From b02397e460ec56b4b74146508eeab2a3ba13950e Mon Sep 17 00:00:00 2001
From: Timothy Jaeryang Baek <tim@openwebui.com>
Date: Mon, 8 Dec 2025 11:49:27 -0500
Subject: [PATCH] feat: WEB_LOADER_TIMEOUT

---
 backend/open_webui/config.py                      |  7 +++++++
 backend/open_webui/main.py                        |  2 ++
 backend/open_webui/retrieval/web/utils.py         | 15 +++++++++++++++
 backend/open_webui/routers/retrieval.py           |  5 +++++
 .../components/admin/Settings/WebSearch.svelte    | 13 +++++++++++++
 5 files changed, 42 insertions(+)

diff --git a/backend/open_webui/config.py b/backend/open_webui/config.py
index 6d60ab89f5..983db4e04b 100644
--- a/backend/open_webui/config.py
+++ b/backend/open_webui/config.py
@@ -635,6 +635,7 @@ OAUTH_AUDIENCE = PersistentConfig(
     os.environ.get("OAUTH_AUDIENCE", ""),
 )
 
+
 def load_oauth_providers():
     OAUTH_PROVIDERS.clear()
     if GOOGLE_CLIENT_ID.value and GOOGLE_CLIENT_SECRET.value:
@@ -2999,6 +3000,12 @@ WEB_LOADER_CONCURRENT_REQUESTS = PersistentConfig(
     int(os.getenv("WEB_LOADER_CONCURRENT_REQUESTS", "10")),
 )
 
+WEB_LOADER_TIMEOUT = PersistentConfig(
+    "WEB_LOADER_TIMEOUT",
+    "rag.web.loader.timeout",
+    os.getenv("WEB_LOADER_TIMEOUT", ""),
+)
+
 
 ENABLE_WEB_LOADER_SSL_VERIFICATION = PersistentConfig(
     "ENABLE_WEB_LOADER_SSL_VERIFICATION",
diff --git a/backend/open_webui/main.py b/backend/open_webui/main.py
index dc4468e8e7..5609289166 100644
--- a/backend/open_webui/main.py
+++ b/backend/open_webui/main.py
@@ -208,6 +208,7 @@ from open_webui.config import (
     FIRECRAWL_API_KEY,
     WEB_LOADER_ENGINE,
     WEB_LOADER_CONCURRENT_REQUESTS,
+    WEB_LOADER_TIMEOUT,
     WHISPER_MODEL,
     WHISPER_VAD_FILTER,
     WHISPER_LANGUAGE,
@@ -922,6 +923,7 @@ app.state.config.WEB_SEARCH_CONCURRENT_REQUESTS = WEB_SEARCH_CONCURRENT_REQUESTS
 
 app.state.config.WEB_LOADER_ENGINE = WEB_LOADER_ENGINE
 app.state.config.WEB_LOADER_CONCURRENT_REQUESTS = WEB_LOADER_CONCURRENT_REQUESTS
+app.state.config.WEB_LOADER_TIMEOUT = WEB_LOADER_TIMEOUT
 
 app.state.config.WEB_SEARCH_TRUST_ENV = WEB_SEARCH_TRUST_ENV
 app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL = (
diff --git a/backend/open_webui/retrieval/web/utils.py b/backend/open_webui/retrieval/web/utils.py
index bdbde0b3a9..ec0a8d8ed7 100644
--- a/backend/open_webui/retrieval/web/utils.py
+++ b/backend/open_webui/retrieval/web/utils.py
@@ -33,6 +33,7 @@ from open_webui.config import (
     PLAYWRIGHT_WS_URL,
     PLAYWRIGHT_TIMEOUT,
     WEB_LOADER_ENGINE,
+    WEB_LOADER_TIMEOUT,
     FIRECRAWL_API_BASE_URL,
     FIRECRAWL_API_KEY,
     TAVILY_API_KEY,
@@ -674,6 +675,20 @@ def get_web_loader(
 
     if WEB_LOADER_ENGINE.value == "" or WEB_LOADER_ENGINE.value == "safe_web":
         WebLoaderClass = SafeWebBaseLoader
+
+        request_kwargs = {}
+        if WEB_LOADER_TIMEOUT.value:
+            try:
+                timeout_value = float(WEB_LOADER_TIMEOUT.value)
+            except ValueError:
+                timeout_value = None
+
+            if timeout_value:
+                request_kwargs["timeout"] = timeout_value
+
+        if request_kwargs:
+            web_loader_args["requests_kwargs"] = request_kwargs
+
     if WEB_LOADER_ENGINE.value == "playwright":
         WebLoaderClass = SafePlaywrightURLLoader
         web_loader_args["playwright_timeout"] = PLAYWRIGHT_TIMEOUT.value
diff --git a/backend/open_webui/routers/retrieval.py b/backend/open_webui/routers/retrieval.py
index cc2457eba7..08ffde1733 100644
--- a/backend/open_webui/routers/retrieval.py
+++ b/backend/open_webui/routers/retrieval.py
@@ -536,6 +536,7 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
             "SOUGOU_API_SID": request.app.state.config.SOUGOU_API_SID,
             "SOUGOU_API_SK": request.app.state.config.SOUGOU_API_SK,
             "WEB_LOADER_ENGINE": request.app.state.config.WEB_LOADER_ENGINE,
+            "WEB_LOADER_TIMEOUT": request.app.state.config.WEB_LOADER_TIMEOUT,
             "ENABLE_WEB_LOADER_SSL_VERIFICATION": request.app.state.config.ENABLE_WEB_LOADER_SSL_VERIFICATION,
             "PLAYWRIGHT_WS_URL": request.app.state.config.PLAYWRIGHT_WS_URL,
             "PLAYWRIGHT_TIMEOUT": request.app.state.config.PLAYWRIGHT_TIMEOUT,
@@ -594,6 +595,7 @@ class WebConfig(BaseModel):
     SOUGOU_API_SID: Optional[str] = None
     SOUGOU_API_SK: Optional[str] = None
     WEB_LOADER_ENGINE: Optional[str] = None
+    WEB_LOADER_TIMEOUT: Optional[str] = None
     ENABLE_WEB_LOADER_SSL_VERIFICATION: Optional[bool] = None
     PLAYWRIGHT_WS_URL: Optional[str] = None
     PLAYWRIGHT_TIMEOUT: Optional[int] = None
@@ -1071,6 +1073,8 @@ async def update_rag_config(
 
         # Web loader settings
         request.app.state.config.WEB_LOADER_ENGINE = form_data.web.WEB_LOADER_ENGINE
+        request.app.state.config.WEB_LOADER_TIMEOUT = form_data.web.WEB_LOADER_TIMEOUT
+
         request.app.state.config.ENABLE_WEB_LOADER_SSL_VERIFICATION = (
             form_data.web.ENABLE_WEB_LOADER_SSL_VERIFICATION
         )
@@ -1206,6 +1210,7 @@ async def update_rag_config(
             "SOUGOU_API_SID": request.app.state.config.SOUGOU_API_SID,
             "SOUGOU_API_SK": request.app.state.config.SOUGOU_API_SK,
             "WEB_LOADER_ENGINE": request.app.state.config.WEB_LOADER_ENGINE,
+            "WEB_LOADER_TIMEOUT": request.app.state.config.WEB_LOADER_TIMEOUT,
             "ENABLE_WEB_LOADER_SSL_VERIFICATION": request.app.state.config.ENABLE_WEB_LOADER_SSL_VERIFICATION,
             "PLAYWRIGHT_WS_URL": request.app.state.config.PLAYWRIGHT_WS_URL,
             "PLAYWRIGHT_TIMEOUT": request.app.state.config.PLAYWRIGHT_TIMEOUT,
diff --git a/src/lib/components/admin/Settings/WebSearch.svelte b/src/lib/components/admin/Settings/WebSearch.svelte
index 17191ac216..f26a9f85b8 100644
--- a/src/lib/components/admin/Settings/WebSearch.svelte
+++ b/src/lib/components/admin/Settings/WebSearch.svelte
@@ -767,6 +767,19 @@
 					</div>
 
 					{#if webConfig.WEB_LOADER_ENGINE === '' || webConfig.WEB_LOADER_ENGINE === 'safe_web'}
+						<div class="  mb-2.5 flex w-full justify-between">
+							<div class=" self-center text-xs font-medium">
+								{$i18n.t('Timeout')}
+							</div>
+							<div class="flex items-center relative">
+								<input
+									class="flex-1 w-full text-sm bg-transparent outline-hidden"
+									placeholder={$i18n.t('Timeout')}
+									bind:value={webConfig.WEB_LOADER_TIMEOUT}
+								/>
+							</div>
+						</div>
+
 						<div class="  mb-2.5 flex w-full justify-between">
 							<div class=" self-center text-xs font-medium">
 								{$i18n.t('Verify SSL Certificate')}