"
id: 4edde558fbbaa6d180f5b700b83eeb861b91cf442b3e81a2dca93eed60f3a31d
title: Create an Ensemble Retriever
collection: admin
version: current
locale: en-us
portal_url: https://docs.salesforce.com/admin/current/en-us/data/264-0-0/c360_a_ai_retriever_ensemble_create.md
canonical_url: https://help.salesforce.com/s/articleView?id=data.c360_a_ai_retriever_ensemble_create.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: d8e31ee2f57b1b7998336231a0306b7c031995f0a07da7ba527b9f0599f8c981
description: Use ensemble retrievers to get the most relevant information from multiple searches or data sources. In AI Models (formerly Einstein Studio), an ensemble retriever is a collection of individual retrievers. When you run an ensemble retriever, it runs all the individual retrievers, combines their results into a single list, reranks the list according to relevance to the search request, and returns just the most relevant information to the prompt or agent.
products:
  - Data 360
release: "264"
---
# Create an Ensemble Retriever

Use ensemble retrievers to get the most relevant information from multiple searches or data sources. In AI Models (formerly Einstein Studio), an ensemble retriever is a collection of individual retrievers. When you run an ensemble retriever, it runs all the individual retrievers, combines their results into a single list, reranks the list according to relevance to the search request, and returns just the most relevant information to the prompt or agent.

### Required Editions

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small edition"><colgroup><col></colgroup><tbody><tr class=""><td class="slds-cell-wrap" style="vertical-align:top;">Available in: <strong>All Editions</strong> supported by Data 360. See <a href="https://help.salesforce.com/s/articleView?id=data.c360_a_dc_editions.htm&amp;language=en_US" target="_blank">Data 360 edition availability</a>.</td></tr></tbody></table>

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small permission">
        <colgroup>
          <col style="width:50%">
          <col style="width:50%">
        </colgroup>
        <thead class="slds-text-title_caps ">
          <tr class="">
            <th scope="colgroup" class="slds-cell-wrap" colspan="2" style="text-align:left;vertical-align:top;" id="d108300e61">User Permissions
              Needed</th>
          </tr>
        </thead>
        <tbody>
          <tr class="">
            <td data-label="User Permissions Needed" class="slds-cell-wrap" style="vertical-align:top;" headers="d108300e61 ">To manage retrievers or versions in AI Models (create, edit, and
              delete)</td>

            <td class="slds-cell-wrap" style="vertical-align:top;" headers="d108300e61 ">
              <p>Allow users to manage models in AI Models AND Access to Field Relationship Path
                object</p>
              <p>OR</p>
              <p style="margin-bottom:0;">Data Cloud Architect Permission Set</p>
            </td>

          </tr>
          <tr class="">
            <td data-label="User Permissions Needed" class="slds-cell-wrap" style="vertical-align:top;" headers="d108300e61 ">To access data with retrievers</td>

            <td class="slds-cell-wrap" style="vertical-align:top;" headers="d108300e61 ">
              <p>For the Knowledge object, make sure that the user has read access to the
                Knowledge object and has the App Permission: Allow View Knowledge </p>
              <p style="margin-bottom:0;">For all other
                standard objects, make sure that the user has read access to the object and
                appropriate sharing rules. For more information see, <a href="https://help.salesforce.com/s/articleView?id=platform.admin_sharing.htm&amp;type=5&amp;language=en_US" target="_blank"><u>Set Your Internal Organization-Wide Sharing
                    Defaults</u></a>.</p>
            </td>

          </tr>
        </tbody>
      </table>

1. In AI Models on the Retrievers tab, click **New Retriever**.
2. Select **Ensemble Retriever** as the retriever type. Click **Next**.
3. Select the data space in Data Cloud where the data sources are located for your ensemble retriever. Click **Next**.
4. Select two or more individual retrievers to add to this ensemble retriever. Click **Next**.
    
    - Ensemble retrievers don't support retrievers of type Code.
    - Individual retrievers with dynamic filters can’t be part of an ensemble retriever.
    
    Ensemble retrievers don't support retrievers of type Code.
5. Configure which information to return and how much.
    1. Specify the maximum number of results to return.
    2. Specify one or more fields that ground the prompt. For each field selected, enter a unique, descriptive label for the retrieved information.
    3. Click **Next**.
6. Review your selections.
    1. To change a selection, click the Edit icon.
    2. Save your changes, and specify a retriever name and an optional description.
    3. Save your changes.

When you create an ensemble retriever, AI Models creates the first version. Each time you edit and save an updated retriever, AI Models creates another version.

![Note](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-data-data_cloud-264-0-0-production-enus/f3569962-3c9b-4f83-9d0c-b6a574e785da/images/icon_note.png)

Note The ensemble retriever isn’t available for use in prompt templates until you activate a version.

#### See Also

- [Test an Ensemble Retriever](https://help.salesforce.com/s/articleView?id=data.c360_a_ai_retriever_test_ensemble.htm&release=264.0.0&type=5 "Test an ensemble retriever configuration in the AI Models retriever playground before you use it in prompt templates or AI agents. Add or remove retrievers to an ensemble, configure test data, and result parameters to verify the retrieval logic.")