https://pypi.org/project/optimas-ai/ Recent updates to the Python Package Index for optimas-ai en https://pypi.org/project/optimas-ai/0.0.4/ Optimas is a unified framework for end-to-end optimization of compound AI systems. While traditional optimization methods focus on single configuration types—such as prompts or hyperparameters—modern compound AI systems require coordinated optimization across multiple heterogeneous configuration types that work well together. shirwu@cs.stanford.edu Wed, 06 Aug 2025 04:57:43 GMT https://pypi.org/project/optimas-ai/0.0.3/ Optimas is a unified framework for end-to-end optimization of compound AI systems. While traditional optimization methods focus on single configuration types—such as prompts or hyperparameters—modern compound AI systems require coordinated optimization across multiple heterogeneous configuration types that work well together. shirwu@cs.stanford.edu Mon, 04 Aug 2025 18:40:14 GMT https://pypi.org/project/optimas-ai/0.0.2/ Optimas is a unified framework for end-to-end optimization of compound AI systems. While traditional optimization methods focus on single configuration types—such as prompts or hyperparameters—modern compound AI systems require coordinated optimization across multiple heterogeneous configuration types that work well together. shirwu@cs.stanford.edu Fri, 01 Aug 2025 08:13:25 GMT https://pypi.org/project/optimas-ai/0.0.1/ Optimas is a unified framework for end-to-end optimization of compound AI systems. While traditional optimization methods focus on single configuration types—such as prompts or hyperparameters—modern compound AI systems require coordinated optimization across multiple heterogeneous configuration types that work well together. shirwu@cs.stanford.edu Sun, 06 Jul 2025 20:21:50 GMT https://pypi.org/project/optimas-ai/0.0.0/ Optimas is a unified framework for end-to-end optimization of compound AI systems. While traditional optimization methods focus on single configuration types—such as prompts or hyperparameters—modern compound AI systems require coordinated optimization across multiple heterogeneous configuration types that work well together. shirwu@cs.stanford.edu Sun, 06 Jul 2025 19:50:02 GMT