feat: bypass web loader in web search

Co-Authored-By: Perry Li <peiyaoli@mail.nankai.edu.cn>
Co-Authored-By: WilliamGates <3852641+williamgateszhao@users.noreply.github.com>
This commit is contained in:
Timothy Jaeryang Baek 2025-05-23 02:30:35 +04:00
parent 0b7f927983
commit 2eca6f6414
4 changed files with 51 additions and 7 deletions

View File

@ -2177,6 +2177,12 @@ BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL = PersistentConfig(
)
BYPASS_WEB_SEARCH_WEB_LOADER = PersistentConfig(
"BYPASS_WEB_SEARCH_WEB_LOADER",
"rag.web.search.bypass_web_loader",
os.getenv("BYPASS_WEB_SEARCH_WEB_LOADER", "False").lower() == "true",
)
WEB_SEARCH_RESULT_COUNT = PersistentConfig(
"WEB_SEARCH_RESULT_COUNT",
"rag.web.search.result_count",
@ -2202,6 +2208,7 @@ WEB_SEARCH_CONCURRENT_REQUESTS = PersistentConfig(
int(os.getenv("WEB_SEARCH_CONCURRENT_REQUESTS", "10")),
)
WEB_LOADER_ENGINE = PersistentConfig(
"WEB_LOADER_ENGINE",
"rag.web.loader.engine",

View File

@ -228,6 +228,7 @@ from open_webui.config import (
ENABLE_WEB_SEARCH,
WEB_SEARCH_ENGINE,
BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL,
BYPASS_WEB_SEARCH_WEB_LOADER,
WEB_SEARCH_RESULT_COUNT,
WEB_SEARCH_CONCURRENT_REQUESTS,
WEB_SEARCH_TRUST_ENV,
@ -707,6 +708,7 @@ app.state.config.WEB_SEARCH_TRUST_ENV = WEB_SEARCH_TRUST_ENV
app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL = (
BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL
)
app.state.config.BYPASS_WEB_SEARCH_WEB_LOADER = BYPASS_WEB_SEARCH_WEB_LOADER
app.state.config.ENABLE_GOOGLE_DRIVE_INTEGRATION = ENABLE_GOOGLE_DRIVE_INTEGRATION
app.state.config.ENABLE_ONEDRIVE_INTEGRATION = ENABLE_ONEDRIVE_INTEGRATION

View File

@ -387,6 +387,7 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
"WEB_SEARCH_CONCURRENT_REQUESTS": request.app.state.config.WEB_SEARCH_CONCURRENT_REQUESTS,
"WEB_SEARCH_DOMAIN_FILTER_LIST": request.app.state.config.WEB_SEARCH_DOMAIN_FILTER_LIST,
"BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL": request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL,
"BYPASS_WEB_SEARCH_WEB_LOADER": request.app.state.config.BYPASS_WEB_SEARCH_WEB_LOADER,
"SEARXNG_QUERY_URL": request.app.state.config.SEARXNG_QUERY_URL,
"YACY_QUERY_URL": request.app.state.config.YACY_QUERY_URL,
"YACY_USERNAME": request.app.state.config.YACY_USERNAME,
@ -439,6 +440,7 @@ class WebConfig(BaseModel):
WEB_SEARCH_CONCURRENT_REQUESTS: Optional[int] = None
WEB_SEARCH_DOMAIN_FILTER_LIST: Optional[List[str]] = []
BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL: Optional[bool] = None
BYPASS_WEB_SEARCH_WEB_LOADER: Optional[bool] = None
SEARXNG_QUERY_URL: Optional[str] = None
YACY_QUERY_URL: Optional[str] = None
YACY_USERNAME: Optional[str] = None
@ -751,6 +753,9 @@ async def update_rag_config(
request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL = (
form_data.web.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL
)
request.app.state.config.BYPASS_WEB_SEARCH_WEB_LOADER = (
form_data.web.BYPASS_WEB_SEARCH_WEB_LOADER
)
request.app.state.config.SEARXNG_QUERY_URL = form_data.web.SEARXNG_QUERY_URL
request.app.state.config.YACY_QUERY_URL = form_data.web.YACY_QUERY_URL
request.app.state.config.YACY_USERNAME = form_data.web.YACY_USERNAME
@ -875,6 +880,7 @@ async def update_rag_config(
"WEB_SEARCH_CONCURRENT_REQUESTS": request.app.state.config.WEB_SEARCH_CONCURRENT_REQUESTS,
"WEB_SEARCH_DOMAIN_FILTER_LIST": request.app.state.config.WEB_SEARCH_DOMAIN_FILTER_LIST,
"BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL": request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL,
"BYPASS_WEB_SEARCH_WEB_LOADER": request.app.state.config.BYPASS_WEB_SEARCH_WEB_LOADER,
"SEARXNG_QUERY_URL": request.app.state.config.SEARXNG_QUERY_URL,
"YACY_QUERY_URL": request.app.state.config.YACY_QUERY_URL,
"YACY_USERNAME": request.app.state.config.YACY_USERNAME,
@ -1678,13 +1684,29 @@ async def process_web_search(
)
try:
loader = get_web_loader(
urls,
verify_ssl=request.app.state.config.ENABLE_WEB_LOADER_SSL_VERIFICATION,
requests_per_second=request.app.state.config.WEB_SEARCH_CONCURRENT_REQUESTS,
trust_env=request.app.state.config.WEB_SEARCH_TRUST_ENV,
)
docs = await loader.aload()
if request.app.state.config.BYPASS_WEB_SEARCH_WEB_LOADER:
docs = [
Document(
page_content=result.snippet,
metadata={
"source": result.link,
"title": result.title,
"snippet": result.snippet,
"link": result.link,
},
)
for result in search_results
if hasattr(result, "snippet")
]
else:
loader = get_web_loader(
urls,
verify_ssl=request.app.state.config.ENABLE_WEB_LOADER_SSL_VERIFICATION,
requests_per_second=request.app.state.config.WEB_SEARCH_CONCURRENT_REQUESTS,
trust_env=request.app.state.config.WEB_SEARCH_TRUST_ENV,
)
docs = await loader.aload()
urls = [
doc.metadata.get("source") for doc in docs if doc.metadata.get("source")
] # only keep the urls returned by the loader

View File

@ -613,6 +613,19 @@
</div>
</div>
<div class=" mb-2.5 flex w-full justify-between">
<div class=" self-center text-xs font-medium">
<Tooltip content={$i18n.t('Bypass Web Loader')} placement="top-start">
{$i18n.t('Bypass Web Loader')}
</Tooltip>
</div>
<div class="flex items-center relative">
<Tooltip content={''}>
<Switch bind:state={webConfig.BYPASS_WEB_SEARCH_WEB_LOADER} />
</Tooltip>
</div>
</div>
<div class=" mb-2.5 flex w-full justify-between">
<div class=" self-center text-xs font-medium">
{$i18n.t('Trust Proxy Environment')}