Overview

AI Chat in MySQL Studio offers a powerful, conversational interface for unlocking the full potential of MySQL AI. With AI Chat, you can seamlessly load documents into a vector store, choose which vector stores to include in your searches, and interact directly with the AI features using natural language queries. This allows you to efficiently retrieve relevant information, manage your data, and leverage MySQL AI’s advanced capabilities—all through an intuitive chat-based experience.

Start or Continue a Conversation

Use the chat input to enter a message and interact conversationally with MySQL AI. You can begin a new inquiry or follow up on earlier responses for an ongoing, intelligent conversation.

Start Over

Reset your session at any time by using the Start Over button located in the top right corner of the conversation. This clears your conversation history, allowing you to begin a new topic or inquiry with a fresh context.

Access Vector Stores

Open the left sidebar in AI Chat to view all vector stores currently loaded into your MySQL AI database. The vector stores contain vectorized collections of documents that can be efficiently searched and referenced by the AI.

Select Vector Stores for Conversation

Use the checkboxes in the vector stores sidebar to choose which stores you want to include in your AI conversation. Select one or more stores for targeted searching; if all stores are unchecked, AI Chat will rely solely on its built-in model for responses.

Loading a Document

Note: The secure file priv space used to add a document into vector stores is not the same as the My Files space located within MySQL Studio. Files located in the secure file priv location can only be accessed via the database, or commands issued via SQL to the database, while files located in My Files can only be accessed from within MySQL Studio and MySQL Studio Python notebooks.

To load a new document into a vector store:

1. In the Vector stores sidebar, click the plus (+) button to start loading a new document.
2. A popup will appear, displaying the files available in your secure file priv area.
3. Select a document from this list.
4. Choose the vector store schema and table where the document should be loaded. This action will create a new vector store containing the selected document.
5. Note: The current user must have the FILE privilege granted to perform this action.