chore: 更新项目配置和依赖，优化前后端代码

backend/llm.py

@@ -9,9 +9,14 @@ from dotenv import load_dotenv
 load_dotenv()
 
 OLLAMA_MODEL = os.getenv('OLLAMA_MODEL', 'gpt-oss:20b')
-OLLAMA_HOST = os.getenv('OLLAMA_HOST', 'http://192.168.0.120:11434')
+OLLAMA_HOST = os.getenv('OLLAMA_HOST', 'http://localhost:11434')
 VLM_MODEL = os.getenv('VLM_MODEL', 'qwen3-vl:30b')
 
+# Timeouts in seconds
+COMPLETION_TIMEOUT = 30
+OCR_TIMEOUT = 60
+CONVERT_TIMEOUT = 30
+
 client = ollama.AsyncClient(host=OLLAMA_HOST)
 logger = logging.getLogger("llm")
 
@@ -97,7 +102,7 @@ async def call_ollama(
         if thinking:
             kwargs["think"] = thinking
 
-        response = await client.chat(**kwargs)
+        response = await asyncio.wait_for(client.chat(**kwargs), timeout=COMPLETION_TIMEOUT)
     except asyncio.CancelledError:
         elapsed_ms = (time.perf_counter() - start) * 1000
         end_dt = datetime.now()
@@ -156,15 +161,18 @@ async def call_vlm_ocr(image_bytes: bytes, language: str = 'auto') -> str:
     )
 
     try:
-        response = await client.chat(
-            model=VLM_MODEL,
-            messages=[{
-                'role': 'user',
-                'content': VLM_OCR_CONTEXT_PROMPT,
-                'images': [image_bytes]
-            }],
-            stream=False,
-            options={'temperature': 0.3}
+        response = await asyncio.wait_for(
+            client.chat(
+                model=VLM_MODEL,
+                messages=[{
+                    'role': 'user',
+                    'content': VLM_OCR_CONTEXT_PROMPT,
+                    'images': [image_bytes]
+                }],
+                stream=False,
+                options={'temperature': 0.3}
+            ),
+            timeout=OCR_TIMEOUT
         )
     except Exception:
         elapsed_ms = (time.perf_counter() - start) * 1000