mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-28 15:00:23 +00:00
8516a03a02
This PR upgrades langchain-community to pydantic 2.
* Most of this PR was auto-generated using code mods with gritql
(https://github.com/eyurtsev/migrate-pydantic/tree/main)
* Subsequently, some code was fixed manually due to accommodate
differences between pydantic 1 and 2
Breaking Changes:
- Use TEXTEMBED_API_KEY and TEXTEMBEB_API_URL for env variables for text
embed integrations:
cbea780492
Other changes:
- Added pydantic_settings as a required dependency for community. This
may be removed if we have enough time to convert the dependency into an
optional one.
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
81 lines
2.6 KiB
Python
81 lines
2.6 KiB
Python
import json
|
|
from typing import List
|
|
|
|
import requests
|
|
from langchain_core.documents import Document
|
|
from pydantic 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": " ".join(
|
|
filter(
|
|
None, [item.get("description"), *item.get("extra_snippets", [])]
|
|
)
|
|
),
|
|
}
|
|
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=" ".join(
|
|
filter(
|
|
None, [item.get("description"), *item.get("extra_snippets", [])]
|
|
)
|
|
),
|
|
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, "extra_snippets": True}}
|
|
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", [])
|