This commit is contained in:
Eugene Yurtsev
2023-06-02 14:14:19 -04:00
parent 7adbcb195d
commit 68e39f7f26
3 changed files with 5 additions and 15 deletions

View File

@@ -1,9 +1,7 @@
from __future__ import annotations
from typing import Any, Dict, List, Literal, Mapping, Optional, Union
import itertools
from langchain.chains.research.download import AutoDownloadHandler, DownloadHandler
from typing import Any, Dict, List, Literal, Mapping, Optional, Union
from langchain.base_language import BaseLanguageModel
from langchain.callbacks.manager import (
@@ -12,6 +10,7 @@ from langchain.callbacks.manager import (
)
from langchain.chains.base import Chain
from langchain.chains.llm import LLMChain
from langchain.chains.research.download import AutoDownloadHandler, DownloadHandler
from langchain.chains.research.readers import DocReadingChain, ParallelApplyChain
from langchain.chains.research.search import GenericSearcher
from langchain.document_loaders.parsers.html.markdownify import MarkdownifyHTMLParser

View File

@@ -14,7 +14,7 @@ Downloading is batched by default to allow efficient parallelization.
import abc
import asyncio
import mimetypes
from typing import Any, List, Sequence, Optional
from typing import Any, List, Optional, Sequence
from bs4 import BeautifulSoup

View File

@@ -1,8 +1,5 @@
"""Tests for the downloader."""
from langchain.chains.research.fetch import (
AutoDownloadHandler,
PlaywrightDownloadHandler,
RequestsDownloadHandler,
from langchain.chains.research.download import (
_is_javascript_required,
)
@@ -22,17 +19,11 @@ def test_is_javascript_required():
assert _is_javascript_required(
"""
<html>
<body>
<script>
console.log("Javascript is required.");
</script>
<body>
</body>
</html>
"""
)
def test_requests_handler():
"""Test that the requests handler is working."""
handler = RequestsDownloadHandler()
fetch = handler.download(["https://www.google.com"])