REFACTOR: combine core documents files (#13733)

libs/core/langchain_core/documents/__init__.py

@@ -0,0 +1,4 @@
+from langchain_core.documents.base import Document
+from langchain_core.documents.transformers import BaseDocumentTransformer
+
+__all__ = ["Document", "BaseDocumentTransformer"]

libs/core/tests/unit_tests/documents/test_imports.py

@@ -0,0 +1,7 @@
+from langchain_core.documents import __all__
+
+EXPECTED_ALL = ["Document", "BaseDocumentTransformer"]
+
+
+def test_all_imports() -> None:
+    assert set(__all__) == set(EXPECTED_ALL)

libs/langchain/langchain/document_transformers/beautiful_soup_transformer.py

@@ -1,7 +1,6 @@
 from typing import Any, Iterator, List, Sequence, cast
 
-from langchain_core.document_transformers import BaseDocumentTransformer
+from langchain_core.documents import BaseDocumentTransformer, Document
-from langchain_core.documents import Document
 
 
 class BeautifulSoupTransformer(BaseDocumentTransformer):

libs/langchain/langchain/document_transformers/doctran_text_extract.py

@@ -1,7 +1,6 @@
 from typing import Any, List, Optional, Sequence
 
-from langchain_core.document_transformers import BaseDocumentTransformer
+from langchain_core.documents import BaseDocumentTransformer, Document
-from langchain_core.documents import Document
 
 from langchain.utils import get_from_env
 

libs/langchain/langchain/document_transformers/doctran_text_qa.py

@@ -1,7 +1,6 @@
 from typing import Any, Optional, Sequence
 
-from langchain_core.document_transformers import BaseDocumentTransformer
+from langchain_core.documents import BaseDocumentTransformer, Document
-from langchain_core.documents import Document
 
 from langchain.utils import get_from_env
 

libs/langchain/langchain/document_transformers/doctran_text_translate.py

@@ -1,7 +1,6 @@
 from typing import Any, Optional, Sequence
 
-from langchain_core.document_transformers import BaseDocumentTransformer
+from langchain_core.documents import BaseDocumentTransformer, Document
-from langchain_core.documents import Document
 
 from langchain.utils import get_from_env
 

libs/langchain/langchain/document_transformers/embeddings_redundant_filter.py

@@ -2,8 +2,7 @@
 from typing import Any, Callable, List, Sequence
 
 import numpy as np
-from langchain_core.document_transformers import BaseDocumentTransformer
+from langchain_core.documents import BaseDocumentTransformer, Document
-from langchain_core.documents import Document
 from langchain_core.embeddings import Embeddings
 from langchain_core.pydantic_v1 import BaseModel, Field
 

libs/langchain/langchain/document_transformers/google_translate.py

@@ -1,7 +1,6 @@
 from typing import Any, Optional, Sequence
 
-from langchain_core.document_transformers import BaseDocumentTransformer
+from langchain_core.documents import BaseDocumentTransformer, Document
-from langchain_core.documents import Document
 
 from langchain.utilities.vertexai import get_client_info
 

libs/langchain/langchain/document_transformers/html2text.py

@@ -1,7 +1,6 @@
 from typing import Any, Sequence
 
-from langchain_core.document_transformers import BaseDocumentTransformer
+from langchain_core.documents import BaseDocumentTransformer, Document
-from langchain_core.documents import Document
 
 
 class Html2TextTransformer(BaseDocumentTransformer):

libs/langchain/langchain/document_transformers/long_context_reorder.py

@@ -1,8 +1,7 @@
 """Reorder documents"""
 from typing import Any, List, Sequence
 
-from langchain_core.document_transformers import BaseDocumentTransformer
+from langchain_core.documents import BaseDocumentTransformer, Document
-from langchain_core.documents import Document
 from langchain_core.pydantic_v1 import BaseModel
 
 

libs/langchain/langchain/document_transformers/nuclia_text_transform.py

@@ -3,8 +3,7 @@ import json
 import uuid
 from typing import Any, Sequence
 
-from langchain_core.document_transformers import BaseDocumentTransformer
+from langchain_core.documents import BaseDocumentTransformer, Document
-from langchain_core.documents import Document
 
 from langchain.tools.nuclia.tool import NucliaUnderstandingAPI
 

libs/langchain/langchain/document_transformers/openai_functions.py

@@ -1,8 +1,7 @@
 """Document transformers that use OpenAI Functions models"""
 from typing import Any, Dict, Optional, Sequence, Type, Union
 
-from langchain_core.document_transformers import BaseDocumentTransformer
+from langchain_core.documents import BaseDocumentTransformer, Document
-from langchain_core.documents import Document
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.prompts import ChatPromptTemplate
 from langchain_core.pydantic_v1 import BaseModel

libs/langchain/langchain/retrievers/document_compressors/base.py

@@ -3,8 +3,7 @@ from abc import ABC, abstractmethod
 from inspect import signature
 from typing import List, Optional, Sequence, Union
 
-from langchain_core.document_transformers import BaseDocumentTransformer
+from langchain_core.documents import BaseDocumentTransformer, Document
-from langchain_core.documents import Document
 from langchain_core.pydantic_v1 import BaseModel
 
 from langchain.callbacks.manager import Callbacks

libs/langchain/langchain/schema/__init__.py

@@ -2,8 +2,7 @@
 from langchain_core.agents import AgentAction, AgentFinish
 from langchain_core.caches import BaseCache
 from langchain_core.chat_history import BaseChatMessageHistory
-from langchain_core.document_transformers import BaseDocumentTransformer
+from langchain_core.documents import BaseDocumentTransformer, Document
-from langchain_core.documents import Document
 from langchain_core.exceptions import LangChainException, OutputParserException
 from langchain_core.memory import BaseMemory
 from langchain_core.messages import (

libs/langchain/langchain/schema/document.py

@@ -1,4 +1,3 @@
-from langchain_core.document_transformers import BaseDocumentTransformer
+from langchain_core.documents import BaseDocumentTransformer, Document
-from langchain_core.documents import Document
 
 __all__ = ["Document", "BaseDocumentTransformer"]

libs/langchain/langchain/text_splitter.py

@@ -51,7 +51,7 @@ from typing import (
 )
 
 import requests
-from langchain_core.document_transformers import BaseDocumentTransformer
+from langchain_core.documents import BaseDocumentTransformer
 
 from langchain.docstore.document import Document