mirror of
https://github.com/hwchase17/langchain.git
synced 2025-06-01 04:29:09 +00:00
b2102b8cc4
This PR closes #27781 # Problem The current implementation of `NLTKTextSplitter` is using `sent_tokenize`. However, this `sent_tokenize` doesn't handle chars between 2 tokenized sentences... hence, this behavior throws errors when we are using `add_start_index=True`, as described in issue #27781. In particular: ```python from nltk.tokenize import sent_tokenize output1 = sent_tokenize("Innovation drives our success. Collaboration fosters creative solutions. Efficiency enhances data management.", language="english") print(output1) output2 = sent_tokenize("Innovation drives our success. Collaboration fosters creative solutions. Efficiency enhances data management.", language="english") print(output2) >>> ['Innovation drives our success.', 'Collaboration fosters creative solutions.', 'Efficiency enhances data management.'] >>> ['Innovation drives our success.', 'Collaboration fosters creative solutions.', 'Efficiency enhances data management.'] ``` # Solution With this new `use_span_tokenize` parameter, we can use NLTK to create sentences (with `span_tokenize`), but also add extra chars to be sure that we still can map the chunks to the original text. --------- Co-authored-by: Erick Friis <erick@langchain.dev> Co-authored-by: Erick Friis <erickfriis@gmail.com>
69 lines
2.2 KiB
Makefile
69 lines
2.2 KiB
Makefile
.PHONY: all format lint test tests test_watch integration_tests docker_tests help extended_tests
|
|
|
|
# Default target executed when no arguments are given to make.
|
|
all: help
|
|
|
|
# Define a variable for the test file path.
|
|
TEST_FILE ?= tests/unit_tests/
|
|
|
|
test tests:
|
|
poetry run pytest --disable-socket --allow-unix-socket $(TEST_FILE)
|
|
|
|
integration_test integration_tests:
|
|
poetry run pytest tests/integration_tests/
|
|
|
|
test_watch:
|
|
poetry run ptw --snapshot-update --now . -- -vv -x tests/unit_tests
|
|
|
|
test_profile:
|
|
poetry run pytest -vv tests/unit_tests/ --profile-svg
|
|
|
|
check_imports: $(shell find langchain_text_splitters -name '*.py')
|
|
poetry run python ./scripts/check_imports.py $^
|
|
|
|
extended_tests:
|
|
poetry run pytest --disable-socket --allow-unix-socket --only-extended $(TEST_FILE)
|
|
|
|
|
|
######################
|
|
# LINTING AND FORMATTING
|
|
######################
|
|
|
|
# Define a variable for Python and notebook files.
|
|
PYTHON_FILES=.
|
|
MYPY_CACHE=.mypy_cache
|
|
lint format: PYTHON_FILES=.
|
|
lint_diff format_diff: PYTHON_FILES=$(shell git diff --relative=libs/core --name-only --diff-filter=d master | grep -E '\.py$$|\.ipynb$$')
|
|
lint_package: PYTHON_FILES=langchain_text_splitters
|
|
lint_tests: PYTHON_FILES=tests
|
|
lint_tests: MYPY_CACHE=.mypy_cache_test
|
|
|
|
lint lint_diff lint_package lint_tests:
|
|
./scripts/lint_imports.sh
|
|
[ "$(PYTHON_FILES)" = "" ] || poetry run ruff check $(PYTHON_FILES)
|
|
[ "$(PYTHON_FILES)" = "" ] || poetry run ruff format $(PYTHON_FILES) --diff
|
|
[ "$(PYTHON_FILES)" = "" ] || mkdir -p $(MYPY_CACHE) && poetry run mypy $(PYTHON_FILES) --cache-dir $(MYPY_CACHE)
|
|
|
|
format format_diff:
|
|
[ "$(PYTHON_FILES)" = "" ] || poetry run ruff format $(PYTHON_FILES)
|
|
[ "$(PYTHON_FILES)" = "" ] || poetry run ruff check --select I --fix $(PYTHON_FILES)
|
|
|
|
spell_check:
|
|
poetry run codespell --toml pyproject.toml
|
|
|
|
spell_fix:
|
|
poetry run codespell --toml pyproject.toml -w
|
|
|
|
######################
|
|
# HELP
|
|
######################
|
|
|
|
help:
|
|
@echo '----'
|
|
@echo 'format - run code formatters'
|
|
@echo 'lint - run linters'
|
|
@echo 'test - run unit tests'
|
|
@echo 'tests - run unit tests'
|
|
@echo 'test TEST_FILE=<test_file> - run all tests in file'
|
|
@echo 'test_watch - run unit tests in watch mode'
|