Add yacy config for user/pass, automatically add yacy json api path

This commit is contained in:
Stephen Smith 2025-04-26 21:27:55 -04:00
parent 0f73b96616
commit 240d91d38d
5 changed files with 67 additions and 7 deletions

View File

@ -2093,6 +2093,18 @@ YACY_QUERY_URL = PersistentConfig(
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",

View File

@ -220,6 +220,8 @@ from open_webui.config import (
SERPAPI_ENGINE,
SEARXNG_QUERY_URL,
YACY_QUERY_URL,
YACY_USERNAME,
YACY_PASSWORD,
SERPER_API_KEY,
SERPLY_API_KEY,
SERPSTACK_API_KEY,
@ -648,6 +650,8 @@ app.state.config.ENABLE_GOOGLE_DRIVE_INTEGRATION = ENABLE_GOOGLE_DRIVE_INTEGRATI
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

View File

@ -12,6 +12,8 @@ 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,
@ -46,6 +48,11 @@ def search_yacy(
time_range = kwargs.get("time_range", "")
categories = "".join(kwargs.get("categories", []))
# Use authentication if either username or password is set
yacy_auth = None
if username or password:
yacy_auth = HTTPDigestAuth(username, password)
params = {
"query": query,
"resource": "global",
@ -60,16 +67,16 @@ def search_yacy(
# "image_proxy": 0,
}
# Legacy query format
if "<query>" in query_url:
# 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.split("?")[0]
query_url = query_url.rstrip('/') + "/yacysearch.json"
log.debug(f"searching {query_url}")
response = requests.get(
query_url,
auth=HTTPDigestAuth('admin', 'yacy'),
auth=yacy_auth,
headers={
"User-Agent": "Open WebUI (https://github.com/open-webui/open-webui) RAG Bot",
"Accept": "text/html",

View File

@ -391,6 +391,8 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
"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,
@ -437,6 +439,8 @@ class WebConfig(BaseModel):
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
@ -655,6 +659,8 @@ async def update_rag_config(
)
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
@ -754,6 +760,8 @@ async def update_rag_config(
"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,
@ -1271,7 +1279,7 @@ 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_QUERY_URL + YACY_USERNAME + YACY_PASSWORD
- GOOGLE_PSE_API_KEY + GOOGLE_PSE_ENGINE_ID
- BRAVE_SEARCH_API_KEY
- KAGI_SEARCH_API_KEY
@ -1305,6 +1313,8 @@ def search_web(request: Request, engine: str, query: str) -> list[SearchResult]:
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,

View File

@ -148,7 +148,7 @@
<div class="mb-2.5 flex w-full flex-col">
<div>
<div class=" self-center text-xs font-medium mb-1">
{$i18n.t('Yacy Query URL')}
{$i18n.t('Yacy Instance URL')}
</div>
<div class="flex w-full">
@ -156,7 +156,7 @@
<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={$i18n.t('Enter Yacy Query URL')}
placeholder={$i18n.t('Enter Yacy URL (e.g. http://yacy.example.com:8090)')}
bind:value={webConfig.YACY_QUERY_URL}
autocomplete="off"
/>
@ -164,6 +164,33 @@
</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>