Skip to content
Docs
AI-Chat
AI data collection

AI data collection

One of the highlights of Chat2DB's intelligent question-and-answer feature is its powerful ability to create custom AI collection.

With this feature, users have the flexibility to build different sets of Q&A data, so that the content of the Q&A is highly customized, ensuring that each answer is precisely tailored to your specific needs. Not only that, this process also greatly improves the intelligence level of the question and answer system and the accuracy of the answer, so that you are more comfortable in dealing with complex and changeable query scenarios.

In short, the custom AI data collection is the key to unlocking Chat2DB intelligent question-and-answer precision service and realizing the intelligent upgrade of question-and-answer.

Step 1: Create an AI data collection

You can use each data source to create ai data sets for that data source. Tables from one or more different databases can be placed in an ai collection. You can also right-click all tables on the Tables node under each database to add a specified table to the ai collection.

If your table structure changes after you synchronize, you can right-click the collection node to resynchronize.

  1. Create an AI data collection 'sql-copilot'

  2. Enter the name of AI data collection 'sql-copilot'

  3. Choose the database and select the tables you need. 'sql-copilot'

  4. Sync to Al data collection 'sql-copilot'

It will take a few minutes to finish, you can close this window.

Step 2: Modify the AI Column Name and AI Column Comment

You can edit the table by double-clicking it within the ai collection. You can not modify your origin column name and comment here, you can modify the AI column name and comment as well as the AI Table Name and AI Table Comment, so that AI can better understand your table structure and column information.

This will greatly improve the accuracy of AI generation.

'sql-copilot'

Step 3: How to use the data collection

After set up the AI data collection, wherever you call AI, you can select AI data collections to do more precise content generation.

Demo 1: Natural language generation SQL

'sql-copilot'

Demo 2: Generate Dashboard in natural language

'sql-copilot'

AI table creationSQL-Optimization