Appearance
AI Actions
AI Gateway includes three actions under the AI category in an API Endpoint. Use this page to pick the right one. Each section links to the action page for fields, results, and setup.
You add them the same way as any other backend action: open an API Endpoint, click Add an action, then open the AI category.
Learn how to add an AI action →
Text Generation
Text Generation asks a model to write a reply from a prompt. You can also ask it to return a structured result, such as an object, a list, or one option from a set of choices.
Use it when the app needs to create or reshape text, for example:
- Summarize a support message before a teammate opens it
- Turn a form submission into a short product description
- Return a structured object the next action can save to a table
- Stream a chat reply so the user sees words as they arrive
Learn how to set up Text Generation →
Image Generation
Image Generation creates an image from a text prompt. You can show the result in the app right away, or upload it to storage if you need to keep it.
Use it when the app should create a picture on demand, for example:
- Generate a product mockup from a short description
- Create a cover image for a post the user just wrote
- Preview a design idea before you save it
Learn how to set up Image Generation →
Embed Text
Embed Text turns a piece of text into a vector embedding: a list of numbers that represents the meaning of that text. You can compare embeddings later to find similar items.
Use it when you need semantic search, for example:
- Find products that match a search even if the wording is different
- Suggest related support articles
- Group similar messages or records by meaning
Embed Text only creates the vector. WeWeb tables cannot store or search embeddings yet, so you need an external database that supports vectors.
Learn how to set up Embed Text →