llm-typesafe
A plugin for Simon Willison's LLM command-line tool that integrates TypeSafe AI's Jev model. It is designed specifically for structured judgment tasks such as classification and scoring, and supports type-safe structured output.
Timeline (last 90 days)
The first plugin to adopt the `supports_conversation = False` feature is llm-typesafe, which focuses on type-safe structured output scenarios.
The llm-typesafe plugin is used to connect the command-line tool LLM to the model Jev launched by TypeSafe AI, serving specifically structured judgment tasks.
The plugin is installed via the command llm install llm-typesafe, and after configuring the API key, the model is invoked with -m jev.
The current version of llm-typesafe, 0.1a0, is in an early alpha stage, and both the API and behavior are subject to change.
All Facts (3)
The first plugin to adopt the `supports_conversation = False` feature is llm-typesafe, which focuses on type-safe structured output scenarios.
50%UnverifiedThe llm-typesafe plugin is used to connect the command-line tool LLM to the model Jev launched by TypeSafe AI, serving specifically structured judgment tasks.
50%UnverifiedThe plugin is installed via the command llm install llm-typesafe, and after configuring the API key, the model is invoked with -m jev.
50%