Skip to main content

Crate llm_toolkit

Crate llm_toolkit 

Source
Expand description

‘llm-toolkit’ - A low-level Rust toolkit for the LLM last mile problem.

This library provides a set of sharp, reliable, and unopinionated “tools” for building robust LLM-powered applications in Rust. It focuses on solving the common and frustrating problems that occur at the boundary between a strongly-typed Rust application and the unstructured, often unpredictable string-based responses from LLM APIs.

Re-exports§

pub extern crate minijinja;
pub use attachment::Attachment;
pub use attachment::AttachmentSchema;
pub use attachment::ToAttachments;
pub use context::ContextProfile;
pub use context::Priority;
pub use context::TaskHealth;
pub use extract::FlexibleExtractor;
pub use extract::MarkdownCodeBlockExtractor;
pub use intent::frame::IntentFrame;
pub use intent::IntentError;
pub use intent::IntentExtractor;
pub use intent::PromptBasedExtractor;Deprecated
pub use models::ClaudeModel;
pub use models::GeminiModel;
pub use models::Model;
pub use models::ModelError;
pub use models::OpenAIModel;
pub use multimodal::ImageData;
pub use prompt::PromptPart;
pub use prompt::PromptSetError;
pub use prompt::ToPrompt;
pub use prompt::ToPromptFor;
pub use prompt::ToPromptSet;
pub use retrieval::Document;

Modules§

attachment
Attachment types for multimodal workflows.
context
Context types for agent behavior and expertise activation.
extract
Content extraction and JSON repair utilities for LLM responses.
intent
Traits and implementations for extracting structured intents from LLM responses.
models
Model definitions for LLM providers.
multimodal
Multimodal support for prompts, including image data handling.
prompt
A trait and macros for powerful, type-safe prompt generation.
retrieval
Data structures for Retrieval-Augmented Generation (RAG).

Macros§

prompt
Creates a prompt string from a template and key-value pairs.

Functions§

extract_json
Extracts a JSON string from a raw LLM response string.
extract_markdown_block
Extracts content from any Markdown code block in the text.
extract_markdown_block_with_lang
Extracts content from a Markdown code block with a specific language.