fix: add HuggingFace mirror support for China network

- Add HF_ENDPOINT configuration option
- Set HuggingFace mirror to https://hf-mirror.com
- Fix 'cannot connect to huggingface.co' error
- Update .env.example with HF_ENDPOINT setting

Problem:
- RAG engine uses sentence-transformers model
- Model download requires connection to huggingface.co
- China network cannot access huggingface.co
- Error: 'We couldn't connect to https://huggingface.co'

Solution:
- Add HF_ENDPOINT environment variable support
- Use hf-mirror.com as HuggingFace mirror
- Set mirror before loading sentence-transformers
- Document in .env.example

Files:
- backend/app/config.py: add HF_ENDPOINT config
- backend/app/core/rag_engine.py: set HF_ENDPOINT before model load
- backend/setup_hf_mirror.sh: setup script
- backend/.env: configure mirror (not tracked)

backend/app/core/rag_engine.py

@@ -4,6 +4,7 @@ This module provides the RAGEngine class that handles knowledge document
 storage and retrieval using ChromaDB and sentence-transformers embeddings.
 """
 
+import os
 from typing import Optional
 
 import chromadb
@@ -28,6 +29,11 @@ class RAGEngine:
         """Initialize RAG engine with ChromaDB and embedding model."""
         settings = get_settings()
 
+        # Set HuggingFace mirror if configured
+        if settings.HF_ENDPOINT:
+            os.environ['HF_ENDPOINT'] = settings.HF_ENDPOINT
+            logger.info(f"Using HuggingFace mirror: {settings.HF_ENDPOINT}")
+
         # Initialize ChromaDB persistent client
         logger.info(f"Initializing ChromaDB at: {settings.CHROMA_DB_PATH}")
         self.chroma_client = chromadb.PersistentClient(