Crate llama_core

Llama Core, abbreviated as llama-core, defines a set of APIs. Developers can utilize these APIs to build applications based on large models, such as chatbots, RAG, and more.

Re-exports

pub use error::LlamaCoreError;

pub use graph::EngineType;

pub use graph::Graph;

pub use graph::GraphBuilder;

pub use metadata::ggml::GgmlMetadata;

pub use metadata::ggml::GgmlTtsMetadata;

pub use metadata::piper::PiperMetadata;

pub use metadata::BaseMetadata;

Modules

audio

chat

Define APIs for chat completion.

completions

Define APIs for completions.

embeddings

Define APIs for computing embeddings.

error

Error types for the Llama Core library.

files

Define APIs for file operations.

graph

Define Graph and GraphBuilder APIs for creating a new computation graph.

images

Define APIs for image generation and edit.

metadata

Define the types for model metadata.

models

Define APIs for querying models.

ragrag

Define APIs for RAG operations.

searchsearch

Define APIs for web search operations.

tts

utils

Define utility functions.

Structs

PluginInfo

Version info of the wasi-nn_ggml plugin, including the build number and the commit id.

Enums

StableDiffusionTask

The task type of the stable diffusion context

Constants

ARCHIVES_DIR

The directory for storing the archives in wasm virtual file system.

Functions

get_plugin_info

Get the plugin info

init_ggml_chat_context

Initialize the ggml context

init_ggml_embeddings_context

Initialize the ggml context

init_ggml_rag_contextrag

Initialize the ggml context for RAG scenarios.

init_ggml_tts_context

Initialize the ggml context for TTS scenarios.

init_piper_context

Initialize the piper context

init_sd_context_with_full_model

Initialize the stable-diffusion context with the given full diffusion model

init_sd_context_with_standalone_model

Initialize the stable-diffusion context with the given standalone diffusion model

init_whisper_contextwhisper

Initialize the whisper context

running_mode

Return the current running mode.