fix: testing in Windows and add missing dev dependency (#2340)

This changes addresses two issues.

First, we add `setuptools` to the dev dependencies in order to debug
tests locally with an IDE, especially with PyCharm. All dependencies dev
dependencies should be installed with `poetry install --extras "dev"`.

Second, we use PurePosixPath instead of Path for URL paths to fix issues
with testing in Windows. This ensures that forward slashes are used as
the path separator regardless of the operating system.

Closes #2334

Author: sergerdn

langchain/utilities/loading.py

@@ -3,7 +3,7 @@
 import os
 import re
 import tempfile
-from pathlib import Path
+from pathlib import Path, PurePosixPath
 from typing import Any, Callable, Optional, Set, TypeVar, Union
 from urllib.parse import urljoin
 
@@ -16,7 +16,6 @@
 )
 HUB_PATH_RE = re.compile(r"lc(?P<ref>@[^:]+)?://(?P<path>.*)")
 
-
 T = TypeVar("T")
 
 
@@ -38,7 +37,13 @@ def try_load_from_hub(
     if remote_path.suffix[1:] not in valid_suffixes:
         raise ValueError("Unsupported file type.")
 
-    full_url = urljoin(URL_BASE.format(ref=ref), str(remote_path))
+    # Using Path with URLs is not recommended, because on Windows
+    # the backslash is used as the path separator, which can cause issues
+    # when working with URLs that use forward slashes as the path separator.
+    # Instead, use PurePosixPath to ensure that forward slashes are used as the
+    # path separator, regardless of the operating system.
+    full_url = urljoin(URL_BASE.format(ref=ref), PurePosixPath(remote_path).__str__())
+
     r = requests.get(full_url, timeout=5)
     if r.status_code != 200:
         raise ValueError(f"Could not find file at {full_url}")

poetry.lock

@@ -99,6 +99,7 @@ optional = true
 [tool.poetry.group.dev.dependencies]
 jupyter = "^1.0.0"
 playwright = "^1.28.0"
+setuptools = "^67.6.1"
 
 [tool.poetry.extras]
 llms = ["anthropic", "cohere", "openai", "nlpcloud", "huggingface_hub", "manifest-ml", "torch", "transformers"]