multiple: pydantic 2 compatibility, v0.3 (#26443)

Signed-off-by: ChengZi <chen.zhang@zilliz.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Dan O'Donovan <dan.odonovan@gmail.com>
Co-authored-by: Tom Daniel Grande <tomdgrande@gmail.com>
Co-authored-by: Grande <Tom.Daniel.Grande@statsbygg.no>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: ccurme <chester.curme@gmail.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Tomaz Bratanic <bratanic.tomaz@gmail.com>
Co-authored-by: ZhangShenao <15201440436@163.com>
Co-authored-by: Friso H. Kingma <fhkingma@gmail.com>
Co-authored-by: ChengZi <chen.zhang@zilliz.com>
Co-authored-by: Nuno Campos <nuno@langchain.dev>
Co-authored-by: Morgante Pell <morgantep@google.com>

libs/community/langchain_community/document_loaders/html_bs.py

@@ -1,3 +1,4 @@
+import importlib.util
 import logging
 from pathlib import Path
 from typing import Dict, Iterator, Union
@@ -106,6 +107,13 @@ class BSHTMLLoader(BaseLoader):
         self.file_path = file_path
         self.open_encoding = open_encoding
         if bs_kwargs is None:
+            if not importlib.util.find_spec("lxml"):
+                raise ImportError(
+                    "By default BSHTMLLoader uses the 'lxml' package. Please either "
+                    "install it with `pip install -U lxml` or pass in init arg "
+                    "`bs_kwargs={'features': '...'}` to overwrite the default "
+                    "BeautifulSoup kwargs."
+                )
             bs_kwargs = {"features": "lxml"}
         self.bs_kwargs = bs_kwargs
         self.get_text_separator = get_text_separator