core[patch], langchain[patch], experimental[patch]: import CI

.github/workflows/_all_ci.yml

@@ -52,8 +52,8 @@ jobs:
       working-directory: ${{ inputs.working-directory }}
     secrets: inherit
 
-  pydantic-compatibility:
-    uses: ./.github/workflows/_pydantic_compatibility.yml
+  dependencies:
+    uses: ./.github/workflows/_dependencies.yml
     with:
       working-directory: ${{ inputs.working-directory }}
     secrets: inherit

.github/workflows/_pydantic_compatibility.yml → .github/workflows/_dependencies.yml

@@ -1,4 +1,4 @@
-name: pydantic v1/v2 compatibility
+name: dependencies
 
 on:
   workflow_call:
@@ -28,7 +28,7 @@ jobs:
           - "3.9"
           - "3.10"
           - "3.11"
-    name: Pydantic v1/v2 compatibility - Python ${{ matrix.python-version }}
+    name: dependencies - Python ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v4
 
@@ -42,7 +42,15 @@ jobs:
 
       - name: Install dependencies
         shell: bash
-        run: poetry install  --with test
+        run: poetry install
+
+      - name: Check imports with base dependencies
+        shell: bash
+        run: poetry run make check_imports
+
+      - name: Install test dependencies
+        shell: bash
+        run: poetry install --with test
 
       - name: Install langchain editable
         working-directory: ${{ inputs.working-directory }}

libs/core/Makefile

@@ -15,6 +15,10 @@ tests:
 test_watch:
 	poetry run ptw --snapshot-update --now . -- -vv -x tests/unit_tests
 
+check_imports: langchain_core/**/*.py
+	for f in $^ ; do \
+		python -c "from importlib.machinery import SourceFileLoader; SourceFileLoader('x', '$$f').load_module()" || exit 1; \
+	done
 extended_tests:
 	poetry run pytest --only-extended $(TEST_FILE)
 
@@ -32,7 +36,7 @@ lint_tests: PYTHON_FILES=tests
 
 lint lint_diff lint_package lint_tests:
 	./scripts/check_pydantic.sh .
-	./scripts/check_imports.sh
+	./scripts/lint_imports.sh
 	poetry run ruff .
 	[ "$(PYTHON_FILES)" = "" ] || poetry run ruff format $(PYTHON_FILES) --diff
 	[ "$(PYTHON_FILES)" = "" ] || poetry run ruff --select I $(PYTHON_FILES)

libs/experimental/Makefile

@@ -21,6 +21,11 @@ extended_tests:
 integration_tests:
 	poetry run pytest tests/integration_tests
 
+check_imports: langchain_experimental/**/*.py
+	for f in $^ ; do \
+		python -c "from importlib.machinery import SourceFileLoader; SourceFileLoader('x', '$$f').load_module()" || exit 1; \
+	done
+
 
 ######################
 # LINTING AND FORMATTING

libs/experimental/langchain_experimental/data_anonymizer/deanonymizer_mapping.py

@@ -1,10 +1,11 @@
 import re
 from collections import defaultdict
 from dataclasses import dataclass, field
-from typing import Dict, List
+from typing import TYPE_CHECKING, Dict, List
 
-from presidio_analyzer import RecognizerResult
-from presidio_anonymizer.entities import EngineResult
+if TYPE_CHECKING:
+    from presidio_analyzer import RecognizerResult
+    from presidio_anonymizer.entities import EngineResult
 
 MappingDataType = Dict[str, Dict[str, str]]
 
@@ -62,8 +63,8 @@ def update(self, new_mapping: MappingDataType) -> None:
 
 def create_anonymizer_mapping(
     original_text: str,
-    analyzer_results: List[RecognizerResult],
-    anonymizer_results: EngineResult,
+    analyzer_results: List["RecognizerResult"],
+    anonymizer_results: "EngineResult",
     is_reversed: bool = False,
 ) -> MappingDataType:
     """Creates or updates the mapping used to anonymize and/or deanonymize text.

libs/experimental/langchain_experimental/data_anonymizer/presidio.py

@@ -23,28 +23,62 @@
     get_pseudoanonymizer_mapping,
 )
 
-try:
-    from presidio_analyzer import AnalyzerEngine
+if TYPE_CHECKING:
+    from presidio_analyzer import AnalyzerEngine, EntityRecognizer
     from presidio_analyzer.nlp_engine import NlpEngineProvider
-
-except ImportError as e:
-    raise ImportError(
-        "Could not import presidio_analyzer, please install with "
-        "`pip install presidio-analyzer`. You will also need to download a "
-        "spaCy model to use the analyzer, e.g. "
-        "`python -m spacy download en_core_web_lg`."
-    ) from e
-try:
     from presidio_anonymizer import AnonymizerEngine
     from presidio_anonymizer.entities import OperatorConfig
-except ImportError as e:
-    raise ImportError(
-        "Could not import presidio_anonymizer, please install with "
-        "`pip install presidio-anonymizer`."
-    ) from e
 
-if TYPE_CHECKING:
-    from presidio_analyzer import EntityRecognizer
+
+def _import_analyzer_engine() -> "AnalyzerEngine":
+    try:
+        from presidio_analyzer import AnalyzerEngine
+
+    except ImportError as e:
+        raise ImportError(
+            "Could not import presidio_analyzer, please install with "
+            "`pip install presidio-analyzer`. You will also need to download a "
+            "spaCy model to use the analyzer, e.g. "
+            "`python -m spacy download en_core_web_lg`."
+        ) from e
+    return AnalyzerEngine
+
+
+def _import_nlp_engine_provider() -> "NlpEngineProvider":
+    try:
+        from presidio_analyzer.nlp_engine import NlpEngineProvider
+
+    except ImportError as e:
+        raise ImportError(
+            "Could not import presidio_analyzer, please install with "
+            "`pip install presidio-analyzer`. You will also need to download a "
+            "spaCy model to use the analyzer, e.g. "
+            "`python -m spacy download en_core_web_lg`."
+        ) from e
+    return NlpEngineProvider
+
+
+def _import_anonymizer_engine() -> "AnonymizerEngine":
+    try:
+        from presidio_anonymizer import AnonymizerEngine
+    except ImportError as e:
+        raise ImportError(
+            "Could not import presidio_anonymizer, please install with "
+            "`pip install presidio-anonymizer`."
+        ) from e
+    return AnonymizerEngine
+
+
+def _import_operator_config() -> "OperatorConfig":
+    try:
+        from presidio_anonymizer.entities import OperatorConfig
+    except ImportError as e:
+        raise ImportError(
+            "Could not import presidio_anonymizer, please install with "
+            "`pip install presidio-anonymizer`."
+        ) from e
+    return OperatorConfig
+
 
 # Configuring Anonymizer for multiple languages
 # Detailed description and examples can be found here:
@@ -89,6 +123,11 @@ def __init__(
                 Defaults to None, in which case faker will be seeded randomly
                 and provide random values.
         """
+        OperatorConfig = _import_operator_config()
+        AnalyzerEngine = _import_analyzer_engine()
+        NlpEngineProvider = _import_nlp_engine_provider()
+        AnonymizerEngine = _import_anonymizer_engine()
+
         self.analyzed_fields = (
             analyzed_fields
             if analyzed_fields is not None

libs/langchain/Makefile

@@ -40,6 +40,11 @@ docker_tests:
 	docker build -t my-langchain-image:test .
 	docker run --rm my-langchain-image:test
 
+check_imports: langchain/**/*.py
+	for f in $^ ; do \
+		python -c "from importlib.machinery import SourceFileLoader; SourceFileLoader('x', '$$f').load_module()" || exit 1; \
+	done
+
 ######################
 # LINTING AND FORMATTING
 ######################
@@ -53,7 +58,7 @@ lint_tests: PYTHON_FILES=tests
 
 lint lint_diff lint_package lint_tests:
 	./scripts/check_pydantic.sh .
-	./scripts/check_imports.sh
+	./scripts/lint_imports.sh
 	poetry run ruff .
 	[ "$(PYTHON_FILES)" = "" ] || poetry run ruff format $(PYTHON_FILES) --diff
 	[ "$(PYTHON_FILES)" = "" ] || poetry run ruff --select I $(PYTHON_FILES)

libs/langchain/langchain/utilities/github.py

@@ -5,7 +5,6 @@
 from typing import TYPE_CHECKING, Any, Dict, List, Optional
 
 import requests
-import tiktoken
 from langchain_core.pydantic_v1 import BaseModel, Extra, root_validator
 
 from langchain.utils import get_from_dict_or_env
@@ -15,6 +14,18 @@
     from github.PullRequest import PullRequest
 
 
+def _import_tiktoken() -> Any:
+    """Import tiktoken."""
+    try:
+        import tiktoken
+    except ImportError:
+        raise ImportError(
+            "tiktoken is not installed. "
+            "Please install it with `pip install tiktoken`"
+        )
+    return tiktoken
+
+
 class GitHubAPIWrapper(BaseModel):
     """Wrapper for GitHub API."""
 
@@ -385,6 +396,7 @@ def list_pull_request_files(self, pr_number: int) -> List[Dict[str, Any]]:
             dict: A dictionary containing the issue's title,
             body, and comments as a string
         """
+        tiktoken = _import_tiktoken()
         MAX_TOKENS_FOR_FILES = 3_000
         pr_files = []
         pr = self.github_repo_instance.get_pull(number=int(pr_number))
@@ -453,6 +465,7 @@ def get_pull_request(self, pr_number: int) -> Dict[str, Any]:
         total_tokens = 0
 
         def get_tokens(text: str) -> int:
+            tiktoken = _import_tiktoken()
             return len(tiktoken.get_encoding("cl100k_base").encode(text))
 
         def add_to_dict(data_dict: Dict[str, Any], key: str, value: str) -> None: