瀏覽代碼

first pass at yacy support copied from searxng

Stephen Smith 5 月之前
父節點
當前提交
0f73b96616

+ 6 - 0
backend/open_webui/config.py

@@ -2087,6 +2087,12 @@ SEARXNG_QUERY_URL = PersistentConfig(
     os.getenv("SEARXNG_QUERY_URL", ""),
 )
 
+YACY_QUERY_URL = PersistentConfig(
+    "YACY_QUERY_URL",
+    "rag.web.search.yacy_query_url",
+    os.getenv("YACY_QUERY_URL", ""),
+)
+
 GOOGLE_PSE_API_KEY = PersistentConfig(
     "GOOGLE_PSE_API_KEY",
     "rag.web.search.google_pse_api_key",

+ 2 - 0
backend/open_webui/main.py

@@ -219,6 +219,7 @@ from open_webui.config import (
     SERPAPI_API_KEY,
     SERPAPI_ENGINE,
     SEARXNG_QUERY_URL,
+    YACY_QUERY_URL,
     SERPER_API_KEY,
     SERPLY_API_KEY,
     SERPSTACK_API_KEY,
@@ -646,6 +647,7 @@ app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL = (
 app.state.config.ENABLE_GOOGLE_DRIVE_INTEGRATION = ENABLE_GOOGLE_DRIVE_INTEGRATION
 app.state.config.ENABLE_ONEDRIVE_INTEGRATION = ENABLE_ONEDRIVE_INTEGRATION
 app.state.config.SEARXNG_QUERY_URL = SEARXNG_QUERY_URL
+app.state.config.YACY_QUERY_URL = YACY_QUERY_URL
 app.state.config.GOOGLE_PSE_API_KEY = GOOGLE_PSE_API_KEY
 app.state.config.GOOGLE_PSE_ENGINE_ID = GOOGLE_PSE_ENGINE_ID
 app.state.config.BRAVE_SEARCH_API_KEY = BRAVE_SEARCH_API_KEY

+ 95 - 0
backend/open_webui/retrieval/web/yacy.py

@@ -0,0 +1,95 @@
+import logging
+from typing import Optional
+
+import requests
+from requests.auth import HTTPDigestAuth
+from open_webui.retrieval.web.main import SearchResult, get_filtered_results
+from open_webui.env import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+
+
+def search_yacy(
+    query_url: str,
+    query: str,
+    count: int,
+    filter_list: Optional[list[str]] = None,
+    **kwargs,
+) -> list[SearchResult]:
+    """
+    Search a Yacy 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 Yacy server.
+        query (str): The search term or question to find in the Yacy 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.
+        safesearch (int): Safe search filter for safer web results; 0 = off, 1 = moderate, 2 = strict. Defaults to 1 (moderate).
+        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")
+    safesearch = kwargs.get("safesearch", "1")
+    time_range = kwargs.get("time_range", "")
+    categories = "".join(kwargs.get("categories", []))
+
+    params = {
+        "query": query,
+        "resource": "global",
+        "nav": "all",
+        # "format": "json",
+        # "pageno": 1,
+        # "safesearch": safesearch,
+        # "language": language,
+        # "time_range": time_range,
+        # "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(
+        query_url,
+        auth=HTTPDigestAuth('admin', 'yacy'),
+        headers={
+            "User-Agent": "Open WebUI (https://github.com/open-webui/open-webui) RAG Bot",
+            "Accept": "text/html",
+            "Accept-Encoding": "gzip, deflate",
+            "Accept-Language": "en-US,en;q=0.5",
+            "Connection": "keep-alive",
+        },
+        params=params,
+    )
+
+    response.raise_for_status()  # Raise an exception for HTTP errors.
+
+    json_response = response.json()
+    results = json_response.get("channels", [{}])[0].get("items", [])
+    sorted_results = sorted(results, key=lambda x: x.get("ranking", 0), reverse=True)
+    if filter_list:
+        sorted_results = get_filtered_results(sorted_results, filter_list)
+    return [
+        SearchResult(
+            link=result["link"], title=result.get("title"), snippet=result.get("description")
+        )
+        for result in sorted_results[:count]
+    ]

+ 16 - 0
backend/open_webui/routers/retrieval.py

@@ -53,6 +53,7 @@ from open_webui.retrieval.web.jina_search import search_jina
 from open_webui.retrieval.web.searchapi import search_searchapi
 from open_webui.retrieval.web.serpapi import search_serpapi
 from open_webui.retrieval.web.searxng import search_searxng
+from open_webui.retrieval.web.yacy import search_yacy
 from open_webui.retrieval.web.serper import search_serper
 from open_webui.retrieval.web.serply import search_serply
 from open_webui.retrieval.web.serpstack import search_serpstack
@@ -389,6 +390,7 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
             "WEB_SEARCH_DOMAIN_FILTER_LIST": request.app.state.config.WEB_SEARCH_DOMAIN_FILTER_LIST,
             "BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL": request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL,
             "SEARXNG_QUERY_URL": request.app.state.config.SEARXNG_QUERY_URL,
+            "YACY_QUERY_URL": request.app.state.config.YACY_QUERY_URL,
             "GOOGLE_PSE_API_KEY": request.app.state.config.GOOGLE_PSE_API_KEY,
             "GOOGLE_PSE_ENGINE_ID": request.app.state.config.GOOGLE_PSE_ENGINE_ID,
             "BRAVE_SEARCH_API_KEY": request.app.state.config.BRAVE_SEARCH_API_KEY,
@@ -434,6 +436,7 @@ class WebConfig(BaseModel):
     WEB_SEARCH_DOMAIN_FILTER_LIST: Optional[List[str]] = []
     BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL: Optional[bool] = None
     SEARXNG_QUERY_URL: Optional[str] = None
+    YACY_QUERY_URL: Optional[str] = None
     GOOGLE_PSE_API_KEY: Optional[str] = None
     GOOGLE_PSE_ENGINE_ID: Optional[str] = None
     BRAVE_SEARCH_API_KEY: Optional[str] = None
@@ -651,6 +654,7 @@ async def update_rag_config(
             form_data.web.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL
         )
         request.app.state.config.SEARXNG_QUERY_URL = form_data.web.SEARXNG_QUERY_URL
+        request.app.state.config.YACY_QUERY_URL = form_data.web.YACY_QUERY_URL
         request.app.state.config.GOOGLE_PSE_API_KEY = form_data.web.GOOGLE_PSE_API_KEY
         request.app.state.config.GOOGLE_PSE_ENGINE_ID = (
             form_data.web.GOOGLE_PSE_ENGINE_ID
@@ -749,6 +753,7 @@ async def update_rag_config(
             "WEB_SEARCH_DOMAIN_FILTER_LIST": request.app.state.config.WEB_SEARCH_DOMAIN_FILTER_LIST,
             "BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL": request.app.state.config.BYPASS_WEB_SEARCH_EMBEDDING_AND_RETRIEVAL,
             "SEARXNG_QUERY_URL": request.app.state.config.SEARXNG_QUERY_URL,
+            "YACY_QUERY_URL": request.app.state.config.YACY_QUERY_URL,
             "GOOGLE_PSE_API_KEY": request.app.state.config.GOOGLE_PSE_API_KEY,
             "GOOGLE_PSE_ENGINE_ID": request.app.state.config.GOOGLE_PSE_ENGINE_ID,
             "BRAVE_SEARCH_API_KEY": request.app.state.config.BRAVE_SEARCH_API_KEY,
@@ -1266,6 +1271,7 @@ def search_web(request: Request, engine: str, query: str) -> list[SearchResult]:
     """Search the web using a search engine and return the results as a list of SearchResult objects.
     Will look for a search engine API key in environment variables in the following order:
     - SEARXNG_QUERY_URL
+    - YACY_QUERY_URL
     - GOOGLE_PSE_API_KEY + GOOGLE_PSE_ENGINE_ID
     - BRAVE_SEARCH_API_KEY
     - KAGI_SEARCH_API_KEY
@@ -1295,6 +1301,16 @@ def search_web(request: Request, engine: str, query: str) -> list[SearchResult]:
             )
         else:
             raise Exception("No SEARXNG_QUERY_URL found in environment variables")
+    elif engine == "yacy":
+        if request.app.state.config.YACY_QUERY_URL:
+            return search_yacy(
+                request.app.state.config.YACY_QUERY_URL,
+                query,
+                request.app.state.config.WEB_SEARCH_RESULT_COUNT,
+                request.app.state.config.WEB_SEARCH_DOMAIN_FILTER_LIST,
+            )
+        else:
+            raise Exception("No YACY_QUERY_URL found in environment variables")
     elif engine == "google_pse":
         if (
             request.app.state.config.GOOGLE_PSE_API_KEY

+ 21 - 0
src/lib/components/admin/Settings/WebSearch.svelte

@@ -14,6 +14,7 @@
 
 	let webSearchEngines = [
 		'searxng',
+		'yacy',
 		'google_pse',
 		'brave',
 		'kagi',
@@ -143,6 +144,26 @@
 									</div>
 								</div>
 							</div>
+						{:else if webConfig.WEB_SEARCH_ENGINE === 'yacy'}
+							<div class="mb-2.5 flex w-full flex-col">
+								<div>
+									<div class=" self-center text-xs font-medium mb-1">
+										{$i18n.t('Yacy Query URL')}
+									</div>
+
+									<div class="flex w-full">
+										<div class="flex-1">
+											<input
+												class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
+												type="text"
+												placeholder={$i18n.t('Enter Yacy Query URL')}
+												bind:value={webConfig.YACY_QUERY_URL}
+												autocomplete="off"
+											/>
+										</div>
+									</div>
+								</div>
+							</div>
 						{:else if webConfig.WEB_SEARCH_ENGINE === 'google_pse'}
 							<div class="mb-2.5 flex w-full flex-col">
 								<div>