refac

backend/open_webui/retrieval/loaders/main.py

@@ -331,13 +331,21 @@ class Loader:
         elif self.engine == "mineru" and file_ext in [
             "pdf"
         ]:  # MinerU currently only supports PDF
+
+            mineru_timeout = self.kwargs.get("MINERU_API_TIMEOUT", 300)
+            if mineru_timeout:
+                try:
+                    mineru_timeout = int(mineru_timeout)
+                except ValueError:
+                    mineru_timeout = 300
+
             loader = MinerULoader(
                 file_path=file_path,
                 api_mode=self.kwargs.get("MINERU_API_MODE", "local"),
                 api_url=self.kwargs.get("MINERU_API_URL", "http://localhost:8000"),
                 api_key=self.kwargs.get("MINERU_API_KEY", ""),
                 params=self.kwargs.get("MINERU_PARAMS", {}),
-                timeout=int(self.kwargs.get("MINERU_API_TIMEOUT", 300)),
+                timeout=mineru_timeout,
             )
         elif (
             self.engine == "mistral_ocr"

backend/open_webui/retrieval/loaders/mineru.py

@@ -26,7 +26,7 @@ class MinerULoader:
         api_url: str = "http://localhost:8000",
         api_key: str = "",
         params: dict = None,
-        timeout: int = 300,
+        timeout: Optional[int] = 300,
     ):
         self.file_path = file_path
         self.api_mode = api_mode.lower()
@@ -103,7 +103,7 @@ class MinerULoader:
                     f"{self.api_url}/file_parse",
                     data=form_data,
                     files=files,
-                    timeout=self.timeout,  # 5 minute timeout for large documents
+                    timeout=self.timeout,
                 )
                 response.raise_for_status()
 
@@ -302,7 +302,7 @@ class MinerULoader:
                 response = requests.put(
                     upload_url,
                     data=f,
-                    timeout=self.timeout,  # 5 minute timeout for large files
+                    timeout=self.timeout,
                 )
                 response.raise_for_status()
         except FileNotFoundError: