text-splitters[minor], langchain[minor], community[patch], templates, docs: langchain-text-splitters 0.0.1 (#18346)

libs/text-splitters/scripts/check_imports.py

@@ -0,0 +1,22 @@
+import random
+import string
+import sys
+import traceback
+from importlib.machinery import SourceFileLoader
+
+if __name__ == "__main__":
+    files = sys.argv[1:]
+    has_failure = False
+    for file in files:
+        try:
+            module_name = "".join(
+                random.choice(string.ascii_letters) for _ in range(20)
+            )
+            SourceFileLoader(module_name, file).load_module()
+        except Exception:
+            has_failure = True
+            print(file)  # noqa: T201
+            traceback.print_exc()
+            print()  # noqa: T201
+
+    sys.exit(1 if has_failure else 0)

libs/text-splitters/scripts/check_pydantic.sh

@@ -0,0 +1,27 @@
+#!/bin/bash
+#
+# This script searches for lines starting with "import pydantic" or "from pydantic"
+# in tracked files within a Git repository.
+#
+# Usage: ./scripts/check_pydantic.sh /path/to/repository
+
+# Check if a path argument is provided
+if [ $# -ne 1 ]; then
+  echo "Usage: $0 /path/to/repository"
+  exit 1
+fi
+
+repository_path="$1"
+
+# Search for lines matching the pattern within the specified repository
+result=$(git -C "$repository_path" grep -E '^import pydantic|^from pydantic')
+
+# Check if any matching lines were found
+if [ -n "$result" ]; then
+  echo "ERROR: The following lines need to be updated:"
+  echo "$result"
+  echo "Please replace the code with an import from langchain_core.pydantic_v1."
+  echo "For example, replace 'from pydantic import BaseModel'"
+  echo "with 'from langchain_core.pydantic_v1 import BaseModel'"
+  exit 1
+fi

libs/text-splitters/scripts/lint_imports.sh

@@ -0,0 +1,18 @@
+#!/bin/bash
+
+set -eu
+
+# Initialize a variable to keep track of errors
+errors=0
+
+# make sure not importing from langchain or langchain_experimental
+git --no-pager grep '^from langchain\.' . && errors=$((errors+1))
+git --no-pager grep '^from langchain_experimental\.' . && errors=$((errors+1))
+git --no-pager grep '^from langchain_community\.' . && errors=$((errors+1))
+
+# Decide on an exit status based on the errors
+if [ "$errors" -gt 0 ]; then
+    exit 1
+else
+    exit 0
+fi