fix depth param issue for WaterCrawl (#18839)

wesleysui · web-flow · commit b62eb61400ae · 2025-04-27T11:04:56.000+08:00
diff --git a/api/core/rag/extractor/watercrawl/provider.py b/api/core/rag/extractor/watercrawl/provider.py
@@ -20,7 +20,7 @@ def crawl_url(self, url, options: dict | Any = None) -> dict:
         }
         if options.get("crawl_sub_pages", True):
             spider_options["page_limit"] = options.get("limit", 1)
-            spider_options["max_depth"] = options.get("depth", 1)
+            spider_options["max_depth"] = options.get("max_depth", 1)
             spider_options["include_paths"] = options.get("includes", "").split(",") if options.get("includes") else []
             spider_options["exclude_paths"] = options.get("excludes", "").split(",") if options.get("excludes") else []
 

Original file line number	Diff line number	Diff line change
`@@ -20,7 +20,7 @@ def crawl_url(self, url, options: dict \| Any = None) -> dict:`
`20`	`20`	`}`
`21`	`21`	`if options.get("crawl_sub_pages", True):`
`22`	`22`	`spider_options["page_limit"] = options.get("limit", 1)`
`23`		`- spider_options["max_depth"] = options.get("depth", 1)`
	`23`	`+ spider_options["max_depth"] = options.get("max_depth", 1)`
`24`	`24`	`spider_options["include_paths"] = options.get("includes", "").split(",") if options.get("includes") else []`
`25`	`25`	`spider_options["exclude_paths"] = options.get("excludes", "").split(",") if options.get("excludes") else []`
`26`	`26`