refactor: replace requests with Firecrawl SDK in search and requests Firecrawl SDK in scrape rather than langchain_community FireCrawlLoader

backend/open_webui/retrieval/web/firecrawl.py

@@ -1,11 +1,11 @@
 import logging
 from typing import Optional, List
-from urllib.parse import urljoin
 
-import requests
 from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 from open_webui.env import SRC_LOG_LEVELS
 
+from firecrawl import Firecrawl
+
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["RAG"])
 
@@ -18,27 +18,18 @@ def search_firecrawl(
     filter_list: Optional[List[str]] = None,
 ) -> List[SearchResult]:
     try:
-        firecrawl_search_url = urljoin(firecrawl_url, "/v1/search")
-        response = requests.post(
-            firecrawl_search_url,
-            headers={
-                "User-Agent": "Open WebUI (https://github.com/open-webui/open-webui) RAG Bot",
-                "Authorization": f"Bearer {firecrawl_api_key}",
-            },
-            json={
-                "query": query,
-                "limit": count,
-            },
+        firecrawl = Firecrawl(api_key=firecrawl_api_key, api_url=firecrawl_url)
+        response = firecrawl.search(
+            query=query, limit=count, ignore_invalid_urls=True, timeout=count * 3
         )
-        response.raise_for_status()
-        results = response.json().get("data", [])
+        results = response.web
         if filter_list:
             results = get_filtered_results(results, filter_list)
         results = [
             SearchResult(
-                link=result.get("url"),
-                title=result.get("title"),
-                snippet=result.get("description"),
+                link=result.url,
+                title=result.title,
+                snippet=result.description,
             )
             for result in results[:count]
         ]