Creating and Managing Knowledge Stores

Understanding the Knowledge Store Interface

Navigate to Management > Semantic Search >Knowledge Stores, and you will see a table of your existing Knowledge Stores. If you have not made a Knowledge Store yet, you will still see Knowledge Stores with the type System. These are automatically derived from your existing data. The rest of the details contained in the table are as follows:

Creating a Knowledge Store

1. Click the Management icon in the application menu.

2. Under Semantic Search, click Knowledge Store.

3. Click + New Store in the top right corner.

4. Provide the following information on the Create Knowledge Store screen. Complete the following information:

   Knowledge Store Name

   Required— The unique name used to identify this Knowledge Store. It should be descriptive and concise.

   Knowledge Store Type

   Required—The type of Knowledge Store. SQL Based (Collection) or Document Based (Document Collection).

   Enabled

   Optional— Selecting this checkbox indicates that this Knowledge Store is active and available for users.

   User Roles

   Optional— Select one or more roles allowed to interact with this Knowledge Store.

   Description

   Optional—Describe the contents and topics of the Knowledge Store. Clear descriptions help the Assistant identify when the Knowledge Store is relevant and what information to use. A clearer and more detailed description will help Assistants use this Knowledge Store effectively.

   Embedding Model

   Required—The embedding model used for processing and storing data in this Knowledge Store. Choose an embedding model based on your retrieval needs:

   • text-embedding-3-small – Best for general vector search at scale. Faster and lower cost, with slightly lower precision.

   • text-embedding-3-large – Use for complex or high-stakes retrieval where meaning is subtle or requires inference. Higher accuracy and greater resource requirements.

   • text-embedding-ada-002 – Legacy option. Use only for backward compatibility with existing Ada embeddings.

   Tokenization Library

   Required— Specifies the library used for tokenizing text data in this Knowledge Store.

   Chunk Size

   Required— The size of data chunks for processing. Larger chunks may improve performance but require more memory.

   Overlap

   Required—The overlap size between consecutive chunks to ensure continuity between adjacent chunks.

5. Once all the fields are completed, click Submit. The new Knowledge Store will appear on your Knowledge Store table.

The next step in this process is to Add Data to Your Knowledge Store.

Editing a Knowledge Store

1. Click the Management icon in the application menu.

2. Under Semantic Search, click Knowledge Store.

3. Click the Edit menu . A drop-down menu appears.

4. Click Edit Store.

5. Modify the fields you would like to change.

6. Click Submit.

Changes take effect for future data processing. Existing indexed data may need to be reprocessed depending on the fields modified.

Delete a Knowledge Store

You can delete a Knowledge store with the type Document Collection or Collection. System Knowledge Stores cannot be deleted. To do so:

1. Click the Management icon in the application menu.

2. Under Semantic Search, click Knowledge Store.

3. Click the Edit menu . A drop-down menu appears.

4. From the menu, click Delete Store. A confirmation box appears.

5. Click Delete.

Deleted Knowledge Stores cannot be recovered.

Disable or Enable a Knowledge Store

1. Click the Management icon in the application menu.

2. Under Semantic Search, click Knowledge Store.

3. Click the Edit menu. A drop-down menu appears.

4. From the menu, click Disable to disable the Knowledge Store or Enable to re-enable it.