feat: Add frontend configuration for web loader

This commit is contained in:
tth37 2025-04-12 17:13:30 +08:00
parent 30d02c638c
commit 5eac5960ef
3 changed files with 361 additions and 195 deletions

View File

@ -2087,18 +2087,6 @@ SERPLY_API_KEY = PersistentConfig(
os.getenv("SERPLY_API_KEY", ""),
)
TAVILY_API_KEY = PersistentConfig(
"TAVILY_API_KEY",
"rag.web.search.tavily_api_key",
os.getenv("TAVILY_API_KEY", ""),
)
TAVILY_EXTRACT_DEPTH = PersistentConfig(
"TAVILY_EXTRACT_DEPTH",
"rag.web.search.tavily_extract_depth",
os.getenv("TAVILY_EXTRACT_DEPTH", "basic"),
)
JINA_API_KEY = PersistentConfig(
"JINA_API_KEY",
"rag.web.search.jina_api_key",
@ -2193,28 +2181,40 @@ RAG_WEB_SEARCH_TRUST_ENV = PersistentConfig(
PLAYWRIGHT_WS_URI = PersistentConfig(
"PLAYWRIGHT_WS_URI",
"rag.web.loader.engine.playwright.ws.uri",
os.environ.get("PLAYWRIGHT_WS_URI", None),
"rag.web.loader.playwright_ws_uri",
os.environ.get("PLAYWRIGHT_WS_URI", ""),
)
PLAYWRIGHT_TIMEOUT = PersistentConfig(
"PLAYWRIGHT_TIMEOUT",
"rag.web.loader.engine.playwright.timeout",
int(os.environ.get("PLAYWRIGHT_TIMEOUT", "10")),
"rag.web.loader.playwright_timeout",
int(os.environ.get("PLAYWRIGHT_TIMEOUT", "10000")),
)
FIRECRAWL_API_KEY = PersistentConfig(
"FIRECRAWL_API_KEY",
"firecrawl.api_key",
"rag.web.loader.firecrawl_api_key",
os.environ.get("FIRECRAWL_API_KEY", ""),
)
FIRECRAWL_API_BASE_URL = PersistentConfig(
"FIRECRAWL_API_BASE_URL",
"firecrawl.api_url",
"rag.web.loader.firecrawl_api_url",
os.environ.get("FIRECRAWL_API_BASE_URL", "https://api.firecrawl.dev"),
)
TAVILY_API_KEY = PersistentConfig(
"TAVILY_API_KEY",
"rag.web.loader.tavily_api_key",
os.getenv("TAVILY_API_KEY", ""),
)
TAVILY_EXTRACT_DEPTH = PersistentConfig(
"TAVILY_EXTRACT_DEPTH",
"rag.web.loader.tavily_extract_depth",
os.getenv("TAVILY_EXTRACT_DEPTH", "basic"),
)
####################################
# Images
####################################

View File

@ -378,18 +378,9 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
"max_size": request.app.state.config.FILE_MAX_SIZE,
"max_count": request.app.state.config.FILE_MAX_COUNT,
},
"youtube": {
"language": request.app.state.config.YOUTUBE_LOADER_LANGUAGE,
"translation": request.app.state.YOUTUBE_LOADER_TRANSLATION,
"proxy_url": request.app.state.config.YOUTUBE_LOADER_PROXY_URL,
},
"web": {
"ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION": request.app.state.config.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION,
"BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL": request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL,
"ENABLE_RAG_WEB_SEARCH": request.app.state.config.ENABLE_RAG_WEB_SEARCH,
"search": {
"enabled": request.app.state.config.ENABLE_RAG_WEB_SEARCH,
"drive": request.app.state.config.ENABLE_GOOGLE_DRIVE_INTEGRATION,
"onedrive": request.app.state.config.ENABLE_ONEDRIVE_INTEGRATION,
"engine": request.app.state.config.RAG_WEB_SEARCH_ENGINE,
"searxng_query_url": request.app.state.config.SEARXNG_QUERY_URL,
"google_pse_api_key": request.app.state.config.GOOGLE_PSE_API_KEY,
@ -415,10 +406,26 @@ 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,
"result_count": request.app.state.config.RAG_WEB_SEARCH_RESULT_COUNT,
"trust_env": request.app.state.config.RAG_WEB_SEARCH_TRUST_ENV,
"concurrent_requests": request.app.state.config.RAG_WEB_SEARCH_CONCURRENT_REQUESTS,
"domain_filter_list": request.app.state.config.RAG_WEB_SEARCH_DOMAIN_FILTER_LIST,
},
"loader": {
"engine": request.app.state.config.RAG_WEB_LOADER_ENGINE,
"enable_ssl_verification": request.app.state.config.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION,
"trust_env": request.app.state.config.RAG_WEB_SEARCH_TRUST_ENV,
"bypass_embedding_and_retrieval": request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL,
"playwright_ws_uri": request.app.state.config.PLAYWRIGHT_WS_URI,
"playwright_timeout": request.app.state.config.PLAYWRIGHT_TIMEOUT,
"firecrawl_api_key": request.app.state.config.FIRECRAWL_API_KEY,
"firecrawl_api_base_url": request.app.state.config.FIRECRAWL_API_BASE_URL,
"tavily_api_key": request.app.state.config.TAVILY_API_KEY,
"tavily_extract_depth": request.app.state.config.TAVILY_EXTRACT_DEPTH,
"youtube": {
"language": request.app.state.config.YOUTUBE_LOADER_LANGUAGE,
"proxy_url": request.app.state.config.YOUTUBE_LOADER_PROXY_URL,
"translation": request.app.state.YOUTUBE_LOADER_TRANSLATION,
},
},
},
}
@ -458,7 +465,6 @@ class YoutubeLoaderConfig(BaseModel):
class WebSearchConfig(BaseModel):
enabled: bool
engine: Optional[str] = None
searxng_query_url: Optional[str] = None
google_pse_api_key: Optional[str] = None
@ -485,14 +491,27 @@ class WebSearchConfig(BaseModel):
sougou_api_sk: Optional[str] = None
result_count: Optional[int] = None
concurrent_requests: Optional[int] = None
trust_env: Optional[bool] = None
domain_filter_list: Optional[List[str]] = []
class WebLoaderConfig(BaseModel):
engine: Optional[str] = None
enable_ssl_verification: Optional[bool] = None
trust_env: Optional[bool] = None
bypass_embedding_and_retrieval: Optional[bool] = None
playwright_ws_uri: Optional[str] = None
playwright_timeout: Optional[int] = None
firecrawl_api_key: Optional[str] = None
firecrawl_api_base_url: Optional[str] = None
tavily_api_key: Optional[str] = None
tavily_extract_depth: Optional[str] = None
youtube: Optional[YoutubeLoaderConfig] = None
class WebConfig(BaseModel):
ENABLE_RAG_WEB_SEARCH: Optional[bool] = None
search: WebSearchConfig
ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION: Optional[bool] = None
BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL: Optional[bool] = None
loader: WebLoaderConfig
class ConfigUpdateForm(BaseModel):
@ -504,7 +523,6 @@ class ConfigUpdateForm(BaseModel):
file: Optional[FileConfig] = None
content_extraction: Optional[ContentExtractionConfig] = None
chunk: Optional[ChunkParamUpdateForm] = None
youtube: Optional[YoutubeLoaderConfig] = None
web: Optional[WebConfig] = None
@ -576,24 +594,12 @@ async def update_rag_config(
request.app.state.config.CHUNK_SIZE = form_data.chunk.chunk_size
request.app.state.config.CHUNK_OVERLAP = form_data.chunk.chunk_overlap
if form_data.youtube is not None:
request.app.state.config.YOUTUBE_LOADER_LANGUAGE = form_data.youtube.language
request.app.state.config.YOUTUBE_LOADER_PROXY_URL = form_data.youtube.proxy_url
request.app.state.YOUTUBE_LOADER_TRANSLATION = form_data.youtube.translation
if form_data.web is not None:
request.app.state.config.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION = (
# Note: When UI "Bypass SSL verification for Websites"=True then ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION=False
form_data.web.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION
request.app.state.config.ENABLE_RAG_WEB_SEARCH = (
form_data.web.ENABLE_RAG_WEB_SEARCH
)
request.app.state.config.ENABLE_RAG_WEB_SEARCH = form_data.web.search.enabled
request.app.state.config.RAG_WEB_SEARCH_ENGINE = form_data.web.search.engine
request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL = (
form_data.web.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL
)
request.app.state.config.SEARXNG_QUERY_URL = (
form_data.web.search.searxng_query_url
)
@ -628,10 +634,8 @@ async def update_rag_config(
request.app.state.config.SEARCHAPI_ENGINE = (
form_data.web.search.searchapi_engine
)
request.app.state.config.SERPAPI_API_KEY = form_data.web.search.serpapi_api_key
request.app.state.config.SERPAPI_ENGINE = form_data.web.search.serpapi_engine
request.app.state.config.JINA_API_KEY = form_data.web.search.jina_api_key
request.app.state.config.BING_SEARCH_V7_ENDPOINT = (
form_data.web.search.bing_search_v7_endpoint
@ -639,32 +643,59 @@ async def update_rag_config(
request.app.state.config.BING_SEARCH_V7_SUBSCRIPTION_KEY = (
form_data.web.search.bing_search_v7_subscription_key
)
request.app.state.config.EXA_API_KEY = form_data.web.search.exa_api_key
request.app.state.config.PERPLEXITY_API_KEY = (
form_data.web.search.perplexity_api_key
)
request.app.state.config.SOUGOU_API_SID = (
form_data.web.search.sougou_api_sid
)
request.app.state.config.SOUGOU_API_SK = (
form_data.web.search.sougou_api_sk
)
request.app.state.config.SOUGOU_API_SID = form_data.web.search.sougou_api_sid
request.app.state.config.SOUGOU_API_SK = form_data.web.search.sougou_api_sk
request.app.state.config.RAG_WEB_SEARCH_RESULT_COUNT = (
form_data.web.search.result_count
)
request.app.state.config.RAG_WEB_SEARCH_CONCURRENT_REQUESTS = (
form_data.web.search.concurrent_requests
)
request.app.state.config.RAG_WEB_SEARCH_TRUST_ENV = (
form_data.web.search.trust_env
)
request.app.state.config.RAG_WEB_SEARCH_DOMAIN_FILTER_LIST = (
form_data.web.search.domain_filter_list
)
request.app.state.config.RAG_WEB_LOADER_ENGINE = form_data.web.loader.engine
request.app.state.config.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION = (
# Note: When UI "Bypass SSL verification for Websites"=True then ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION=False
form_data.web.loader.enable_ssl_verification
)
request.app.state.config.RAG_WEB_SEARCH_TRUST_ENV = (
form_data.web.loader.trust_env
)
request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL = (
form_data.web.loader.bypass_embedding_and_retrieval
)
request.app.state.config.PLAYWRIGHT_WS_URI = (
form_data.web.loader.playwright_ws_uri
)
request.app.state.config.PLAYWRIGHT_TIMEOUT = (
form_data.web.loader.playwright_timeout
)
request.app.state.config.FIRECRAWL_API_KEY = (
form_data.web.loader.firecrawl_api_key
)
request.app.state.config.FIRECRAWL_API_BASE_URL = (
form_data.web.loader.firecrawl_api_base_url
)
request.app.state.config.TAVILY_API_KEY = form_data.web.loader.tavily_api_key
request.app.state.config.TAVILY_EXTRACT_DEPTH = (
form_data.web.loader.tavily_extract_depth
)
request.app.state.config.YOUTUBE_LOADER_LANGUAGE = (
form_data.web.loader.youtube.language
)
request.app.state.config.YOUTUBE_LOADER_PROXY_URL = (
form_data.web.loader.youtube.proxy_url
)
request.app.state.YOUTUBE_LOADER_TRANSLATION = (
form_data.web.loader.youtube.translation
)
return {
"status": True,
"pdf_extract_images": request.app.state.config.PDF_EXTRACT_IMAGES,
@ -691,16 +722,9 @@ async def update_rag_config(
"chunk_size": request.app.state.config.CHUNK_SIZE,
"chunk_overlap": request.app.state.config.CHUNK_OVERLAP,
},
"youtube": {
"language": request.app.state.config.YOUTUBE_LOADER_LANGUAGE,
"proxy_url": request.app.state.config.YOUTUBE_LOADER_PROXY_URL,
"translation": request.app.state.YOUTUBE_LOADER_TRANSLATION,
},
"web": {
"ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION": request.app.state.config.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION,
"BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL": request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL,
"ENABLE_RAG_WEB_SEARCH": request.app.state.config.ENABLE_RAG_WEB_SEARCH,
"search": {
"enabled": request.app.state.config.ENABLE_RAG_WEB_SEARCH,
"engine": request.app.state.config.RAG_WEB_SEARCH_ENGINE,
"searxng_query_url": request.app.state.config.SEARXNG_QUERY_URL,
"google_pse_api_key": request.app.state.config.GOOGLE_PSE_API_KEY,
@ -713,11 +737,11 @@ async def update_rag_config(
"serpstack_https": request.app.state.config.SERPSTACK_HTTPS,
"serper_api_key": request.app.state.config.SERPER_API_KEY,
"serply_api_key": request.app.state.config.SERPLY_API_KEY,
"serachapi_api_key": request.app.state.config.SEARCHAPI_API_KEY,
"tavily_api_key": request.app.state.config.TAVILY_API_KEY,
"searchapi_api_key": request.app.state.config.SEARCHAPI_API_KEY,
"searchapi_engine": request.app.state.config.SEARCHAPI_ENGINE,
"serpapi_api_key": request.app.state.config.SERPAPI_API_KEY,
"serpapi_engine": request.app.state.config.SERPAPI_ENGINE,
"tavily_api_key": request.app.state.config.TAVILY_API_KEY,
"jina_api_key": request.app.state.config.JINA_API_KEY,
"bing_search_v7_endpoint": request.app.state.config.BING_SEARCH_V7_ENDPOINT,
"bing_search_v7_subscription_key": request.app.state.config.BING_SEARCH_V7_SUBSCRIPTION_KEY,
@ -727,9 +751,25 @@ async def update_rag_config(
"sougou_api_sk": request.app.state.config.SOUGOU_API_SK,
"result_count": request.app.state.config.RAG_WEB_SEARCH_RESULT_COUNT,
"concurrent_requests": request.app.state.config.RAG_WEB_SEARCH_CONCURRENT_REQUESTS,
"trust_env": request.app.state.config.RAG_WEB_SEARCH_TRUST_ENV,
"domain_filter_list": request.app.state.config.RAG_WEB_SEARCH_DOMAIN_FILTER_LIST,
},
"loader": {
"engine": request.app.state.config.RAG_WEB_LOADER_ENGINE,
"enable_ssl_verification": request.app.state.config.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION,
"trust_env": request.app.state.config.RAG_WEB_SEARCH_TRUST_ENV,
"bypass_embedding_and_retrieval": request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL,
"playwright_ws_uri": request.app.state.config.PLAYWRIGHT_WS_URI,
"playwright_timeout": request.app.state.config.PLAYWRIGHT_TIMEOUT,
"firecrawl_api_key": request.app.state.config.FIRECRAWL_API_KEY,
"firecrawl_api_base_url": request.app.state.config.FIRECRAWL_API_BASE_URL,
"tavily_api_key": request.app.state.config.TAVILY_API_KEY,
"tavily_extract_depth": request.app.state.config.TAVILY_EXTRACT_DEPTH,
"youtube": {
"language": request.app.state.config.YOUTUBE_LOADER_LANGUAGE,
"proxy_url": request.app.state.config.YOUTUBE_LOADER_PROXY_URL,
"translation": request.app.state.YOUTUBE_LOADER_TRANSLATION,
},
},
},
}

View File

@ -13,6 +13,11 @@
export let saveHandler: Function;
let webConfig = null;
let bypass_ssl_verification = null;
let tavily_api_key = null;
let youtube_language = null;
let webSearchEngines = [
'searxng',
'google_pse',
@ -33,10 +38,7 @@
'perplexity',
'sougou'
];
let youtubeLanguage = 'en';
let youtubeTranslation = null;
let youtubeProxyUrl = '';
let webLoaderEngines = ['safe_web', 'playwright', 'firecrawl', 'tavily'];
const submitHandler = async () => {
// Convert domain filter string to array before sending
@ -49,16 +51,20 @@
webConfig.search.domain_filter_list = [];
}
// Set the enable_ssl_verification flag based on the switch state
webConfig.loader.enable_ssl_verification = !bypass_ssl_verification;
// Set shared tavily_api_key
webConfig.search.tavily_api_key = tavily_api_key;
webConfig.loader.tavily_api_key = tavily_api_key;
webConfig.loader.youtube.language = youtube_language.split(',').map((lang) => lang.trim());
const res = await updateRAGConfig(localStorage.token, {
web: webConfig,
youtube: {
language: youtubeLanguage.split(',').map((lang) => lang.trim()),
translation: youtubeTranslation,
proxy_url: youtubeProxyUrl
}
web: webConfig
});
webConfig.search.domain_filter_list = webConfig.search.domain_filter_list.join(', ');
youtube_language = webConfig.loader.youtube.language.join(', ');
};
onMount(async () => {
@ -70,10 +76,9 @@
if (webConfig?.search?.domain_filter_list) {
webConfig.search.domain_filter_list = webConfig.search.domain_filter_list.join(', ');
}
youtubeLanguage = res.youtube.language.join(',');
youtubeTranslation = res.youtube.translation;
youtubeProxyUrl = res.youtube.proxy_url;
bypass_ssl_verification = !webConfig.loader.enable_ssl_verification;
tavily_api_key = webConfig.search.tavily_api_key || webConfig.loader.tavily_api_key;
youtube_language = webConfig.loader.youtube.language.join(', ');
}
});
</script>
@ -95,10 +100,10 @@
<div class=" mb-2.5 flex w-full justify-between">
<div class=" self-center text-xs font-medium">
{$i18n.t('Web Search')}
{$i18n.t('Enable Web Search')}
</div>
<div class="flex items-center relative">
<Switch bind:state={webConfig.search.enabled} />
<Switch bind:state={webConfig.ENABLE_RAG_WEB_SEARCH} />
</div>
</div>
@ -197,7 +202,6 @@
bind:value={webConfig.search.kagi_search_api_key}
/>
</div>
.
</div>
{:else if webConfig.search.engine === 'mojeek'}
<div class="mb-2.5 flex w-full flex-col">
@ -333,7 +337,7 @@
<SensitiveInput
placeholder={$i18n.t('Enter Tavily API Key')}
bind:value={webConfig.search.tavily_api_key}
bind:value={tavily_api_key}
/>
</div>
</div>
@ -405,135 +409,208 @@
/>
</div>
</div>
{:else if webConfig.search.engine === 'sougou'}
<div class="mb-2.5 flex w-full flex-col">
<div>
<div class=" self-center text-xs font-medium mb-1">
{$i18n.t('Sougou Search API sID')}
</div>
<SensitiveInput
placeholder={$i18n.t('Enter Sougou Search API sID')}
bind:value={webConfig.search.sougou_api_sid}
/>
{:else if webConfig.search.engine === 'sougou'}
<div class="mb-2.5 flex w-full flex-col">
<div>
<div class=" self-center text-xs font-medium mb-1">
{$i18n.t('Sougou Search API sID')}
</div>
<SensitiveInput
placeholder={$i18n.t('Enter Sougou Search API sID')}
bind:value={webConfig.search.sougou_api_sid}
/>
</div>
<div class="mb-2.5 flex w-full flex-col">
<div>
<div class=" self-center text-xs font-medium mb-1">
{$i18n.t('Sougou Search API SK')}
</div>
<SensitiveInput
placeholder={$i18n.t('Enter Sougou Search API SK')}
bind:value={webConfig.search.sougou_api_sk}
/>
</div>
<div class="mb-2.5 flex w-full flex-col">
<div>
<div class=" self-center text-xs font-medium mb-1">
{$i18n.t('Sougou Search API SK')}
</div>
<SensitiveInput
placeholder={$i18n.t('Enter Sougou Search API SK')}
bind:value={webConfig.search.sougou_api_sk}
/>
</div>
</div>
{/if}
{/if}
{#if webConfig.search.enabled}
<div class="mb-2.5 flex w-full flex-col">
<div class="flex gap-2">
<div class="w-full">
<div class=" self-center text-xs font-medium mb-1">
{$i18n.t('Search Result Count')}
</div>
<input
class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
placeholder={$i18n.t('Search Result Count')}
bind:value={webConfig.search.result_count}
required
/>
<div class="mb-2.5 flex w-full flex-col">
<div class="flex gap-2">
<div class="w-full">
<div class=" self-center text-xs font-medium mb-1">
{$i18n.t('Search Result Count')}
</div>
<div class="w-full">
<div class=" self-center text-xs font-medium mb-1">
{$i18n.t('Concurrent Requests')}
</div>
<input
class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
placeholder={$i18n.t('Search Result Count')}
bind:value={webConfig.search.result_count}
required
/>
</div>
<input
class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
placeholder={$i18n.t('Concurrent Requests')}
bind:value={webConfig.search.concurrent_requests}
required
/>
<div class="w-full">
<div class=" self-center text-xs font-medium mb-1">
{$i18n.t('Concurrent Requests')}
</div>
<input
class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
placeholder={$i18n.t('Concurrent Requests')}
bind:value={webConfig.search.concurrent_requests}
required
/>
</div>
</div>
<div class="mb-2.5 flex w-full flex-col">
<div class=" text-xs font-medium mb-1">
{$i18n.t('Domain Filter List')}
</div>
<input
class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
placeholder={$i18n.t(
'Enter domains separated by commas (e.g., example.com,site.org)'
)}
bind:value={webConfig.search.domain_filter_list}
/>
</div>
{/if}
<div class=" mb-2.5 flex w-full justify-between">
<div class=" self-center text-xs font-medium">
<Tooltip content={$i18n.t('Full Context Mode')} placement="top-start">
{$i18n.t('Bypass Embedding and Retrieval')}
</Tooltip>
</div>
<div class="flex items-center relative">
<Tooltip
content={webConfig.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL
? $i18n.t(
'Inject the entire content as context for comprehensive processing, this is recommended for complex queries.'
)
: $i18n.t(
'Default to segmented retrieval for focused and relevant content extraction, this is recommended for most cases.'
)}
>
<Switch bind:state={webConfig.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL} />
</Tooltip>
</div>
</div>
<div class=" mb-2.5 flex w-full justify-between">
<div class=" self-center text-xs font-medium">
{$i18n.t('Trust Proxy Environment')}
<div class="mb-2.5 flex w-full flex-col">
<div class=" text-xs font-medium mb-1">
{$i18n.t('Domain Filter List')}
</div>
<div class="flex items-center relative">
<Tooltip
content={webConfig.search.trust_env
? $i18n.t(
'Use proxy designated by http_proxy and https_proxy environment variables to fetch page contents.'
)
: $i18n.t(
'Use no proxy to fetch page contents.'
)}
>
<Switch bind:state={webConfig.search.trust_env} />
</Tooltip>
</div>
</div>
</div>
<div class="mb-3">
<input
class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300dark:bg-gray-850 outline-hidden"
placeholder={$i18n.t(
'Enter domains separated by commas (e.g., example.com,site.org)'
)}
bind:value={webConfig.search.domain_filter_list}
/>
</div>
<div class=" mb-2.5 text-base font-medium">{$i18n.t('Loader')}</div>
<hr class=" border-gray-100 dark:border-gray-850 my-2" />
<div class=" mb-2.5 flex w-full justify-between">
<div class=" self-center text-xs font-medium">
{$i18n.t('Bypass SSL verification for Websites')}
{$i18n.t('Web Loader Engine')}
</div>
<div class="flex items-center relative">
<Switch bind:state={webConfig.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION} />
<select
class="dark:bg-gray-900 w-fit pr-8 rounded-sm px-2 p-1 text-xs bg-transparent outline-hidden text-right"
bind:value={webConfig.loader.engine}
placeholder={$i18n.t('Select a engine')}
required
>
<option disabled selected value="">{$i18n.t('Select a engine')}</option>
{#each webLoaderEngines as engine}
<option value={engine}>{engine}</option>
{/each}
</select>
</div>
</div>
{#if webConfig.loader.engine !== ''}
{#if webConfig.loader.engine === 'playwright'}
<div class="mb-2.5 flex w-full flex-col">
<div>
<div class=" self-center text-xs font-medium mb-1">
{$i18n.t('Playwright WebSocket URL')}
</div>
<div class="flex w-full">
<div class="flex-1">
<input
class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
type="text"
placeholder={$i18n.t('Enter Playwright WebSocket URL')}
bind:value={webConfig.loader.playwright_ws_uri}
autocomplete="off"
/>
</div>
</div>
</div>
<div class="mt-2">
<div class=" self-center text-xs font-medium mb-1">
{$i18n.t('Playwright Timeout (ms)')}
</div>
<div class="flex w-full">
<div class="flex-1">
<input
class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
placeholder={$i18n.t('Enter Playwright Timeout (ms)')}
bind:value={webConfig.loader.playwright_timeout}
autocomplete="off"
/>
</div>
</div>
</div>
</div>
{:else if webConfig.loader.engine === 'firecrawl'}
<div class="mb-2.5 flex w-full flex-col">
<div>
<div class=" self-center text-xs font-medium mb-1">
{$i18n.t('Firecrawl API Base URL')}
</div>
<div class="flex w-full">
<div class="flex-1">
<input
class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
type="text"
placeholder={$i18n.t('Enter Firecrawl API Base URL')}
bind:value={webConfig.loader.firecrawl_api_base_url}
autocomplete="off"
/>
</div>
</div>
</div>
<div class="mt-2">
<div class=" self-center text-xs font-medium mb-1">
{$i18n.t('Firecrawl API Key')}
</div>
<SensitiveInput
placeholder={$i18n.t('Enter Firecrawl API Key')}
bind:value={webConfig.loader.firecrawl_api_key}
/>
</div>
</div>
{:else if webConfig.loader.engine === 'tavily'}
<div class="mb-2.5 flex w-full flex-col">
<div>
<div class=" self-center text-xs font-medium mb-1">
{$i18n.t('Tavily Extract Depth')}
</div>
<div class="flex w-full">
<div class="flex-1">
<input
class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
type="text"
placeholder={$i18n.t('Enter Tavily Extract Depth')}
bind:value={webConfig.loader.tavily_extract_depth}
autocomplete="off"
/>
</div>
</div>
</div>
{#if webConfig.search.engine !== 'tavily'}
<div class="mt-2">
<div class=" self-center text-xs font-medium mb-1">
{$i18n.t('Tavily API Key')}
</div>
<SensitiveInput
placeholder={$i18n.t('Enter Tavily API Key')}
bind:value={tavily_api_key}
/>
</div>
{/if}
</div>
{/if}
{/if}
<hr class=" border-gray-100 dark:border-gray-850 my-2" />
<div class=" mb-2.5 flex w-full justify-between">
<div class=" self-center text-xs font-medium">
{$i18n.t('Youtube Language')}
@ -543,7 +620,7 @@
class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
type="text"
placeholder={$i18n.t('Enter language codes')}
bind:value={youtubeLanguage}
bind:value={youtube_language}
autocomplete="off"
/>
</div>
@ -555,14 +632,63 @@
</div>
<div class="flex items-center relative">
<input
class="flex-1 w-full rounded-lg text-sm bg-transparent outline-hidden"
class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
type="text"
placeholder={$i18n.t('Enter proxy URL (e.g. https://user:password@host:port)')}
bind:value={youtubeProxyUrl}
bind:value={webConfig.loader.youtube.proxy_url}
autocomplete="off"
/>
</div>
</div>
<hr class=" border-gray-100 dark:border-gray-850 my-2" />
<div class=" mb-2.5 flex w-full justify-between">
<div class=" self-center text-xs font-medium">
{$i18n.t('Bypass SSL verification for Websites')}
</div>
<div class="flex items-center relative">
<Switch bind:state={bypass_ssl_verification} />
</div>
</div>
<div class=" mb-2.5 flex w-full justify-between">
<div class=" self-center text-xs font-medium">
{$i18n.t('Trust Proxy Environment')}
</div>
<div class="flex items-center relative">
<Tooltip
content={webConfig.loader.trust_env
? $i18n.t(
'Use proxy designated by http_proxy and https_proxy environment variables to fetch page contents.'
)
: $i18n.t('Use no proxy to fetch page contents.')}
>
<Switch bind:state={webConfig.loader.trust_env} />
</Tooltip>
</div>
</div>
<div class=" mb-2.5 flex w-full justify-between">
<div class=" self-center text-xs font-medium">
<Tooltip content={$i18n.t('Full Context Mode')} placement="top-start">
{$i18n.t('Bypass Embedding and Retrieval')}
</Tooltip>
</div>
<div class="flex items-center relative">
<Tooltip
content={webConfig.loader.bypass_embedding_and_retrieval
? $i18n.t(
'Inject the entire content as context for comprehensive processing, this is recommended for complex queries.'
)
: $i18n.t(
'Default to segmented retrieval for focused and relevant content extraction, this is recommended for most cases.'
)}
>
<Switch bind:state={webConfig.loader.bypass_embedding_and_retrieval} />
</Tooltip>
</div>
</div>
</div>
</div>
{/if}