DocJev launches with a claimed 6x speedup over gpt-5.6-luna

DocJev’s announcement says the library uses Jev to predict document categories or boundaries between sub-documents from natural-language category rules. It claims 6x faster performance than gpt-5.6-luna with equivalent accuracy, including liteparse processing time. Users can choose liteparse or LlamaParse for preprocessing. The announcement says LlamaParse adds latency but is an option for complex documents and for caching document representations for downstream tasks.