langchain/libs/community/langchain_community/utilities/brave_search.py
Harrison Chase 4eda647fdd
infra: add -p to mkdir in lint steps (#17013)
Previously, if this did not find a mypy cache then it wouldnt run

this makes it always run

adding mypy ignore comments with existing uncaught issues to unblock other prs

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-02-05 11:22:06 -08:00

73 lines
2.3 KiB
Python

import json
from typing import List
import requests
from langchain_core.documents import Document
from langchain_core.pydantic_v1 import BaseModel, Field
class BraveSearchWrapper(BaseModel):
"""Wrapper around the Brave search engine."""
api_key: str
"""The API key to use for the Brave search engine."""
search_kwargs: dict = Field(default_factory=dict)
"""Additional keyword arguments to pass to the search request."""
base_url: str = "https://api.search.brave.com/res/v1/web/search"
"""The base URL for the Brave search engine."""
def run(self, query: str) -> str:
"""Query the Brave search engine and return the results as a JSON string.
Args:
query: The query to search for.
Returns: The results as a JSON string.
"""
web_search_results = self._search_request(query=query)
final_results = [
{
"title": item.get("title"),
"link": item.get("url"),
"snippet": item.get("description"),
}
for item in web_search_results
]
return json.dumps(final_results)
def download_documents(self, query: str) -> List[Document]:
"""Query the Brave search engine and return the results as a list of Documents.
Args:
query: The query to search for.
Returns: The results as a list of Documents.
"""
results = self._search_request(query)
return [
Document(
page_content=item.get("description"), # type: ignore[arg-type]
metadata={"title": item.get("title"), "link": item.get("url")},
)
for item in results
]
def _search_request(self, query: str) -> List[dict]:
headers = {
"X-Subscription-Token": self.api_key,
"Accept": "application/json",
}
req = requests.PreparedRequest()
params = {**self.search_kwargs, **{"q": query}}
req.prepare_url(self.base_url, params)
if req.url is None:
raise ValueError("prepared url is None, this should not happen")
response = requests.get(req.url, headers=headers)
if not response.ok:
raise Exception(f"HTTP error {response.status_code}")
return response.json().get("web", {}).get("results", [])