---
title: Create and manage Semantic Encoder (SE) models
slug: nb890247
canonical_url: https://docs.coveo.com/en/nb890247/
collection: leverage-machine-learning
source_format: adoc
---
# Create and manage Semantic Encoder (SE) models

> **Important**
>
> * A [Semantic Encoder (SE)](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/) is only supported for use as part of a [Relevance Generative Answering (RGA)](https://docs.coveo.com/en/n9de0370/) or [Passage Retrieval (CPR)](https://docs.coveo.com/en/oaie5277/) implementation.
> 
> * The [Semantic Encoder (SE)](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/) is available as a paid product extension.
> Contact [Coveo Sales](https://www.coveo.com/en/contact) or your Account Manager to add SE to your [organization](https://docs.coveo.com/en/185/) license.

A [Coveo Machine Learning (Coveo ML)](https://docs.coveo.com/en/188/) [Semantic Encoder (SE)](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/) retrieves items from your index based on semantic similarity with the query.

## What does an SE model do?

When an [SE](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/) builds, it creates [embeddings](https://docs.coveo.com/en/n9de0370#embeddings) for the indexed items specified in the model settings and stores the embeddings in the index.

> **Note**
>
> The model is preconfigured to rebuild and update the embeddings weekly based on when the model is created.
> Contact your Coveo Account Manager if a different build interval is required.

> **Tip**
>
> By default, content retrieval is supported only for English content.
> However, Coveo offers beta support for content retrieval in languages other than English.
> Learn more about [multilingual content retrieval and answer generation](https://docs.coveo.com/en/p5ne0024/).

![Semantic Encoder model embeddings | Coveo](https://docs.coveo.com/en/assets/images/leverage-machine-learning/ses-embeddings.png)

An [SE](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/) uses a pre-trained sentence transformer language model to create the [embeddings](https://docs.coveo.com/en/ncc87383/).
The language model does this by capturing relationships between words, phrases, and sentences in the dataset.

An [SE](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/) creates embeddings only for the content in an [item](https://docs.coveo.com/en/210/)'s title and body.
That is, the item's content that's mapped to the `title` and `body` fields in the Coveo index.
For more information, see [How SE uses your content](https://docs.coveo.com/en/nbo90598#how-se-uses-your-content).

> **Note**
>
> The [SE](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/) uses only the content in an item's `body` and `title` fields.
> Content in other searchable fields, such as `author`, `source`, and `date`, isn't embedded by the [model](https://docs.coveo.com/en/1012/) and therefore isn't considered for vector-based content retrieval.

As shown in the following diagram, the model uses a [chunking strategy](https://docs.coveo.com/en/n9de0370#chunking) to create the embeddings.
This means that instead of creating a [vector](https://docs.coveo.com/en/nccf9008/) for each individual word, a [vector](https://docs.coveo.com/en/nccf9008/) is created for a segment of text (chunk) to increase relevance.

![Vector space | Coveo](https://docs.coveo.com/en/assets/images/leverage-machine-learning/ses-chunk-example.png)

When a user enters a query in a Coveo-powered search interface or an LLM-powered application that uses an [SE](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/), the query passes through a [query pipeline](https://docs.coveo.com/en/180/) where pipeline rules and machine learning are applied to optimize relevance.
However, the [SE](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/) adds [vector](https://docs.coveo.com/en/nccf9008/) search capabilities to the search engine.
As shown in the following diagram, the [SE](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/) embeds the query in the embedding vector space in the index to find items with high semantic similarity with the query.
The search results include items that are based on both semantic and lexical similarity.

![Vector space query | Coveo](https://docs.coveo.com/en/assets/images/leverage-machine-learning/grouped-se.png)

In the context of generating an answer using [Relevance Generative Answering (RGA)](https://docs.coveo.com/en/n9de0370/), or retrieving passages using [Passage Retrieval (CPR)](https://docs.coveo.com/en/oaie5277/), the SE model ensures that the [RGA](https://docs.coveo.com/en/nbtb6010/) or [CPR](https://docs.coveo.com/en/oaie9196/) model retrieves segments of text only from the most relevant items in the index.
For more information on how an SE model works with [RGA](https://docs.coveo.com/en/nbtb6010/) or [CPR](https://docs.coveo.com/en/oaie9196/) during content retrieval, see [RGA overview](https://docs.coveo.com/en/n9de0370#rga-overview) or [CPR overview](https://docs.coveo.com/en/oaie5277/).

> **Note**
>
> The embeddings created by the [SE](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/) aren't impacted by [Coveo Analytics events](https://docs.coveo.com/en/260/).

## Prerequisites

* You have the [required privileges](https://docs.coveo.com/en/nb6a0085#required-privileges) to create an SE model.

* The content that you want to use for the model respects the [item requirements](https://docs.coveo.com/en/nbo90598#requirements) and is [optimized](https://docs.coveo.com/en/nbo90598#best-practices).

> **Note**
>
> When an [SE](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/) is used in a [Relevance Generative Answering (RGA)](https://docs.coveo.com/en/n9de0370/) or [Passage Retrieval (CPR)](https://docs.coveo.com/en/oaie5277/) implementation, the same [SE](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/) can be used with multiple [RGA](https://docs.coveo.com/en/nbtb6010/) or [CPR](https://docs.coveo.com/en/oaie9196/) models.
> The [RGA](https://docs.coveo.com/en/nbtb6010/) and [CPR](https://docs.coveo.com/en/oaie9196/) models must be configured to use the same content as the [SE](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/).
> 
> See [RGA overview](https://docs.coveo.com/en/n9de0370#rga-overview) or [CPR overview](https://docs.coveo.com/en/oaie5277#cpr-overview) for information on how SE works with RGA or CPR in the context of a search session.

> **Important**
>
> Keep the [model embedding limits](#model-embedding-limits) in mind when choosing the content for your model.

## Create an SE model

. On the [**Models**](https://platform.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) ([platform-ca](https://platform-ca.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) | [platform-eu](https://platform-eu.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) | [platform-au](https://platform-au.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/)) page of the [Coveo Administration Console](https://docs.coveo.com/en/183/), click **Add model**, and then click the **Semantic Encoder** card.

. Click **Next**.

. In the **Learn from** section, select the content that the model will use.
You can select the sources and apply additional filters using the **Standard** configuration, or use **Advanced** mode to define a custom filter expression.

> **Important**
>
> You'll lose the current mode settings when you switch between **Standard** and **Advanced** mode.

> **Note**
>
> When an [SE](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/) is used in a [Relevance Generative Answering (RGA)](https://docs.coveo.com/en/n9de0370/) or [Passage Retrieval (CPR)](https://docs.coveo.com/en/oaie5277/) implementation, the same [SE](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/) can be used with multiple [RGA](https://docs.coveo.com/en/nbtb6010/) or [CPR](https://docs.coveo.com/en/oaie9196/) models.
> The [RGA](https://docs.coveo.com/en/nbtb6010/) and [CPR](https://docs.coveo.com/en/oaie9196/) models must be configured to use the same content as the [SE](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/).
> 
> See [RGA overview](https://docs.coveo.com/en/n9de0370#rga-overview) or [CPR overview](https://docs.coveo.com/en/oaie5277#cpr-overview) for information on how SE works with RGA or CPR in the context of a search session.

> **Tip**
>
> The **Data volume preview** section shows the impact of your settings on the data that's available to the model.

** In the **Standard** tab:

.. In the **Sources** dropdown menu, select the [sources](https://docs.coveo.com/en/246/) that contain the [items](https://docs.coveo.com/en/210/) from which you want the model to learn.

--
> **Note**
>
> If your Coveo organization includes [multiple indexes](https://docs.coveo.com/en/2877/), the model can learn only from sources that are linked to the default index.
--

.. (Optional) In the **Apply filters on dataset** section, you can specify a condition to segment the content on which the model should base its training.

**Example**

You want the model to base its training only on items for which the **collection** [field](https://docs.coveo.com/en/200/) have the `FAQ` value.

Therefore, you add a `collection is equal to FAQ` condition.

... Click **Add filter(s)**.

... In the **Field name** input, enter the name of the [field](https://docs.coveo.com/en/200/) that you want to use to segment the dataset.

... In the **Select an operator** dropdown menu, select the desired operator.

... In the **Value** input, enter the value of the field on which you want to segment the dataset.

... Click **Apply**.

** In the **Advanced** tab:

.. Enter a custom filter expression using [Coveo query syntax](https://docs.coveo.com/en/1552/).

.. Click **Apply**.

. Click **Next**.

. In the **Name your model** input, enter a meaningful display name for the model.

. (Optional) Use the **Project** selector to associate your model with one or more [projects](https://docs.coveo.com/en/n7ef0517/).

. Click **Start building**.

. [Associate the model with a pipeline](https://docs.coveo.com/en/nb8b0088/) to use the [model](https://docs.coveo.com/en/1012/) in a search interface.

## Manage an SE model

You can [edit](#edit-an-se-model), [delete](#delete-an-se-model), or [review information](#review-model-information) for your [model](https://docs.coveo.com/en/1012/).

### Edit an SE model

. On the [**Models**](https://platform.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) ([platform-ca](https://platform-ca.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) | [platform-eu](https://platform-eu.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) | [platform-au](https://platform-au.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/)) page, click the model you want to edit, and then click **Edit** in the Action bar.

. On the subpage that opens, select the **Configuration** tab.

. Under **Name**, edit the model's display name.

. (Optional) Use the **Project** selector to associate your model with one or more [projects](https://docs.coveo.com/en/n7ef0517/).

. In the **Learn from** section, select the content that the model will use.
You can select the sources and apply additional filters using the **Standard** configuration or use **Advanced** mode to define a custom filter expression.

> **Important**
>
> You'll lose the current mode settings when you switch between **Standard** and **Advanced** mode.

> **Note**
>
> When an [SE](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/) is used in a [Relevance Generative Answering (RGA)](https://docs.coveo.com/en/n9de0370/) or [Passage Retrieval (CPR)](https://docs.coveo.com/en/oaie5277/) implementation, the same [SE](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/) can be used with multiple [RGA](https://docs.coveo.com/en/nbtb6010/) or [CPR](https://docs.coveo.com/en/oaie9196/) models.
> The [RGA](https://docs.coveo.com/en/nbtb6010/) and [CPR](https://docs.coveo.com/en/oaie9196/) models must be configured to use the same content as the [SE](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/).
> 
> See [RGA overview](https://docs.coveo.com/en/n9de0370#rga-overview) or [CPR overview](https://docs.coveo.com/en/oaie5277#cpr-overview) for information on how SE works with RGA or CPR in the context of a search session.

> **Tip**
>
> The **Data volume preview** section shows the impact of your settings on the data that's available to the model.

** In the **Standard** tab:

.. In the **Sources** dropdown menu, select the [sources](https://docs.coveo.com/en/246/) that contain the [items](https://docs.coveo.com/en/210/) from which you want the model to learn.

--
> **Note**
>
> If your Coveo organization includes [multiple indexes](https://docs.coveo.com/en/2877/), the model can learn only from sources that are linked to the default index.
--

.. (Optional) In the **Apply filters on dataset** section, you can specify a condition to segment the content on which the model should base its training.

**Example**

You want the model to base its training only on items for which the **collection** [field](https://docs.coveo.com/en/200/) have the `FAQ` value.

Therefore, you add a `collection is equal to FAQ` condition.

... Click **Add filter(s)**.

... In the **Field name** input, enter the name of the [field](https://docs.coveo.com/en/200/) that you want to use to segment the dataset.

... In the **Select an operator** dropdown menu, select the desired operator.

... In the **Value** input, enter the value of the field on which you want to segment the dataset.

... Click **Apply**.

** In the **Advanced** tab:

.. Enter a custom filter expression using [Coveo query syntax](https://docs.coveo.com/en/1552/).

.. Click **Apply**.

. Click **Save**.

> **Note**
>
> Some configuration changes initiate an automatic model rebuild when you save the model.
> The [**Models**](https://platform.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) ([platform-ca](https://platform-ca.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) | [platform-eu](https://platform-eu.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) | [platform-au](https://platform-au.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/)) page shows your model's current **Status**.
> Model settings take effect only when its status is **Active**.
> 
> For more information on Coveo ML model statuses, see the [**Status** column reference](#status-column).

### Delete an SE model

> **Note**
>
> If the model is associated with a query pipeline, make sure to dissociate the model from the query pipeline after deleting it.

. On the [**Models**](https://platform.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) ([platform-ca](https://platform-ca.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) | [platform-eu](https://platform-eu.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) | [platform-au](https://platform-au.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/)) page, click the ML model that you want to delete, and then click **More** > **Delete** in the Action bar.

. In the panel that appears, click **Delete**.

### Review model information

On the [**Models**](https://platform.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) ([platform-ca](https://platform-ca.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) | [platform-eu](https://platform-eu.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) | [platform-au](https://platform-au.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/)) page, click the desired model, and then click **View** in the Action bar.
For more information, see [Reviewing model information](https://docs.coveo.com/en/1894/).

## Model embedding limits

The [SE](https://docs.coveo.com/en/nbtb0041/) [model](https://docs.coveo.com/en/1012/) converts your content's title and body text into numerical representations ([vectors](https://docs.coveo.com/en/nccf9008/)) in a process called [embedding](https://docs.coveo.com/en/ncc87383/).
It does this by breaking the text up into smaller segments called chunks, and each chunk is mapped as a distinct vector.
For more information, see [Embeddings](https://docs.coveo.com/en/n9de0370#embeddings).

The model is subject to the following embedding limits based on the selected [chunking strategy](https://docs.coveo.com/en/oaie5476#set-the-chunking-strategy):

> **Note**
>
> For a given [model](https://docs.coveo.com/en/1012/), the same chunking strategy is used for all sources and item types.

* Up to 15 million items or 50 million chunks

> **Note**
>
> The maximum number of items depends on the [item allocation of your product plan](https://docs.coveo.com/en/l2590456#generative-ai-solutions).

* 11 chunks per item

> **Important**
>
> This limit is sufficient for the SE [model](https://docs.coveo.com/en/1012/) to capture an item's main concepts.
> If an item is long with a lot of text, however, such as more than 4000 words or 5 pages, the [model](https://docs.coveo.com/en/1012/) will embed the item's text until the 11-chunk limit is reached.
> The remaining text won't be embedded and therefore won't be used by the [model](https://docs.coveo.com/en/1012/).
> 
> To make sure that each item's text is fully embedded, follow [best practices](https://docs.coveo.com/en/nbo90598#best-practices) by keeping items concise and focused.

* 500 words per chunk

> **Note**
>
> There can be an overlap of up to 20% between chunks.
> In other words, the last 20% of the previous chunk can be the first 20% of the next chunk.

## "Status" column

On the [**Models**](https://platform.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) ([platform-ca](https://platform-ca.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) | [platform-eu](https://platform-eu.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) | [platform-au](https://platform-au.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/)) page of the [Administration Console](https://docs.coveo.com/en/183/), the **Status** column indicates the current state of your Coveo ML models.

The following table lists the possible model statuses and their definitions:

[%header,cols="1,6,^.^1"]
|===
.^|Status
.^|Definition
|Status icon

|Active
|The model is active and available.
a|![Active](leverage-machine-learning/model-active.png)

|Build in progress
|The model is currently building.
a|![Building](leverage-machine-learning/model-build.png)

|Inactive
|The model isn't ready to be queried, such as when a model was recently created or the organization is offline.  
Click **See more details** for additional information (see [Review model information](https://docs.coveo.com/en/1894/)).
a|![Inactive](leverage-machine-learning/model-limited.png)

|Limited
|Build issues exist that may affect model performance.  
Click **See more details** for additional information (see [Review model information](https://docs.coveo.com/en/1894/)).
a|![Limited](leverage-machine-learning/model-limited.png)

|Soon to be archived
|The model will soon be archived because it hasn't been queried for an extended period of time.  
Click **Delete** to remove the model.  
[Learn more about archived models](https://docs.coveo.com/en/mb3e0324/).
a|![Archive pending](leverage-machine-learning/model-limited.png)

|Error
|An error prevented the model from being built successfully.  
If it's a temporary system error, check back soon.
Otherwise, click **See more details** for additional information (see [Review model information](https://docs.coveo.com/en/1894/)).
a|![Error](leverage-machine-learning/model-error.png)

|Archived
|The model was archived because it hasn't been queried for an extended period of time.  
Click **Delete** to remove the model.  
[Learn more about archived models](https://docs.coveo.com/en/mb3e0324/).
a|![Archived](leverage-machine-learning/model-archived.png)
|===

## Required privileges

By default, members with the [required privileges](https://docs.coveo.com/en/1832#required-privileges) can view and edit elements of the [**Models**](https://platform.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) ([platform-ca](https://platform-ca.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) | [platform-eu](https://platform-eu.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/) | [platform-au](https://platform-au.cloud.coveo.com/admin/#/orgid/ai-and-ml/models/)) page.

The following table indicates the privileges required for members to manage Coveo Generic models (see [Manage privileges](https://docs.coveo.com/en/3151/) and [Privilege reference](https://docs.coveo.com/en/1707/)).

[cols="3",options="header"]
|===
|Action
|Service - Domain
|Required access level

|View models
|Machine Learning - Models  
Organization - Organization  
Search - Query pipelines
|View

.5+|Manage models
|Organization - Organization  
Search - Query pipelines
|View

|Machine Learning - Models
|Edit

|Machine Learning - Allow content preview
|Enable

|Content - Sources
|View All

|Content - Fields
|View
|===

## What's next?

[Associate the SE model with a query pipeline](https://docs.coveo.com/en/nb8b0088/).