Skip to main content
The LLM Engine serves as the operational core for model interaction within the Ladder AI framework. It provides a unified interface to manage and coordinate both large and small language models, facilitating seamless integration with various model providers and architectures. The engine is responsible for handling all model-related tasks, including prompt formatting, response parsing, and orchestrating the flow of information between different components of the system.
llm_engin.py

from ladder.engines import LLMEngine

llm_engine = LLMEngine(lm="openai/gpt-3.5-turbo")