Host structured tabular data such as XLSX and XLS for agents to query table schemas and content.
The Table connector manages structured tabular data. After a table is imported, the platform parses it, and an agent uses the automatically generated tool to obtain the table schema and then query the data accordingly.
Like the File connector, it requires no credentials from an external system.
After the connector is created, 1 tool is generated automatically:
Neither input parameter is required. Pass
XLSX and XLS formats are supported.
Tables are also organized by category, and the import methods are the same as for files. See Categories and Import data on the File connector page.
Both handle structured data, but they make different trade-offs:
When data changes continuously, prefer the database connector.
Create a connector
1
Open the connection dialog
On the Apps page, find the Table connector card and click Connect.
2
Enter the basic information
| Field | Required | Description |
|---|---|---|
| Connector name | Yes | Use a name that is easy to recognize. Up to 64 characters |
| Connector description | No | Describes the table content and its purpose, for example, monthly sales reports and customer ledgers |
3
Confirm the storage location
Storage location currently offers only one option, Use platform storage. Select it and continue. Data is stored in the storage space provided by Alibaba Cloud Model Studio, with a quota of up to 200,000 files and 1 TB, free for a limited time. For details, see Quotas and Limits.
4
Confirm creation
Click Confirm. After creation, the connector type cannot be changed.
Automatically generated tools
After the connector is created, 1 tool is generated automatically:
| Tool | Function | Input parameters |
|---|---|---|
| Get table schema | Retrieves the schema of a table file by the ID of the table file | tableId (string): the ID of the table filefuzzyTableName (string): the table name, which supports fuzzy matching |
tableId when you know the specific table ID, and pass fuzzyTableName when you only remember the table name or need to look it up by name.
Get table schema returns field definitions, not the data rows in the table. An agent typically uses it first to learn which fields a table has, and then decides how to query it.
Supported table formats
XLSX and XLS formats are supported.
Import data
Tables are also organized by category, and the import methods are the same as for files. See Categories and Import data on the File connector page.
Differences from the database connector
Both handle structured data, but they make different trade-offs:
| Table connector | Database connector | |
|---|---|---|
| Data location | A copy is uploaded to the platform | Stays in the original database |
| Data freshness | A snapshot taken at import time | Real time |
| Suitable scenarios | One-off reports and offline ledgers | Business data that changes continuously |
| Preparation required | No external credentials | A database instance that is reachable over the network |