fix(backend): restore real trained MobileNetV2 and EfficientNet-B0 neural network prediction pipeline

fix(vercel): add dual path resolution in api/index.py and main.py for serverless entrypoint

fix(backend): guard jose and passlib imports in auth.py to fix serverless FUNCTION_INVOCATION_FAILED on Vercel

fix(backend): make top-level imports in llm_service and rag_service fully guarded for serverless cold start

fix(backend): bypass heavy torch loading in Vercel serverless environment for zero OOM crashes

fix(backend): add numpy tensor guards in disease and soil models for serverless environment

fix(backend): use safe_get_remote_address and lazy model instantiation for serverless Vercel execution

fix(backend): lazy-initialize cache backend to resolve FUNCTION_INVOCATION_FAILED on Vercel

fix(backend): add resilient fallbacks for disease, soil, and image preprocessing in serverless environment

fix(vercel): optimize serverless dependencies and crop model fallback to pass 500MB function size limit

fix(vercel): pin Python 3.11 and update pydantic version to resolve wheel compilation error

feat: configure Vercel Python serverless function handler for FastAPI backend

feat: replace legacy frontend, integrate agriculture-ai-frontend with backend, update CORS, and clean project structure

Add trained ML models (crop, disease, soil), tools, setup scripts, and updated .gitignore

first commit