2024-10-28 09:33:52 +00:00
|
|
|
import logging
|
2024-11-17 07:46:12 +00:00
|
|
|
import os
|
2024-10-28 09:33:52 +00:00
|
|
|
from pprint import pprint
|
|
|
|
from typing import Optional
|
|
|
|
import requests
|
2024-12-12 02:05:42 +00:00
|
|
|
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
|
2024-10-28 09:33:52 +00:00
|
|
|
from open_webui.env import SRC_LOG_LEVELS
|
|
|
|
import argparse
|
|
|
|
|
|
|
|
log = logging.getLogger(__name__)
|
|
|
|
log.setLevel(SRC_LOG_LEVELS["RAG"])
|
2024-11-17 07:46:12 +00:00
|
|
|
"""
|
2024-10-28 09:33:52 +00:00
|
|
|
Documentation: https://docs.microsoft.com/en-us/bing/search-apis/bing-web-search/overview
|
2024-11-17 07:46:12 +00:00
|
|
|
"""
|
|
|
|
|
|
|
|
|
2024-10-28 09:33:52 +00:00
|
|
|
def search_bing(
|
2024-11-17 07:46:12 +00:00
|
|
|
subscription_key: str,
|
|
|
|
endpoint: str,
|
|
|
|
locale: str,
|
|
|
|
query: str,
|
|
|
|
count: int,
|
|
|
|
filter_list: Optional[list[str]] = None,
|
2024-10-28 09:33:52 +00:00
|
|
|
) -> list[SearchResult]:
|
|
|
|
mkt = locale
|
2024-11-17 07:46:12 +00:00
|
|
|
params = {"q": query, "mkt": mkt, "answerCount": count}
|
|
|
|
headers = {"Ocp-Apim-Subscription-Key": subscription_key}
|
2024-10-28 09:33:52 +00:00
|
|
|
|
|
|
|
try:
|
|
|
|
response = requests.get(endpoint, headers=headers, params=params)
|
|
|
|
response.raise_for_status()
|
|
|
|
json_response = response.json()
|
|
|
|
results = json_response.get("webPages", {}).get("value", [])
|
|
|
|
if filter_list:
|
|
|
|
results = get_filtered_results(results, filter_list)
|
|
|
|
return [
|
|
|
|
SearchResult(
|
|
|
|
link=result["url"],
|
|
|
|
title=result.get("name"),
|
|
|
|
snippet=result.get("snippet"),
|
|
|
|
)
|
|
|
|
for result in results
|
|
|
|
]
|
|
|
|
except Exception as ex:
|
|
|
|
log.error(f"Error: {ex}")
|
|
|
|
raise ex
|
2024-11-17 07:46:12 +00:00
|
|
|
|
|
|
|
|
2024-10-28 09:33:52 +00:00
|
|
|
def main():
|
|
|
|
parser = argparse.ArgumentParser(description="Search Bing from the command line.")
|
2024-11-17 07:46:12 +00:00
|
|
|
parser.add_argument(
|
|
|
|
"query",
|
|
|
|
type=str,
|
|
|
|
default="Top 10 international news today",
|
|
|
|
help="The search query.",
|
|
|
|
)
|
|
|
|
parser.add_argument(
|
|
|
|
"--count", type=int, default=10, help="Number of search results to return."
|
|
|
|
)
|
|
|
|
parser.add_argument(
|
|
|
|
"--filter", nargs="*", help="List of filters to apply to the search results."
|
|
|
|
)
|
|
|
|
parser.add_argument(
|
|
|
|
"--locale",
|
|
|
|
type=str,
|
|
|
|
default="en-US",
|
|
|
|
help="The locale to use for the search, maps to market in api",
|
|
|
|
)
|
|
|
|
|
2024-10-28 09:33:52 +00:00
|
|
|
args = parser.parse_args()
|
2024-11-17 07:46:12 +00:00
|
|
|
|
2024-10-28 09:33:52 +00:00
|
|
|
results = search_bing(args.locale, args.query, args.count, args.filter)
|
2024-11-17 07:46:12 +00:00
|
|
|
pprint(results)
|