langchain/libs/partners/unstructured/Makefile

.PHONY: all format lint test tests 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/
integration_test integration_tests: TEST_FILE = tests/integration_tests/


# unit tests are run with the --disable-socket flag to prevent network calls
test tests:
	poetry run pytest --disable-socket --allow-unix-socket $(TEST_FILE)

# integration tests are run without the --disable-socket flag to allow network calls
integration_test:
	poetry run pytest $(TEST_FILE)

# skip tests marked as local in CI
integration_tests:
	poetry run pytest $(TEST_FILE) -m "not local"

######################
# 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/partners/unstructured --name-only --diff-filter=d master | grep -E '\.py$$|\.ipynb$$')
lint_package: PYTHON_FILES=langchain_unstructured
lint_tests: PYTHON_FILES=tests
lint_tests: MYPY_CACHE=.mypy_cache_test

lint lint_diff lint_package lint_tests:
	poetry run ruff .
	poetry run ruff format $(PYTHON_FILES) --diff
	poetry run ruff --select I $(PYTHON_FILES)
	mkdir -p $(MYPY_CACHE); poetry run mypy $(PYTHON_FILES) --cache-dir $(MYPY_CACHE)

format format_diff:
	poetry run ruff format $(PYTHON_FILES)
	poetry run ruff --select I --fix $(PYTHON_FILES)

spell_check:
	poetry run codespell --toml pyproject.toml

spell_fix:
	poetry run codespell --toml pyproject.toml -w

check_imports: $(shell find langchain_unstructured -name '*.py')
	poetry run python ./scripts/check_imports.py $^

######################
# HELP
######################

help:
	@echo '----'
	@echo 'check_imports				- check imports'
	@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'
unstructured, community, initialize langchain-unstructured package (#22779) #### Update (2): A single `UnstructuredLoader` is added to handle both local and api partitioning. This loader also handles single or multiple documents. #### Changes in `community`: Changes here do not affect users. In the initial process of using the SDK for the API Loaders, the Loaders in community were refactored. Other changes include: The `UnstructuredBaseLoader` has a new check to see if both `mode="paged"` and `chunking_strategy="by_page"`. It also now has `Element.element_id` added to the `Document.metadata`. `UnstructuredAPIFileLoader` and `UnstructuredAPIFileIOLoader`. As such, now both directly inherit from `UnstructuredBaseLoader` and initialize their `file_path`/`file` attributes respectively and implement their own `_post_process_elements` methods. -------- #### Update: New SDK Loaders in a [partner package](https://python.langchain.com/v0.1/docs/contributing/integrations/#partner-package-in-langchain-repo) are introduced to prevent breaking changes for users (see discussion below). ##### TODO: - [x] Test docstring examples -------- - Description: UnstructuredAPIFileIOLoader and UnstructuredAPIFileLoader calls to the unstructured api are now made using the unstructured-client sdk. - New Dependencies: unstructured-client - [x] Add tests and docs: If you're adding a new integration, please include - [x] a test for the integration, preferably unit tests that do not rely on network access, - [x] update the description in `docs/docs/integrations/providers/unstructured.mdx` - [x] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. TODO: - [x] Update https://python.langchain.com/v0.1/docs/integrations/document_loaders/unstructured_file/#unstructured-api - `langchain/docs/docs/integrations/document_loaders/unstructured_file.ipynb` - The description here needs to indicate that users should install `unstructured-client` instead of `unstructured`. Read over closely to look for any other changes that need to be made. - [x] Update the `lazy_load` method in `UnstructuredBaseLoader` to handle json responses from the API instead of just lists of elements. - This method may need to be overwritten by the API loaders instead of changing it in the `UnstructuredBaseLoader`. - [x] Update the documentation links in the class docstrings (the Unstructured documents have moved) - [x] Update Document.metadata to include `element_id` (see thread [here](https://unstructuredw-kbe4326.slack.com/archives/C044N0YV08G/p1718187499818419)) --------- Signed-off-by: ChengZi <chen.zhang@zilliz.com> Co-authored-by: Erick Friis <erick@langchain.dev> Co-authored-by: Isaac Francisco <78627776+isahers1@users.noreply.github.com> Co-authored-by: ChengZi <chen.zhang@zilliz.com> 2 months ago			`.PHONY: all format lint test tests 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/`
			`integration_test integration_tests: TEST_FILE = tests/integration_tests/`


			`# unit tests are run with the --disable-socket flag to prevent network calls`
			`test tests:`
			`poetry run pytest --disable-socket --allow-unix-socket $(TEST_FILE)`

			`# integration tests are run without the --disable-socket flag to allow network calls`
			`integration_test:`
			`poetry run pytest $(TEST_FILE)`

			`# skip tests marked as local in CI`
			`integration_tests:`
			`poetry run pytest $(TEST_FILE) -m "not local"`

			`######################`
			`# 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/partners/unstructured --name-only --diff-filter=d master \| grep -E '\.py$$\|\.ipynb$$')`
			`lint_package: PYTHON_FILES=langchain_unstructured`
			`lint_tests: PYTHON_FILES=tests`
			`lint_tests: MYPY_CACHE=.mypy_cache_test`

			`lint lint_diff lint_package lint_tests:`
			`poetry run ruff .`
			`poetry run ruff format $(PYTHON_FILES) --diff`
			`poetry run ruff --select I $(PYTHON_FILES)`
			`mkdir -p $(MYPY_CACHE); poetry run mypy $(PYTHON_FILES) --cache-dir $(MYPY_CACHE)`

			`format format_diff:`
			`poetry run ruff format $(PYTHON_FILES)`
			`poetry run ruff --select I --fix $(PYTHON_FILES)`

			`spell_check:`
			`poetry run codespell --toml pyproject.toml`

			`spell_fix:`
			`poetry run codespell --toml pyproject.toml -w`

			`check_imports: $(shell find langchain_unstructured -name '*.py')`
			`poetry run python ./scripts/check_imports.py $^`

			`######################`
			`# HELP`
			`######################`

			`help:`
			`@echo '----'`
			`@echo 'check_imports - check imports'`
			`@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'`