Crate deepseek_recipe_encoding 

Model-specific conversation rendering and token encoding.

V4 and V4.1 provide prompt rendering. Attach a tokenizer to an encoding to encode conversations into token IDs.

Re-exports

pub use v4::dsv4;

pub use v4::dsv41;

Modules

v4

Structs

RenderedPrompt

A rendered prompt and the images its placeholders refer to.

Enums

EncodingError

Failure to encode a conversation.

Traits

PromptEncoding

Render model prompts and encode conversations into token IDs.

TokenizerEncoder

Encode text into model token ids.