From 7fefbb316dd3b58dd4b2139eb92d6cb3d3fb24a2 Mon Sep 17 00:00:00 2001
From: Jun Siang Cheah <git@jscheah.me>
Date: Mon, 3 Jun 2024 21:13:10 +0100
Subject: [PATCH] fix: add backwards compat with older searxng urls

---
 backend/apps/rag/search/searxng.py | 40 +++++++++++++++++-------------
 1 file changed, 23 insertions(+), 17 deletions(-)

diff --git a/backend/apps/rag/search/searxng.py b/backend/apps/rag/search/searxng.py
index 24f9985a9..bf38ce0d3 100644
--- a/backend/apps/rag/search/searxng.py
+++ b/backend/apps/rag/search/searxng.py
@@ -10,48 +10,54 @@ log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
-def search_searxng(query_url: str, query: str, count: int, **kwargs) -> List[SearchResult]:
+def search_searxng(
+    query_url: str, query: str, count: int, **kwargs
+) -> List[SearchResult]:
     """
     Search a SearXNG instance for a given query and return the results as a list of SearchResult objects.
-    
+
     The function allows passing additional parameters such as language or time_range to tailor the search result.
 
     Args:
-        query_url (str): The base URL of the SearXNG server with a placeholder for the query "<query>".
+        query_url (str): The base URL of the SearXNG server.
         query (str): The search term or question to find in the SearXNG database.
         count (int): The maximum number of results to retrieve from the search.
-        
+
     Keyword Args:
         language (str): Language filter for the search results; e.g., "en-US". Defaults to an empty string.
         time_range (str): Time range for filtering results by date; e.g., "2023-04-05..today" or "all-time". Defaults to ''.
         categories: (Optional[List[str]]): Specific categories within which the search should be performed, defaulting to an empty string if not provided.
-    
+
     Returns:
         List[SearchResult]: A list of SearchResults sorted by relevance score in descending order.
-        
+
     Raise:
         requests.exceptions.RequestException: If a request error occurs during the search process.
     """
-    
+
     # Default values for optional parameters are provided as empty strings or None when not specified.
-    language = kwargs.get('language', 'en-US')
-    time_range = kwargs.get('time_range', '')
-    categories = ''.join(kwargs.get('categories', []))
+    language = kwargs.get("language", "en-US")
+    time_range = kwargs.get("time_range", "")
+    categories = "".join(kwargs.get("categories", []))
 
     params = {
         "q": query,
         "format": "json",
         "pageno": 1,
         "results_per_page": count,
-        'language': language,
-        'time_range': time_range,
-        'engines': '',
-        'categories': categories,
-        'theme': 'simple',
-        'image_proxy': 0
-
+        "language": language,
+        "time_range": time_range,
+        "engines": "",
+        "categories": categories,
+        "theme": "simple",
+        "image_proxy": 0,
     }
 
+    # Legacy query format
+    if "<query>" in query_url:
+        # Strip all query parameters from the URL
+        query_url = query_url.split("?")[0]
+
     log.debug(f"searching {query_url}")
 
     response = requests.get(