text-splitters[major]: update core dep + drop support for python 3.8 (#26102)

libs/text-splitters/Makefile

@@ -39,7 +39,6 @@ lint_tests: PYTHON_FILES=tests
 lint_tests: MYPY_CACHE=.mypy_cache_test
 
 lint lint_diff lint_package lint_tests:
-	./scripts/check_pydantic.sh .
 	./scripts/lint_imports.sh
 	[ "$(PYTHON_FILES)" = "" ] || poetry run ruff check $(PYTHON_FILES)
 	[ "$(PYTHON_FILES)" = "" ] || poetry run ruff format $(PYTHON_FILES) --diff

libs/text-splitters/poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.8.2 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
 
 [[package]]
 name = "annotated-types"
@@ -11,9 +11,6 @@ files = [
     {file = "annotated_types-0.7.0.tar.gz", hash = "sha256:aff07c09a53a08bc8cfccb9c85b05f1aa9a2a6f23728d790723543408344ce89"},
 ]
 
-[package.dependencies]
-typing-extensions = {version = ">=4.0.0", markers = "python_version < \"3.9\""}
-
 [[package]]
 name = "anyio"
 version = "4.4.0"
@@ -185,9 +182,6 @@ files = [
     {file = "babel-2.16.0.tar.gz", hash = "sha256:d1f3554ca26605fe173f3de0c65f750f5a42f924499bf134de6423582298e316"},
 ]
 
-[package.dependencies]
-pytz = {version = ">=2015.7", markers = "python_version < \"3.9\""}
-
 [package.extras]
 dev = ["freezegun (>=1.0,<2.0)", "pytest (>=6.0)", "pytest-cov"]
 
@@ -285,10 +279,7 @@ files = [
 ]
 
 [package.dependencies]
-numpy = [
+numpy = {version = ">=1.19.0", markers = "python_version >= \"3.9\""}
-    {version = ">=1.15.0", markers = "python_version < \"3.9\""},
-    {version = ">=1.19.0", markers = "python_version >= \"3.9\""},
-]
 
 [[package]]
 name = "catalogue"
@@ -827,28 +818,6 @@ doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linke
 perf = ["ipython"]
 test = ["flufl.flake8", "importlib-resources (>=1.3)", "jaraco.test (>=5.4)", "packaging", "pyfakefs", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy", "pytest-perf (>=0.9.2)", "pytest-ruff (>=0.2.1)"]
 
-[[package]]
-name = "importlib-resources"
-version = "6.4.4"
-description = "Read resources from Python packages"
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "importlib_resources-6.4.4-py3-none-any.whl", hash = "sha256:dda242603d1c9cd836c3368b1174ed74cb4049ecd209e7a1a0104620c18c5c11"},
-    {file = "importlib_resources-6.4.4.tar.gz", hash = "sha256:20600c8b7361938dc0bb2d5ec0297802e575df486f5a544fa414da65e13721f7"},
-]
-
-[package.dependencies]
-zipp = {version = ">=3.1.0", markers = "python_version < \"3.10\""}
-
-[package.extras]
-check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1)"]
-cover = ["pytest-cov"]
-doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
-enabler = ["pytest-enabler (>=2.2)"]
-test = ["jaraco.test (>=5.4)", "pytest (>=6,!=8.1.*)", "zipp (>=3.17)"]
-type = ["pytest-mypy"]
-
 [[package]]
 name = "iniconfig"
 version = "2.0.0"
@@ -1054,11 +1023,9 @@ files = [
 attrs = ">=22.2.0"
 fqdn = {version = "*", optional = true, markers = "extra == \"format-nongpl\""}
 idna = {version = "*", optional = true, markers = "extra == \"format-nongpl\""}
-importlib-resources = {version = ">=1.4.0", markers = "python_version < \"3.9\""}
 isoduration = {version = "*", optional = true, markers = "extra == \"format-nongpl\""}
 jsonpointer = {version = ">1.13", optional = true, markers = "extra == \"format-nongpl\""}
 jsonschema-specifications = ">=2023.03.6"
-pkgutil-resolve-name = {version = ">=1.3.10", markers = "python_version < \"3.9\""}
 referencing = ">=0.28.4"
 rfc3339-validator = {version = "*", optional = true, markers = "extra == \"format-nongpl\""}
 rfc3986-validator = {version = ">0.1.0", optional = true, markers = "extra == \"format-nongpl\""}
@@ -1082,7 +1049,6 @@ files = [
 ]
 
 [package.dependencies]
-importlib-resources = {version = ">=1.4.0", markers = "python_version < \"3.9\""}
 referencing = ">=0.31.0"
 
 [[package]]
@@ -1281,7 +1247,6 @@ files = [
 async-lru = ">=1.0.0"
 httpx = ">=0.25.0"
 importlib-metadata = {version = ">=4.8.3", markers = "python_version < \"3.10\""}
-importlib-resources = {version = ">=1.4", markers = "python_version < \"3.9\""}
 ipykernel = ">=6.5.0"
 jinja2 = ">=3.0.3"
 jupyter-core = "*"
@@ -1352,10 +1317,10 @@ files = [
 
 [[package]]
 name = "langchain-core"
-version = "0.2.38"
+version = "0.3.0.dev1"
 description = "Building applications with LLMs through composability"
 optional = false
-python-versions = ">=3.8.1,<4.0"
+python-versions = ">=3.9,<4.0"
 files = []
 develop = true
 
@@ -1909,43 +1874,6 @@ jupyter-server = ">=1.8,<3"
 [package.extras]
 test = ["pytest", "pytest-console-scripts", "pytest-jupyter", "pytest-tornasync"]
 
-[[package]]
-name = "numpy"
-version = "1.24.4"
-description = "Fundamental package for array computing in Python"
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "numpy-1.24.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c0bfb52d2169d58c1cdb8cc1f16989101639b34c7d3ce60ed70b19c63eba0b64"},
-    {file = "numpy-1.24.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:ed094d4f0c177b1b8e7aa9cba7d6ceed51c0e569a5318ac0ca9a090680a6a1b1"},
-    {file = "numpy-1.24.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:79fc682a374c4a8ed08b331bef9c5f582585d1048fa6d80bc6c35bc384eee9b4"},
-    {file = "numpy-1.24.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7ffe43c74893dbf38c2b0a1f5428760a1a9c98285553c89e12d70a96a7f3a4d6"},
-    {file = "numpy-1.24.4-cp310-cp310-win32.whl", hash = "sha256:4c21decb6ea94057331e111a5bed9a79d335658c27ce2adb580fb4d54f2ad9bc"},
-    {file = "numpy-1.24.4-cp310-cp310-win_amd64.whl", hash = "sha256:b4bea75e47d9586d31e892a7401f76e909712a0fd510f58f5337bea9572c571e"},
-    {file = "numpy-1.24.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:f136bab9c2cfd8da131132c2cf6cc27331dd6fae65f95f69dcd4ae3c3639c810"},
-    {file = "numpy-1.24.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:e2926dac25b313635e4d6cf4dc4e51c8c0ebfed60b801c799ffc4c32bf3d1254"},
-    {file = "numpy-1.24.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:222e40d0e2548690405b0b3c7b21d1169117391c2e82c378467ef9ab4c8f0da7"},
-    {file = "numpy-1.24.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7215847ce88a85ce39baf9e89070cb860c98fdddacbaa6c0da3ffb31b3350bd5"},
-    {file = "numpy-1.24.4-cp311-cp311-win32.whl", hash = "sha256:4979217d7de511a8d57f4b4b5b2b965f707768440c17cb70fbf254c4b225238d"},
-    {file = "numpy-1.24.4-cp311-cp311-win_amd64.whl", hash = "sha256:b7b1fc9864d7d39e28f41d089bfd6353cb5f27ecd9905348c24187a768c79694"},
-    {file = "numpy-1.24.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1452241c290f3e2a312c137a9999cdbf63f78864d63c79039bda65ee86943f61"},
-    {file = "numpy-1.24.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:04640dab83f7c6c85abf9cd729c5b65f1ebd0ccf9de90b270cd61935eef0197f"},
-    {file = "numpy-1.24.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a5425b114831d1e77e4b5d812b69d11d962e104095a5b9c3b641a218abcc050e"},
-    {file = "numpy-1.24.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dd80e219fd4c71fc3699fc1dadac5dcf4fd882bfc6f7ec53d30fa197b8ee22dc"},
-    {file = "numpy-1.24.4-cp38-cp38-win32.whl", hash = "sha256:4602244f345453db537be5314d3983dbf5834a9701b7723ec28923e2889e0bb2"},
-    {file = "numpy-1.24.4-cp38-cp38-win_amd64.whl", hash = "sha256:692f2e0f55794943c5bfff12b3f56f99af76f902fc47487bdfe97856de51a706"},
-    {file = "numpy-1.24.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:2541312fbf09977f3b3ad449c4e5f4bb55d0dbf79226d7724211acc905049400"},
-    {file = "numpy-1.24.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:9667575fb6d13c95f1b36aca12c5ee3356bf001b714fc354eb5465ce1609e62f"},
-    {file = "numpy-1.24.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f3a86ed21e4f87050382c7bc96571755193c4c1392490744ac73d660e8f564a9"},
-    {file = "numpy-1.24.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d11efb4dbecbdf22508d55e48d9c8384db795e1b7b51ea735289ff96613ff74d"},
-    {file = "numpy-1.24.4-cp39-cp39-win32.whl", hash = "sha256:6620c0acd41dbcb368610bb2f4d83145674040025e5536954782467100aa8835"},
-    {file = "numpy-1.24.4-cp39-cp39-win_amd64.whl", hash = "sha256:befe2bf740fd8373cf56149a5c23a0f601e82869598d41f8e188a0e9869926f8"},
-    {file = "numpy-1.24.4-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:31f13e25b4e304632a4619d0e0777662c2ffea99fcae2029556b17d8ff958aef"},
-    {file = "numpy-1.24.4-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:95f7ac6540e95bc440ad77f56e520da5bf877f87dca58bd095288dce8940532a"},
-    {file = "numpy-1.24.4-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:e98f220aa76ca2a977fe435f5b04d7b3470c0a2e6312907b37ba6068f26787f2"},
-    {file = "numpy-1.24.4.tar.gz", hash = "sha256:80f5e3a4e498641401868df4208b74581206afbee7cf7b8329daae82676d9463"},
-]
-
 [[package]]
 name = "numpy"
 version = "1.26.4"
@@ -2130,17 +2058,6 @@ files = [
     {file = "pickleshare-0.7.5.tar.gz", hash = "sha256:87683d47965c1da65cdacaf31c8441d12b8044cdec9aca500cd78fc2c683afca"},
 ]
 
-[[package]]
-name = "pkgutil-resolve-name"
-version = "1.3.10"
-description = "Resolve a name to an object."
-optional = false
-python-versions = ">=3.6"
-files = [
-    {file = "pkgutil_resolve_name-1.3.10-py3-none-any.whl", hash = "sha256:ca27cc078d25c5ad71a9de0a7a330146c4e014c2462d9af19c6b828280649c5e"},
-    {file = "pkgutil_resolve_name-1.3.10.tar.gz", hash = "sha256:357d6c9e6a755653cfd78893817c0853af365dd51ec97f3d358a819373bbd174"},
-]
-
 [[package]]
 name = "platformdirs"
 version = "4.2.2"
@@ -2564,17 +2481,6 @@ files = [
     {file = "python_json_logger-2.0.7-py3-none-any.whl", hash = "sha256:f380b826a991ebbe3de4d897aeec42760035ac760345e57b812938dc8b35e2bd"},
 ]
 
-[[package]]
-name = "pytz"
-version = "2024.1"
-description = "World timezone definitions, modern and historical"
-optional = false
-python-versions = "*"
-files = [
-    {file = "pytz-2024.1-py2.py3-none-any.whl", hash = "sha256:328171f4e3623139da4983451950b28e95ac706e13f3f2630a879749e7a8b319"},
-    {file = "pytz-2024.1.tar.gz", hash = "sha256:2a29735ea9c18baf14b448846bde5a48030ed267578472d8955cd0e7443a9812"},
-]
-
 [[package]]
 name = "pywin32"
 version = "306"
@@ -2959,7 +2865,6 @@ files = [
 [package.dependencies]
 markdown-it-py = ">=2.2.0"
 pygments = ">=2.13.0,<3.0.0"
-typing-extensions = {version = ">=4.0.0,<5.0", markers = "python_version < \"3.9\""}
 
 [package.extras]
 jupyter = ["ipywidgets (>=7.5.1,<9)"]
@@ -3240,10 +3145,7 @@ cymem = ">=2.0.2,<2.1.0"
 jinja2 = "*"
 langcodes = ">=3.2.0,<4.0.0"
 murmurhash = ">=0.28.0,<1.1.0"
-numpy = [
+numpy = {version = ">=1.19.0", markers = "python_version >= \"3.9\""}
-    {version = ">=1.15.0", markers = "python_version < \"3.9\""},
-    {version = ">=1.19.0", markers = "python_version >= \"3.9\""},
-]
 packaging = ">=20.0"
 preshed = ">=3.0.2,<3.1.0"
 pydantic = ">=1.7.4,<1.8 || >1.8,<1.8.1 || >1.8.1,<3.0.0"
@@ -3444,10 +3346,7 @@ catalogue = ">=2.0.4,<2.1.0"
 confection = ">=0.0.1,<1.0.0"
 cymem = ">=2.0.2,<2.1.0"
 murmurhash = ">=1.0.2,<1.1.0"
-numpy = [
+numpy = {version = ">=1.19.0,<2.0.0", markers = "python_version >= \"3.9\""}
-    {version = ">=1.15.0,<2.0.0", markers = "python_version < \"3.9\""},
-    {version = ">=1.19.0,<2.0.0", markers = "python_version >= \"3.9\""},
-]
 packaging = ">=20.0"
 preshed = ">=3.0.2,<3.1.0"
 pydantic = ">=1.7.4,<1.8 || >1.8,<1.8.1 || >1.8.1,<3.0.0"
@@ -3947,5 +3846,5 @@ type = ["pytest-mypy"]
 
 [metadata]
 lock-version = "2.0"
-python-versions = ">=3.8.1,<4.0"
+python-versions = ">=3.9,<4.0"
-content-hash = "24740c1e1905b083ea4a58bcb38a15305fcc12e2864b61b0e3f93ebbbbc03149"
+content-hash = "2222f912185fe1f1df9e0fc05f9a59659999ef88f71bf0c27f5a11eb04ce1bbe"

libs/text-splitters/pyproject.toml

@@ -22,8 +22,8 @@ ignore_missing_imports = "True"
 "Release Notes" = "https://github.com/langchain-ai/langchain/releases?q=tag%3A%22langchain-text-splitters%3D%3D0%22&expanded=true"
 
 [tool.poetry.dependencies]
-python = ">=3.8.1,<4.0"
+python = ">=3.9,<4.0"
-langchain-core = "^0.2.38"
+langchain-core = { version = "^0.3.0.dev1", allow-prereleases = true }
 
 [tool.ruff.lint]
 select = [ "E", "F", "I", "T201",]

libs/text-splitters/scripts/check_pydantic.sh

@@ -1,27 +0,0 @@
-#!/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