Data asset configuration is used for the range of data that iDA can retrieve during use and analysis. Users can customize the range of data assets queried by the agent, allowing the agent to better apply it to the current business. This article provides you with configuration guidance for creating data assets that your agent can query when configuring iDA.

The agent supports adding data from the following two sources as its retrievable data assets:

• Add the created data asset as a data source for the agent.
• Add a visualization chart created in Datawind (DataWind) as a data source for the agent. This approach has been supported since version 3.2.0, and you need to combine the DataWind products.

This article describes the activity details for configuring agent data assets based on created data assets; see DataWind for creating data sources based on charts Chart Configuration.

Before configuring the data assets of the agent, you need to create the corresponding data as the data assets of iDA to complete the data preparation operation. For details, please refer to Data Preparation Overview.

Log in to the BytePlus console, select DataAgent, and click Agent Configuration in the corresponding agent list. After entering the agent configuration page, click Data Assets in the left navigation bar, enter the data asset configuration page, and start the configuration of the dataset in the "Datasets" tab.
As of version 3.17, adding a dataset and initializing will enable dataset vectorization by default, see Dataset initialization below.

With this configuration, you can flexibly delineate the data access boundaries of the agent, enhancing the relevance and accuracy of the Q & A results.

1. On the agent list page, select the corresponding agent and click the agent configuration button to enter the agent configuration page.
2. Side navigation Click Data Assets, and click the Add Data Assets button at the top right of the Data Assets list to add data assets.
   
3. The successfully added data asset will be displayed in the list, where you can turn it on, off, or delete it.
   

The semantic model configuration is used to customize the semantic adjustment of the name, field and business meaning of the dataset on the original data source set, which helps the agent to understand the data content and business context more accurately, thereby improving the accuracy of automatic table selection and question answering. Please note when configuring: if an item name or field is not redefined, the original definition of the dataset will be used; and after the semantic model enables fields, new fields in subsequent datasets will not be automatically added, and need to be opened manually as needed.

Configuration key points #

Operation steps #

1. Find the corresponding dataset in the data asset list and click the Operate Column Semantic Model button to enter the Semantic Model Configuration page.

2. Click the Config Model button to add a name, description, and features to the semantic model. Click the OK button when you are done. The relevant parameter configuration instructions are as follows:

   Parameter	Configuration instructions
   Semantic model name	Support user-defined semantic model names. If not specified, they will be synchronized with the dataset name by default.
   Semantic model description	Support users to add descriptions to the semantic model. If not specified, it will be synchronized with the dataset description by default.
   Feature	The feature values of the semantic model are used to define the key characteristics that distinguish the current dataset from other datasets. Users can use commas and carriage returns to separate multiple values. Attention Features affect the priority of the agent surface recall dataset. A single feature is recommended to be no more than 5 characters in length, and the total number of features is recommended to be no more than 10. Feature examples: aaa, bbb, ccc.

   

3. After the above operation is completed, in the semantic model configuration list, click the corresponding field row operation item configuration button to configure the field. The configuration parameters involved in fields of different data types are partially different, and each configuration parameter is described as follows:

   • Date configuration parameter

   Parameter	Configuration instructions
   Field name synonyms	The user can set one or more synonyms for the field name, and when the description of the query is in these synonyms, the agent will preferentially use the field for query. Multiple synonyms are separated by commas or carriage returns.
   Field description	The user can add a description of the agent field to help understand the field, which is consistent with the field description of the dataset when empty.
   Default recall	If "Default Recall" is checked, this field will be passed to the large model as a prompt word each time a question is asked.

   • Text class field-specific configuration parameters

   Parameter	Configuration instructions
   Field value recall	Text class fields turn on the field value recall button by default, you can close it on demand, and the field value will not be recalled after closing.
   Field value blacklist	Field values that do not want to be recalled
   High frequency field value description	For high-frequency text fields, the field meaning range can be configured. The configuration example is as follows.

   • Numerical value class field-specific configuration parameters

   Parameter	Configuration instructions
   Default calculation method	In the drop-down box, select the default calculation method for field values of the numeric class. Current support: sum, count, count differently, mean, maximum, minimum.

4. Enables fields that require the use of a semantic model .
   You can search to open the semantic model configuration content of the required fields in the dataset one by one, or click "Batch Open Status" at the bottom of the field list to open the semantic model configuration of all fields in the dataset.
   

After the data asset is initialized, the vectorization function is enabled by default. If you don't need the current agent to query and use the data asset in the future, you can click "Completed" in the status column, and the page will jump to the initialization configuration page, where you can turn off the vectorization function.
After shutdown, the configuration of the data asset is preserved, but subsequent use of the agent will no longer query and use the data in the corresponding data asset.

Support for deleting datasets that have been added. Find the operation column of the corresponding dataset in the data asset list, and click the Delete button to delete the dataset.