feat(llama-lora): add display names and defaults; add peft; rebuild static\n\n- UI: add baseName/loraName fields and send to backend; show names in results\n- Defaults: base=openlm-research/open_llama_3b, adapter=HGKo/openllama3b-lora-adapter\n- Backend deps: add peft to requirements.txt\n- Frontend: build CRA and sync artifacts to top-level static/

frontend: set default baseModel to gguf:tinyllama-q4km; build with nvm Node 16 and sync to static/ (update static assets)

frontend: add LlamaLoraCompare import and tab wiring; build and sync static for LoRA compare UI

build(frontend): CRA build (Node 16) and sync to static; fix(SSE): add query-param auth fallback for EventSource; backend check_auth now accepts uid/uname; frontend EventSource passes uid/uname

Fix frontend rendering issues causing white screen

Fix: Update React ProductComparison.js SSE handling

Update vision LLM agent with React Product Comparison integration

Frontend build: copy latest React build to static; UI: compare button, full previews, multi-file upload

Frontend build copied to static, add 5 test images, update API integration; ignore static backup folders

Translate Korean UI text to English in OpenAIChat.js

Update OpenAIChat.js to display search results and update static build

feat(frontend): switch OpenAI chat to Vision RAG; wire image base64 to /api/vision-rag/query; add searchType/objectId/class_name and n_results; build and sync to static/

fix(frontend): force preview <img> to contain within container; rebuild & sync CRA assets

style(frontend): responsive preview container using viewport height so entire image fits; rebuild and sync

fix(frontend): constrain preview image to container and improve OpenAI chat error logging; rebuild and sync CRA assets

chore: rebuild frontend and sync to static

Add frontend source code structure for direct development