Struct MultimodalInput 

pub struct MultimodalInput {
    pub multimodal_marker: bool,
    pub text: String,
    pub images: Vec<MultimodalImage>,
}

Multimodal input format for encoding images in string input

When sending images to an LLM callable, encode the input as:

{
  "__multimodal__": true,
  "text": "Describe this image",
  "images": [
    {"data": "<base64>", "mime_type": "image/jpeg"}
  ]
}

Fields

multimodal_marker: bool

text: String

The text portion of the message

images: Vec<MultimodalImage>

Base64-encoded images with mime types

Implementations

impl MultimodalInput

pub fn new(text: impl Into<String>, images: Vec<(Vec<u8>, String)>) -> Self

Create a new multimodal input with text and images

pub fn to_json(&self) -> String

Encode to JSON string for passing through the runner

pub fn parse(input: &str) -> Option<Self>

Try to parse multimodal input from a string Returns None if not multimodal format

Trait Implementations

impl Clone for MultimodalInput

fn clone(&self) -> MultimodalInput

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for MultimodalInput

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for MultimodalInput

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for MultimodalInput

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.