The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls.
OpenAI now supports Structured Outputs mode in its API. This may be very compatible with llama-cpp-agent; it would be helpful to have such an option to allow people without GPUs to use the application.
https://openai.com/index/introducing-structured-outputs-in-the-api/
OpenAI now supports Structured Outputs mode in its API. This may be very compatible with llama-cpp-agent; it would be helpful to have such an option to allow people without GPUs to use the application. https://openai.com/index/introducing-structured-outputs-in-the-api/