Ask My Image

The quick-start guide illustrates how to write a GenAIScript that takes input from an image file.

Place your image in a directory visible in VS Code Explorer
Use the > GenAIScript: Create new script... command in the command palette to create a new script.

Update the model in the script header to refer to a model that understands images:

script({
    title: "Apply a script to an image",
    model: "openai:gpt-4o",
})

Use defImages to ingest the image file into the model context:
```
defImages(env.files, { detail: "low" })
```

Replace the text "TELL THE LLM WHAT TO DO..." with what you want it to do with your image file.

$`You are a helpful assistant.
Your goal is to look at the image of a chart provided
and extract the data it is presented in a tabular format.`

Right click on the image file in VS Code Explorer. Select Run GenAIScript. Select the script you just wrote.
The Output will be displayed in a new document tab.