this strategy will use the html of the page/locator to extract the needed data. we filter out some of the attributes to reduce context. the attributes included are only: aria-label data-name name type placeholder value role title href id alt,

​
Properties

​
model

model: 
  | "claude-3-opus"
  | "claude-3-sonnet"
  | "claude-3.5-sonnet"
  | "claude-3-haiku"
  | "gpt4-turbo"
  | "gpt-4o"
  | "gpt3.5-turbo";

the model to use in the extraction process

​
type

type: "HTML";

the type of the strategy

FileUrlSourceImageFile