Multimodal

Multi-modal input

Images

Calling a BAML function with an image input argument type (see image types).

The from_url and from_base64 methods create an Image object based on input type.

1from baml_py import Image
2from baml_client import b
3
4async def test_image_input():
5  # from URL
6  res = await b.TestImageInput(
7      img=Image.from_url(
8          "https://upload.wikimedia.org/wikipedia/en/4/4d/Shrek_%28character%29.png"
9      )
10  )
11
12  # Base64 image
13  image_b64 = "iVBORw0K...."
14  res = await b.TestImageInput(
15    img=Image.from_base64("image/png", image_b64)
16  )

Audio

Calling functions that have audio types. See audio types

1from baml_py import Audio
2from baml_client import b
3
4async def run():
5  # from URL
6  res = await b.TestAudioInput(
7      img=Audio.from_url(
8          "https://actions.google.com/sounds/v1/emergency/beeper_emergency_call.ogg"
9      )
10  )
11
12  # Base64
13  b64 = "iVBORw0K...."
14  res = await b.TestAudioInput(
15    audio=Audio.from_base64("audio/ogg", b64)
16  )