feat: multimodal RAG with PDF image extraction and display

Extract images from PDFs using pymupdf, generate descriptions via
Qwen3-VL-8B, store in ChromaDB alongside text chunks, and render
images in chat answers. Includes image proxy rewrite, force re-process
endpoint, and VLM API timeout.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

backend/main.py

@@ -197,6 +197,11 @@ if os.path.exists(settings.upload_dir):
 if os.path.exists(settings.generated_images_dir):
     app.mount("/generated_images", StaticFiles(directory=settings.generated_images_dir), name="generated_images")
 
+# 挂载PDF图片提取目录
+IMAGES_DIR = os.path.join(os.path.dirname(os.path.dirname(__file__)), "data", "images")
+os.makedirs(IMAGES_DIR, exist_ok=True)
+app.mount("/images", StaticFiles(directory=IMAGES_DIR), name="images")
+
 # 根路径
 @app.get("/")
 async def root():