Set filter_list as optional param in google_pse.py

This commit is contained in:
Que Nguyen 2024-06-17 14:35:27 +07:00 committed by GitHub
parent 7d2ad8c4bf
commit d8beed13b4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -1,9 +1,9 @@
import json import json
import logging import logging
from typing import List from typing import List, Optional
import requests import requests
from apps.rag.search.main import SearchResult, filter_by_whitelist from apps.rag.search.main import SearchResult, get_filtered_results
from config import SRC_LOG_LEVELS from config import SRC_LOG_LEVELS
log = logging.getLogger(__name__) log = logging.getLogger(__name__)
@ -11,7 +11,7 @@ log.setLevel(SRC_LOG_LEVELS["RAG"])
def search_google_pse( def search_google_pse(
api_key: str, search_engine_id: str, query: str, count: int, whitelist:List[str] api_key: str, search_engine_id: str, query: str, count: int, filter_list: Optional[List[str]] = None
) -> list[SearchResult]: ) -> list[SearchResult]:
"""Search using Google's Programmable Search Engine API and return the results as a list of SearchResult objects. """Search using Google's Programmable Search Engine API and return the results as a list of SearchResult objects.
@ -35,12 +35,13 @@ def search_google_pse(
json_response = response.json() json_response = response.json()
results = json_response.get("items", []) results = json_response.get("items", [])
filtered_results = filter_by_whitelist(results, whitelist) if filter_list:
results = get_filtered_results(results, filter_list)
return [ return [
SearchResult( SearchResult(
link=result["link"], link=result["link"],
title=result.get("title"), title=result.get("title"),
snippet=result.get("snippet"), snippet=result.get("snippet"),
) )
for result in filtered_results for result in results
] ]