feat: brave search llm context
This commit is contained in:
1 parent
1baf73bdd5
commit
6700f7bb72
6 files changed
+127
-1
No files matched your search
@@ -3345,6 +3345,12 @@ BRAVE_SEARCH_API_KEY = PersistentConfig(
|
|||||||
os.getenv('BRAVE_SEARCH_API_KEY', ''),
|
os.getenv('BRAVE_SEARCH_API_KEY', ''),
|
||||||
)
|
)
|
||||||
|
|
||||||
|
BRAVE_SEARCH_CONTEXT_TOKENS = PersistentConfig(
|
||||||
|
'BRAVE_SEARCH_CONTEXT_TOKENS',
|
||||||
|
'rag.web.search.brave_search_context_tokens',
|
||||||
|
int(os.getenv('BRAVE_SEARCH_CONTEXT_TOKENS', '8192')),
|
||||||
|
)
|
||||||
|
|
||||||
KAGI_SEARCH_API_KEY = PersistentConfig(
|
KAGI_SEARCH_API_KEY = PersistentConfig(
|
||||||
'KAGI_SEARCH_API_KEY',
|
'KAGI_SEARCH_API_KEY',
|
||||||
'rag.web.search.kagi_search_api_key',
|
'rag.web.search.kagi_search_api_key',
|
||||||
|
|||||||
@@ -345,6 +345,7 @@ from open_webui.config import (
|
|||||||
BING_SEARCH_V7_ENDPOINT,
|
BING_SEARCH_V7_ENDPOINT,
|
||||||
BING_SEARCH_V7_SUBSCRIPTION_KEY,
|
BING_SEARCH_V7_SUBSCRIPTION_KEY,
|
||||||
BRAVE_SEARCH_API_KEY,
|
BRAVE_SEARCH_API_KEY,
|
||||||
|
BRAVE_SEARCH_CONTEXT_TOKENS,
|
||||||
EXA_API_KEY,
|
EXA_API_KEY,
|
||||||
PERPLEXITY_API_KEY,
|
PERPLEXITY_API_KEY,
|
||||||
PERPLEXITY_MODEL,
|
PERPLEXITY_MODEL,
|
||||||
@@ -1108,6 +1109,7 @@ app.state.config.YACY_PASSWORD = YACY_PASSWORD
|
|||||||
app.state.config.GOOGLE_PSE_API_KEY = GOOGLE_PSE_API_KEY
|
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.GOOGLE_PSE_ENGINE_ID = GOOGLE_PSE_ENGINE_ID
|
||||||
app.state.config.BRAVE_SEARCH_API_KEY = BRAVE_SEARCH_API_KEY
|
app.state.config.BRAVE_SEARCH_API_KEY = BRAVE_SEARCH_API_KEY
|
||||||
|
app.state.config.BRAVE_SEARCH_CONTEXT_TOKENS = BRAVE_SEARCH_CONTEXT_TOKENS
|
||||||
app.state.config.KAGI_SEARCH_API_KEY = KAGI_SEARCH_API_KEY
|
app.state.config.KAGI_SEARCH_API_KEY = KAGI_SEARCH_API_KEY
|
||||||
app.state.config.MOJEEK_SEARCH_API_KEY = MOJEEK_SEARCH_API_KEY
|
app.state.config.MOJEEK_SEARCH_API_KEY = MOJEEK_SEARCH_API_KEY
|
||||||
app.state.config.BOCHA_SEARCH_API_KEY = BOCHA_SEARCH_API_KEY
|
app.state.config.BOCHA_SEARCH_API_KEY = BOCHA_SEARCH_API_KEY
|
||||||
|
|||||||
@@ -135,6 +135,7 @@ class PptxLoader:
|
|||||||
]
|
]
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
class TikaLoader:
|
class TikaLoader:
|
||||||
def __init__(self, url, file_path, mime_type=None, extract_images=None):
|
def __init__(self, url, file_path, mime_type=None, extract_images=None):
|
||||||
self.url = url
|
self.url = url
|
||||||
|
|||||||
@@ -0,0 +1,66 @@
|
|||||||
|
import logging
|
||||||
|
import time
|
||||||
|
from typing import Optional
|
||||||
|
|
||||||
|
import requests
|
||||||
|
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
|
||||||
|
|
||||||
|
log = logging.getLogger(__name__)
|
||||||
|
|
||||||
|
|
||||||
|
def search_brave_llm_context(
|
||||||
|
api_key: str,
|
||||||
|
query: str,
|
||||||
|
count: int,
|
||||||
|
filter_list: Optional[list[str]] = None,
|
||||||
|
context_tokens: int = 8192,
|
||||||
|
) -> list[SearchResult]:
|
||||||
|
"""Search using Brave's LLM Context API and return pre-extracted, relevance-scored
|
||||||
|
page content ready for LLM consumption.
|
||||||
|
|
||||||
|
Uses /res/v1/llm/context instead of /res/v1/web/search. Same API key, same pricing.
|
||||||
|
Returns full extracted passages per URL rather than short snippets, eliminating
|
||||||
|
the need for post-search scraping.
|
||||||
|
|
||||||
|
Args:
|
||||||
|
api_key (str): A Brave Search API key (same key as web search)
|
||||||
|
query (str): The query to search for
|
||||||
|
count (int): Maximum number of results to return
|
||||||
|
filter_list (list[str], optional): Domain filter list
|
||||||
|
context_tokens (int): Maximum total tokens to retrieve (1024–32768, default 8192)
|
||||||
|
"""
|
||||||
|
url = 'https://api.search.brave.com/res/v1/llm/context'
|
||||||
|
headers = {
|
||||||
|
'Accept': 'application/json',
|
||||||
|
'Accept-Encoding': 'gzip',
|
||||||
|
'X-Subscription-Token': api_key,
|
||||||
|
}
|
||||||
|
params = {
|
||||||
|
'q': query,
|
||||||
|
'count': count,
|
||||||
|
'maximum_number_of_tokens': context_tokens,
|
||||||
|
}
|
||||||
|
|
||||||
|
response = requests.get(url, headers=headers, params=params)
|
||||||
|
|
||||||
|
# Handle 429 rate limiting - same rate limits as web search
|
||||||
|
if response.status_code == 429:
|
||||||
|
log.info('Brave LLM Context API rate limited (429), retrying after 1 second...')
|
||||||
|
time.sleep(1)
|
||||||
|
response = requests.get(url, headers=headers, params=params)
|
||||||
|
|
||||||
|
response.raise_for_status()
|
||||||
|
|
||||||
|
json_response = response.json()
|
||||||
|
results = json_response.get('grounding', {}).get('generic', [])
|
||||||
|
if filter_list:
|
||||||
|
results = get_filtered_results(results, filter_list)
|
||||||
|
|
||||||
|
return [
|
||||||
|
SearchResult(
|
||||||
|
link=result['url'],
|
||||||
|
title=result.get('title'),
|
||||||
|
snippet='\n\n'.join(result.get('snippets', [])),
|
||||||
|
)
|
||||||
|
for result in results[:count]
|
||||||
|
]
|
||||||
@@ -57,6 +57,7 @@ from open_webui.retrieval.web.utils import get_web_loader
|
|||||||
from open_webui.retrieval.web.ollama import search_ollama_cloud
|
from open_webui.retrieval.web.ollama import search_ollama_cloud
|
||||||
from open_webui.retrieval.web.perplexity_search import search_perplexity_search
|
from open_webui.retrieval.web.perplexity_search import search_perplexity_search
|
||||||
from open_webui.retrieval.web.brave import search_brave
|
from open_webui.retrieval.web.brave import search_brave
|
||||||
|
from open_webui.retrieval.web.brave_llm_context import search_brave_llm_context
|
||||||
from open_webui.retrieval.web.kagi import search_kagi
|
from open_webui.retrieval.web.kagi import search_kagi
|
||||||
from open_webui.retrieval.web.mojeek import search_mojeek
|
from open_webui.retrieval.web.mojeek import search_mojeek
|
||||||
from open_webui.retrieval.web.bocha import search_bocha
|
from open_webui.retrieval.web.bocha import search_bocha
|
||||||
@@ -531,6 +532,7 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
|
|||||||
'GOOGLE_PSE_API_KEY': request.app.state.config.GOOGLE_PSE_API_KEY,
|
'GOOGLE_PSE_API_KEY': request.app.state.config.GOOGLE_PSE_API_KEY,
|
||||||
'GOOGLE_PSE_ENGINE_ID': request.app.state.config.GOOGLE_PSE_ENGINE_ID,
|
'GOOGLE_PSE_ENGINE_ID': request.app.state.config.GOOGLE_PSE_ENGINE_ID,
|
||||||
'BRAVE_SEARCH_API_KEY': request.app.state.config.BRAVE_SEARCH_API_KEY,
|
'BRAVE_SEARCH_API_KEY': request.app.state.config.BRAVE_SEARCH_API_KEY,
|
||||||
|
'BRAVE_SEARCH_CONTEXT_TOKENS': request.app.state.config.BRAVE_SEARCH_CONTEXT_TOKENS,
|
||||||
'KAGI_SEARCH_API_KEY': request.app.state.config.KAGI_SEARCH_API_KEY,
|
'KAGI_SEARCH_API_KEY': request.app.state.config.KAGI_SEARCH_API_KEY,
|
||||||
'MOJEEK_SEARCH_API_KEY': request.app.state.config.MOJEEK_SEARCH_API_KEY,
|
'MOJEEK_SEARCH_API_KEY': request.app.state.config.MOJEEK_SEARCH_API_KEY,
|
||||||
'BOCHA_SEARCH_API_KEY': request.app.state.config.BOCHA_SEARCH_API_KEY,
|
'BOCHA_SEARCH_API_KEY': request.app.state.config.BOCHA_SEARCH_API_KEY,
|
||||||
@@ -599,6 +601,7 @@ class WebConfig(BaseModel):
|
|||||||
GOOGLE_PSE_API_KEY: Optional[str] = None
|
GOOGLE_PSE_API_KEY: Optional[str] = None
|
||||||
GOOGLE_PSE_ENGINE_ID: Optional[str] = None
|
GOOGLE_PSE_ENGINE_ID: Optional[str] = None
|
||||||
BRAVE_SEARCH_API_KEY: Optional[str] = None
|
BRAVE_SEARCH_API_KEY: Optional[str] = None
|
||||||
|
BRAVE_SEARCH_CONTEXT_TOKENS: Optional[int] = None
|
||||||
KAGI_SEARCH_API_KEY: Optional[str] = None
|
KAGI_SEARCH_API_KEY: Optional[str] = None
|
||||||
MOJEEK_SEARCH_API_KEY: Optional[str] = None
|
MOJEEK_SEARCH_API_KEY: Optional[str] = None
|
||||||
BOCHA_SEARCH_API_KEY: Optional[str] = None
|
BOCHA_SEARCH_API_KEY: Optional[str] = None
|
||||||
@@ -1081,6 +1084,8 @@ async def update_rag_config(request: Request, form_data: ConfigForm, user=Depend
|
|||||||
request.app.state.config.GOOGLE_PSE_API_KEY = form_data.web.GOOGLE_PSE_API_KEY
|
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
|
request.app.state.config.GOOGLE_PSE_ENGINE_ID = form_data.web.GOOGLE_PSE_ENGINE_ID
|
||||||
request.app.state.config.BRAVE_SEARCH_API_KEY = form_data.web.BRAVE_SEARCH_API_KEY
|
request.app.state.config.BRAVE_SEARCH_API_KEY = form_data.web.BRAVE_SEARCH_API_KEY
|
||||||
|
if form_data.web.BRAVE_SEARCH_CONTEXT_TOKENS is not None:
|
||||||
|
request.app.state.config.BRAVE_SEARCH_CONTEXT_TOKENS = form_data.web.BRAVE_SEARCH_CONTEXT_TOKENS
|
||||||
request.app.state.config.KAGI_SEARCH_API_KEY = form_data.web.KAGI_SEARCH_API_KEY
|
request.app.state.config.KAGI_SEARCH_API_KEY = form_data.web.KAGI_SEARCH_API_KEY
|
||||||
request.app.state.config.MOJEEK_SEARCH_API_KEY = form_data.web.MOJEEK_SEARCH_API_KEY
|
request.app.state.config.MOJEEK_SEARCH_API_KEY = form_data.web.MOJEEK_SEARCH_API_KEY
|
||||||
request.app.state.config.BOCHA_SEARCH_API_KEY = form_data.web.BOCHA_SEARCH_API_KEY
|
request.app.state.config.BOCHA_SEARCH_API_KEY = form_data.web.BOCHA_SEARCH_API_KEY
|
||||||
@@ -1216,6 +1221,7 @@ async def update_rag_config(request: Request, form_data: ConfigForm, user=Depend
|
|||||||
'GOOGLE_PSE_API_KEY': request.app.state.config.GOOGLE_PSE_API_KEY,
|
'GOOGLE_PSE_API_KEY': request.app.state.config.GOOGLE_PSE_API_KEY,
|
||||||
'GOOGLE_PSE_ENGINE_ID': request.app.state.config.GOOGLE_PSE_ENGINE_ID,
|
'GOOGLE_PSE_ENGINE_ID': request.app.state.config.GOOGLE_PSE_ENGINE_ID,
|
||||||
'BRAVE_SEARCH_API_KEY': request.app.state.config.BRAVE_SEARCH_API_KEY,
|
'BRAVE_SEARCH_API_KEY': request.app.state.config.BRAVE_SEARCH_API_KEY,
|
||||||
|
'BRAVE_SEARCH_CONTEXT_TOKENS': request.app.state.config.BRAVE_SEARCH_CONTEXT_TOKENS,
|
||||||
'KAGI_SEARCH_API_KEY': request.app.state.config.KAGI_SEARCH_API_KEY,
|
'KAGI_SEARCH_API_KEY': request.app.state.config.KAGI_SEARCH_API_KEY,
|
||||||
'MOJEEK_SEARCH_API_KEY': request.app.state.config.MOJEEK_SEARCH_API_KEY,
|
'MOJEEK_SEARCH_API_KEY': request.app.state.config.MOJEEK_SEARCH_API_KEY,
|
||||||
'BOCHA_SEARCH_API_KEY': request.app.state.config.BOCHA_SEARCH_API_KEY,
|
'BOCHA_SEARCH_API_KEY': request.app.state.config.BOCHA_SEARCH_API_KEY,
|
||||||
@@ -1963,6 +1969,17 @@ def search_web(request: Request, engine: str, query: str, user=None) -> list[Sea
|
|||||||
)
|
)
|
||||||
else:
|
else:
|
||||||
raise Exception('No BRAVE_SEARCH_API_KEY found in environment variables')
|
raise Exception('No BRAVE_SEARCH_API_KEY found in environment variables')
|
||||||
|
elif engine == 'brave_llm_context':
|
||||||
|
if request.app.state.config.BRAVE_SEARCH_API_KEY:
|
||||||
|
return search_brave_llm_context(
|
||||||
|
request.app.state.config.BRAVE_SEARCH_API_KEY,
|
||||||
|
query,
|
||||||
|
request.app.state.config.WEB_SEARCH_RESULT_COUNT,
|
||||||
|
request.app.state.config.WEB_SEARCH_DOMAIN_FILTER_LIST,
|
||||||
|
request.app.state.config.BRAVE_SEARCH_CONTEXT_TOKENS,
|
||||||
|
)
|
||||||
|
else:
|
||||||
|
raise Exception('No BRAVE_SEARCH_API_KEY found in environment variables')
|
||||||
elif engine == 'kagi':
|
elif engine == 'kagi':
|
||||||
if request.app.state.config.KAGI_SEARCH_API_KEY:
|
if request.app.state.config.KAGI_SEARCH_API_KEY:
|
||||||
return search_kagi(
|
return search_kagi(
|
||||||
|
|||||||
@@ -20,6 +20,7 @@
|
|||||||
'yacy',
|
'yacy',
|
||||||
'google_pse',
|
'google_pse',
|
||||||
'brave',
|
'brave',
|
||||||
|
'brave_llm_context',
|
||||||
'kagi',
|
'kagi',
|
||||||
'mojeek',
|
'mojeek',
|
||||||
'bocha',
|
'bocha',
|
||||||
@@ -357,7 +358,40 @@
|
|||||||
/>
|
/>
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
{:else if webConfig.WEB_SEARCH_ENGINE === 'kagi'}
|
{:else if webConfig.WEB_SEARCH_ENGINE === 'brave_llm_context'}
|
||||||
|
<div class="mb-2.5 flex w-full flex-col">
|
||||||
|
<div>
|
||||||
|
<div class=" self-center text-xs font-medium mb-1">
|
||||||
|
{$i18n.t('Brave Search API Key')}
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<SensitiveInput
|
||||||
|
placeholder={$i18n.t('Enter Brave Search API Key')}
|
||||||
|
bind:value={webConfig.BRAVE_SEARCH_API_KEY}
|
||||||
|
/>
|
||||||
|
</div>
|
||||||
|
<div class="mt-1.5">
|
||||||
|
<div class=" self-center text-xs font-medium mb-1">
|
||||||
|
{$i18n.t('Context Tokens')}
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<div class="flex w-full">
|
||||||
|
<div class="flex-1">
|
||||||
|
<input
|
||||||
|
class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
|
||||||
|
type="number"
|
||||||
|
min="1024"
|
||||||
|
max="32768"
|
||||||
|
step="1024"
|
||||||
|
placeholder={$i18n.t('Max tokens to retrieve (1024-32768, default 8192)')}
|
||||||
|
bind:value={webConfig.BRAVE_SEARCH_CONTEXT_TOKENS}
|
||||||
|
autocomplete="off"
|
||||||
|
/>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
{:else if webConfig.WEB_SEARCH_ENGINE === 'kagi'}
|
||||||
<div class="mb-2.5 flex w-full flex-col">
|
<div class="mb-2.5 flex w-full flex-col">
|
||||||
<div>
|
<div>
|
||||||
<div class=" self-center text-xs font-medium mb-1">
|
<div class=" self-center text-xs font-medium mb-1">
|
||||||
|
|||||||
Reference in new issue
Block a user