Update documentation to reflect splash screen and copy button features 36c53c8 AI Agent commited on Jun 16
UI tweak for feedback area and fix token usage metrics extraction 5d52f92 AI Agent commited on Jun 15
Update nvidia_llm to use google/diffusiongemma-26b-a4b-it via requests 145917d AI Agent commited on Jun 15
Fix Kuzu graph write lock error and suppress pip/transformer warnings 5ed03b8 AI Agent commited on Jun 14
Update nvidia_llm to use minimaxai/minimax-m2.7 and new sampling params fbc58fa AI Agent commited on Jun 14
Update nvidia_llm model, endpoint, stream=False, and remove hardcoded API key 4d634bb AI Agent commited on Jun 14
Fix nvidia_llm httpx connection leaks and improve crew.py retrieval logging 3f6235f AI Agent commited on Jun 14
Update gitignore to exclude strategic documents for minimalist deployment e6edb6f AI Agent commited on Jun 13
Update feedback UI: relocate to bottom, add 5-star rating, and immediate capture b21c909 AI Agent commited on Jun 13
Fix OOM crash causing missing jobs by limiting PyTorch concurrency a37260b AI Agent commited on Jun 13
Fix multiuser concurrency bottleneck and update HF deployment docs 130f6cd AI Agent commited on Jun 13
Fix UI 404 by applying async job queue client logic to actual index.html template 87e6e59 AI Agent commited on Jun 13
Refactor RAG query architecture to async job queue to fix mobile background disconnects 03cfa1a AI Agent commited on Jun 13
Fix: Handle mobile UI disconnects during LLM query via SSE keep-alives and UI alerts bfd4772 AI Agent commited on Jun 13