浏览代码

Merge pull request #13311 from stephen304/yacy-support

feat: Yacy search support
Tim Jaeryang Baek 5 月之前
父节点
当前提交
7b863465a9

+ 18 - 0
backend/open_webui/config.py

@@ -2135,6 +2135,24 @@ 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", ""),
+)
+
+YACY_USERNAME = PersistentConfig(
+    "YACY_USERNAME",
+    "rag.web.search.yacy_username",
+    os.getenv("YACY_USERNAME", ""),
+)
+
+YACY_PASSWORD = PersistentConfig(
+    "YACY_PASSWORD",
+    "rag.web.search.yacy_password",
+    os.getenv("YACY_PASSWORD", ""),
+)
+
 GOOGLE_PSE_API_KEY = PersistentConfig(
     "GOOGLE_PSE_API_KEY",
     "rag.web.search.google_pse_api_key",

+ 6 - 0
backend/open_webui/main.py

@@ -223,6 +223,9 @@ from open_webui.config import (
     SERPAPI_API_KEY,
     SERPAPI_ENGINE,
     SEARXNG_QUERY_URL,
+    YACY_QUERY_URL,
+    YACY_USERNAME,
+    YACY_PASSWORD,
     SERPER_API_KEY,
     SERPLY_API_KEY,
     SERPSTACK_API_KEY,
@@ -662,6 +665,9 @@ 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.YACY_USERNAME = YACY_USERNAME
+app.state.config.YACY_PASSWORD = YACY_PASSWORD
 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

+ 85 - 0
backend/open_webui/retrieval/web/yacy.py

@@ -0,0 +1,85 @@
+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,
+    username: Optional[str],
+    password: Optional[str],
+    query: str,
+    count: int,
+    filter_list: Optional[list[str]] = None,
+) -> list[SearchResult]:
+    """
+    Search a Yacy instance for a given query and return the results as a list of SearchResult objects.
+
+    The function accepts username and password for authenticating to Yacy.
+
+    Args:
+        query_url (str): The base URL of the Yacy server.
+        username (str): Optional YaCy username.
+        password (str): Optional YaCy password.
+        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.
+
+    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.
+    """
+
+    # Use authentication if either username or password is set
+    yacy_auth = None
+    if username or password:
+        yacy_auth = HTTPDigestAuth(username, password)
+
+    params = {
+        "query": query,
+        "contentdom": "text",
+        "resource": "global",
+        "maximumRecords": count,
+        "nav": "none",
+    }
+
+    # Check if provided a json API URL
+    if not query_url.endswith("yacysearch.json"):
+        # Strip all query parameters from the URL
+        query_url = query_url.rstrip('/') + "/yacysearch.json"
+
+    log.debug(f"searching {query_url}")
+
+    response = requests.get(
+        query_url,
+        auth=yacy_auth,
+        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]
+    ]

+ 26 - 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
@@ -399,6 +400,9 @@ 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,
+            "YACY_USERNAME": request.app.state.config.YACY_USERNAME,
+            "YACY_PASSWORD": request.app.state.config.YACY_PASSWORD,
             "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,
@@ -448,6 +452,9 @@ 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
+    YACY_USERNAME: Optional[str] = None
+    YACY_PASSWORD: Optional[str] = None
     GOOGLE_PSE_API_KEY: Optional[str] = None
     GOOGLE_PSE_ENGINE_ID: Optional[str] = None
     BRAVE_SEARCH_API_KEY: Optional[str] = None
@@ -669,6 +676,9 @@ 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.YACY_USERNAME = form_data.web.YACY_USERNAME
+        request.app.state.config.YACY_PASSWORD = form_data.web.YACY_PASSWORD
         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
@@ -779,6 +789,9 @@ 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,
+            "YACY_USERNAME": request.app.state.config.YACY_USERNAME,
+            "YACY_PASSWORD": request.app.state.config.YACY_PASSWORD,
             "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,
@@ -1300,6 +1313,7 @@ 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 + YACY_USERNAME + YACY_PASSWORD
     - GOOGLE_PSE_API_KEY + GOOGLE_PSE_ENGINE_ID
     - BRAVE_SEARCH_API_KEY
     - KAGI_SEARCH_API_KEY
@@ -1329,6 +1343,18 @@ 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,
+                request.app.state.config.YACY_USERNAME,
+                request.app.state.config.YACY_PASSWORD,
+                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

+ 48 - 0
src/lib/components/admin/Settings/WebSearch.svelte

@@ -14,6 +14,7 @@
 
 	let webSearchEngines = [
 		'searxng',
+		'yacy',
 		'google_pse',
 		'brave',
 		'kagi',
@@ -144,6 +145,53 @@
 									</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">
+										{$i18n.t('Yacy Instance URL')}
+									</div>
+
+									<div class="flex w-full">
+										<div class="flex-1">
+											<input
+												class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
+												type="text"
+												placeholder={$i18n.t('Enter Yacy URL (e.g. http://yacy.example.com:8090)')}
+												bind:value={webConfig.YACY_QUERY_URL}
+												autocomplete="off"
+											/>
+										</div>
+									</div>
+								</div>
+							</div>
+							<div class="mb-2.5 flex w-full flex-col">
+								<div class="flex gap-2">
+									<div class="w-full">
+										<div class=" self-center text-xs font-medium mb-1">
+											{$i18n.t('Yacy Username')}
+										</div>
+
+										<input
+											class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
+											placeholder={$i18n.t('Enter Yacy Username')}
+											bind:value={webConfig.YACY_USERNAME}
+											required
+										/>
+									</div>
+
+									<div class="w-full">
+										<div class=" self-center text-xs font-medium mb-1">
+											{$i18n.t('Yacy Password')}
+										</div>
+
+										<SensitiveInput
+											placeholder={$i18n.t('Enter Yacy Password')}
+											bind:value={webConfig.YACY_PASSWORD}
+										/>
+									</div>
+								</div>
+							</div>
 						{:else if webConfig.WEB_SEARCH_ENGINE === 'google_pse'}
 							<div class="mb-2.5 flex w-full flex-col">
 								<div>