fix: add system deps to Dockerfile, pre-download all models, remove deprecated hf_hub param 0344c63 Rohan P H commited on Jul 19
fix: replace arun_many with asyncio.gather+semaphore for true parallel crawling acac548 Rohan P H commited on Jul 18
fix: add SemaphoreDispatcher for actual parallel crawling (4 concurrent, tuned for 2vCPU/16GB) 62fe812 Rohan P H commited on Jul 18
fix: replace deprecated bypass_cache with CacheMode.BYPASS, wire PDF size slider 89f822e Rohan P H commited on Jul 18
feat: concurrent crawl with anti-bot, RSS fallback, and depth-by-depth processing a0e1f24 Rohan P H commited on Jul 18
add pdf+text extraction via pymupdf, increase depth/pages limits, show pdf count 87c449b Rohan P H commited on Jul 18