You can use the Prompt Lab to chat with documents by providing a vector index. When you deploy your work as an AI service, the logic for your RAG application is automatically captured in an AI service asset and an online deployment is created for the asset.
Before you begin
- You must have an existing target deployment space or create a new one where you want to deploy your AI service asset.
- You must create a vector index (in-memory vector store or vector database) to chat with documents. For more information, see Chatting with documents and images.
- You must set up your task credentials by generating an API key. For more information, see Managing task credentials.
Creating an online deployment for AI services
Follow these steps to create an online deployment for an AI service from the watsonx.ai Prompt lab user interface:
-
From your project, open the prompt lab and chat with documents to build a RAG solution. For more information, see Chatting with documents and images.
-
To deploy your work as an AI service, click Deploy.
-
In the Deploy as an AI service dialog box, enter your deployment details:
a. Enter a name for your AI service deployment.
b. Select a target project or deployment space from the dropdown menu.
c. Optional: Provide a description and select the checkbox if you want to view the AI service asset in the project after deploying. -
Click Deploy.
This procedure automatically creates an online deployment for your AI service asset in your project or deployment space. To create a batch deployment for your AI service asset, you must follow the process to manually create a batch deployment from your deployment space. For more information, see Deploying AI service assets.
Learn more
Deploying AI services from Prompt Lab with notebooks
Parent topic: Deploying AI services with Prompt Lab