This commit is contained in:
Timothy Jaeryang Baek
2026-06-17 02:52:35 +02:00
parent e8d55c0a8b
commit 5cdcdbaeec
53 changed files with 7829 additions and 7954 deletions
+19 -20
View File
@@ -21,7 +21,6 @@ from typing import (
import aiohttp
import aiohttp.resolver
import certifi
import requests
import urllib3.connection
import urllib3.connectionpool
import validators
@@ -777,13 +776,13 @@ def get_web_loader(
'trust_env': trust_env,
}
if WEB_LOADER_ENGINE.value == '' or WEB_LOADER_ENGINE.value == 'safe_web':
if WEB_LOADER_ENGINE == '' or WEB_LOADER_ENGINE == 'safe_web':
WebLoaderClass = SafeWebBaseLoader
request_kwargs = {}
if WEB_LOADER_TIMEOUT.value:
if WEB_LOADER_TIMEOUT:
try:
timeout_value = float(WEB_LOADER_TIMEOUT.value)
timeout_value = float(WEB_LOADER_TIMEOUT)
except ValueError:
timeout_value = None
@@ -793,31 +792,31 @@ def get_web_loader(
if request_kwargs:
web_loader_args['requests_kwargs'] = request_kwargs
if WEB_LOADER_ENGINE.value == 'playwright':
if WEB_LOADER_ENGINE == 'playwright':
WebLoaderClass = SafePlaywrightURLLoader
web_loader_args['playwright_timeout'] = PLAYWRIGHT_TIMEOUT.value
if PLAYWRIGHT_WS_URL.value:
web_loader_args['playwright_ws_url'] = PLAYWRIGHT_WS_URL.value
web_loader_args['playwright_timeout'] = PLAYWRIGHT_TIMEOUT
if PLAYWRIGHT_WS_URL:
web_loader_args['playwright_ws_url'] = PLAYWRIGHT_WS_URL
if WEB_LOADER_ENGINE.value == 'firecrawl':
if WEB_LOADER_ENGINE == 'firecrawl':
WebLoaderClass = SafeFireCrawlLoader
web_loader_args['api_key'] = FIRECRAWL_API_KEY.value
web_loader_args['api_url'] = FIRECRAWL_API_BASE_URL.value
if FIRECRAWL_TIMEOUT.value:
web_loader_args['api_key'] = FIRECRAWL_API_KEY
web_loader_args['api_url'] = FIRECRAWL_API_BASE_URL
if FIRECRAWL_TIMEOUT:
try:
web_loader_args['timeout'] = int(FIRECRAWL_TIMEOUT.value)
web_loader_args['timeout'] = int(FIRECRAWL_TIMEOUT)
except ValueError:
pass
if WEB_LOADER_ENGINE.value == 'tavily':
if WEB_LOADER_ENGINE == 'tavily':
WebLoaderClass = SafeTavilyLoader
web_loader_args['api_key'] = TAVILY_API_KEY.value
web_loader_args['extract_depth'] = TAVILY_EXTRACT_DEPTH.value
web_loader_args['api_key'] = TAVILY_API_KEY
web_loader_args['extract_depth'] = TAVILY_EXTRACT_DEPTH
if WEB_LOADER_ENGINE.value == 'external':
if WEB_LOADER_ENGINE == 'external':
WebLoaderClass = ExternalWebLoader
web_loader_args['external_url'] = EXTERNAL_WEB_LOADER_URL.value
web_loader_args['external_api_key'] = EXTERNAL_WEB_LOADER_API_KEY.value
web_loader_args['external_url'] = EXTERNAL_WEB_LOADER_URL
web_loader_args['external_api_key'] = EXTERNAL_WEB_LOADER_API_KEY
if WebLoaderClass:
web_loader = WebLoaderClass(**web_loader_args)
@@ -831,6 +830,6 @@ def get_web_loader(
return web_loader
else:
raise ValueError(
f'Invalid WEB_LOADER_ENGINE: {WEB_LOADER_ENGINE.value}. '
f'Invalid WEB_LOADER_ENGINE: {WEB_LOADER_ENGINE}. '
"Please set it to 'safe_web', 'playwright', 'firecrawl', or 'tavily'."
)