model-compose
在單一YAML檔案中宣告AI管道。Token、音訊片段及影片幀在隔離元件之間流動。組合100多個元件,適用於模型、代理、語音、視覺及直播。執行本機模型、雲端API,或兩者並行。靈感來自docker-compose。
model-compose 是什麼?
Declarative AI pipelines in one YAML file. Tokens, audio chunks, and video frames flow between isolated components. Compose 100+ components for models, agents, speech, vision, and live broadcast. Run local models, cloud APIs, or both. Inspired by docker-compose.