community: Use default load() implementation in doc loaders (#18385)

Following https://github.com/langchain-ai/langchain/pull/18289

libs/community/langchain_community/document_loaders/acreom.py

@@ -1,6 +1,6 @@
 import re
 from pathlib import Path
-from typing import Iterator, List
+from typing import Iterator
 
 from langchain_core.documents import Document
 
@@ -74,6 +74,3 @@ class AcreomLoader(BaseLoader):
             }
 
             yield Document(page_content=text, metadata=metadata)
-
-    def load(self) -> List[Document]:
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/airbyte.py

@@ -1,4 +1,4 @@
-from typing import Any, Callable, Iterator, List, Mapping, Optional
+from typing import Any, Callable, Iterator, Mapping, Optional
 
 from langchain_core.documents import Document
 from langchain_core.utils.utils import guard_import
@@ -53,9 +53,6 @@ class AirbyteCDKLoader(BaseLoader):
         self._stream_name = stream_name
         self._state = state
 
-    def load(self) -> List[Document]:
-        return list(self.lazy_load())
-
     def lazy_load(self) -> Iterator[Document]:
         return self._integration._load_data(
             stream_name=self._stream_name, state=self._state

libs/community/langchain_community/document_loaders/airtable.py

@@ -1,4 +1,4 @@
-from typing import Iterator, List
+from typing import Iterator
 
 from langchain_core.documents import Document
 
@@ -34,7 +34,3 @@ class AirtableLoader(BaseLoader):
                     "table_id": self.table_id,
                 },
             )
-
-    def load(self) -> List[Document]:
-        """Load Documents from table."""
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/arcgis_loader.py

@@ -148,7 +148,3 @@ class ArcGISLoader(BaseLoader):
                     )
 
             yield Document(page_content=page_content, metadata=metadata)
-
-    def load(self) -> List[Document]:
-        """Load all records from FeatureLayer."""
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/astradb.py

@@ -76,9 +76,6 @@ class AstraDBLoader(BaseLoader):
         self.nb_prefetched = nb_prefetched
         self.extraction_function = extraction_function
 
-    def load(self) -> List[Document]:
-        return list(self.lazy_load())
-
     def lazy_load(self) -> Iterator[Document]:
         for doc in self.collection.paginated_find(
             filter=self.filter,

libs/community/langchain_community/document_loaders/athena.py

@@ -157,7 +157,3 @@ class AthenaLoader(BaseLoader):
             }
             doc = Document(page_content=page_content, metadata=metadata)
             yield doc
-
-    def load(self) -> List[Document]:
-        """Load data into document objects."""
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/azure_ai_data.py

@@ -1,4 +1,4 @@
-from typing import Iterator, List, Optional
+from typing import Iterator, Optional
 
 from langchain_community.docstore.document import Document
 from langchain_community.document_loaders.base import BaseLoader
@@ -16,10 +16,6 @@ class AzureAIDataLoader(BaseLoader):
         self.glob_pattern = glob
         """Optional glob pattern to select files. Defaults to None."""
 
-    def load(self) -> List[Document]:
-        """Load documents."""
-        return list(self.lazy_load())
-
     def lazy_load(self) -> Iterator[Document]:
         """A lazy loader for Documents."""
         try:

libs/community/langchain_community/document_loaders/baiducloud_bos_directory.py

@@ -1,4 +1,4 @@
-from typing import Any, Iterator, List
+from typing import Any, Iterator
 
 from langchain_core.documents import Document
 
@@ -18,9 +18,6 @@ class BaiduBOSDirectoryLoader(BaseLoader):
         self.bucket = bucket
         self.prefix = prefix
 
-    def load(self) -> List[Document]:
-        return list(self.lazy_load())
-
     def lazy_load(self) -> Iterator[Document]:
         """Load documents."""
         try:

libs/community/langchain_community/document_loaders/baiducloud_bos_file.py

@@ -1,7 +1,7 @@
 import logging
 import os
 import tempfile
-from typing import Any, Iterator, List
+from typing import Any, Iterator
 
 from langchain_core.documents import Document
 
@@ -24,9 +24,6 @@ class BaiduBOSFileLoader(BaseLoader):
         self.bucket = bucket
         self.key = key
 
-    def load(self) -> List[Document]:
-        return list(self.lazy_load())
-
     def lazy_load(self) -> Iterator[Document]:
         """Load documents."""
         try:

libs/community/langchain_community/document_loaders/bibtex.py

@@ -96,16 +96,3 @@ class BibtexLoader(BaseLoader):
             doc = self._load_entry(entry)
             if doc:
                 yield doc
-
-    def load(self) -> List[Document]:
-        """Load bibtex file documents from the given bibtex file path.
-
-        See https://bibtexparser.readthedocs.io/en/master/
-
-        Args:
-            file_path: the path to the bibtex file
-
-        Returns:
-            a list of documents with the document.page_content in text format
-        """
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/browserless.py

@@ -61,7 +61,3 @@ class BrowserlessLoader(BaseLoader):
                         "source": url,
                     },
                 )
-
-    def load(self) -> List[Document]:
-        """Load Documents from URLs."""
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/cassandra.py

@@ -5,7 +5,6 @@ from typing import (
     Any,
     Callable,
     Iterator,
-    List,
     Optional,
     Sequence,
     Union,
@@ -106,9 +105,6 @@ class CassandraLoader(BaseLoader):
         if query_execution_profile is not _NOT_SET:
             self.query_kwargs["execution_profile"] = query_execution_profile
 
-    def load(self) -> List[Document]:
-        return list(self.lazy_load())
-
     def lazy_load(self) -> Iterator[Document]:
         for row in self.session.execute(self.query, **self.query_kwargs):
             metadata = self.metadata.copy()

libs/community/langchain_community/document_loaders/chromium.py

@@ -78,14 +78,3 @@ class AsyncChromiumLoader(BaseLoader):
             html_content = asyncio.run(self.ascrape_playwright(url))
             metadata = {"source": url}
             yield Document(page_content=html_content, metadata=metadata)
-
-    def load(self) -> List[Document]:
-        """
-        Load and return all Documents from the provided URLs.
-
-        Returns:
-            List[Document]: A list of Document objects
-            containing the scraped content from each URL.
-
-        """
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/couchbase.py

@@ -68,10 +68,6 @@ class CouchbaseLoader(BaseLoader):
         self.page_content_fields = page_content_fields
         self.metadata_fields = metadata_fields
 
-    def load(self) -> List[Document]:
-        """Load Couchbase data into Document objects."""
-        return list(self.lazy_load())
-
     def lazy_load(self) -> Iterator[Document]:
         """Load Couchbase data into Document objects lazily."""
         from datetime import timedelta

libs/community/langchain_community/document_loaders/dataframe.py

@@ -1,4 +1,4 @@
-from typing import Any, Iterator, List
+from typing import Any, Iterator
 
 from langchain_core.documents import Document
 
@@ -26,10 +26,6 @@ class BaseDataFrameLoader(BaseLoader):
             metadata.pop(self.page_content_column)
             yield Document(page_content=text, metadata=metadata)
 
-    def load(self) -> List[Document]:
-        """Load full dataframe."""
-        return list(self.lazy_load())
-
 
 class DataFrameLoader(BaseDataFrameLoader):
     """Load `Pandas` DataFrame."""

libs/community/langchain_community/document_loaders/doc_intelligence.py

@@ -1,4 +1,4 @@
-from typing import Iterator, List, Optional
+from typing import Iterator, Optional
 
 from langchain_core.documents import Document
 
@@ -77,10 +77,6 @@ class AzureAIDocumentIntelligenceLoader(BaseLoader):
             mode=mode,
         )
 
-    def load(self) -> List[Document]:
-        """Load given path as pages."""
-        return list(self.lazy_load())
-
     def lazy_load(
         self,
     ) -> Iterator[Document]:

libs/community/langchain_community/document_loaders/etherscan.py

@@ -71,10 +71,6 @@ class EtherscanLoader(BaseLoader):
         for doc in result:
             yield doc
 
-    def load(self) -> List[Document]:
-        """Load transactions from spcifc account by Etherscan."""
-        return list(self.lazy_load())
-
     def getNormTx(self) -> List[Document]:
         url = (
             f"https://api.etherscan.io/api?module=account&action=txlist&address={self.account_address}"

libs/community/langchain_community/document_loaders/fauna.py

@@ -1,4 +1,4 @@
-from typing import Iterator, List, Optional, Sequence
+from typing import Iterator, Optional, Sequence
 
 from langchain_core.documents import Document
 
@@ -28,9 +28,6 @@ class FaunaLoader(BaseLoader):
         self.secret = secret
         self.metadata_fields = metadata_fields
 
-    def load(self) -> List[Document]:
-        return list(self.lazy_load())
-
     def lazy_load(self) -> Iterator[Document]:
         try:
             from fauna import Page, fql

libs/community/langchain_community/document_loaders/generic.py

@@ -115,10 +115,6 @@ class GenericLoader(BaseLoader):
         for blob in self.blob_loader.yield_blobs():
             yield from self.blob_parser.lazy_parse(blob)
 
-    def load(self) -> List[Document]:
-        """Load all documents."""
-        return list(self.lazy_load())
-
     def load_and_split(
         self, text_splitter: Optional[TextSplitter] = None
     ) -> List[Document]:

libs/community/langchain_community/document_loaders/geodataframe.py

@@ -1,4 +1,4 @@
-from typing import Any, Iterator, List
+from typing import Any, Iterator
 
 from langchain_core.documents import Document
 
@@ -67,7 +67,3 @@ class GeoDataFrameLoader(BaseLoader):
 
             # using WKT instead of str() to help GIS system interoperability
             yield Document(page_content=geom.wkt, metadata=metadata)
-
-    def load(self) -> List[Document]:
-        """Load full dataframe."""
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/github.py

@@ -127,32 +127,6 @@ class GitHubIssuesLoader(BaseGitHubLoader):
             else:
                 url = None
 
-    def load(self) -> List[Document]:
-        """
-        Get issues of a GitHub repository.
-
-        Returns:
-            A list of Documents with attributes:
-                - page_content
-                - metadata
-                    - url
-                    - title
-                    - creator
-                    - created_at
-                    - last_update_time
-                    - closed_time
-                    - number of comments
-                    - state
-                    - labels
-                    - assignee
-                    - assignees
-                    - milestone
-                    - locked
-                    - number
-                    - is_pull_request
-        """
-        return list(self.lazy_load())
-
     def parse_issue(self, issue: dict) -> Document:
         """Create Document objects from a list of GitHub issues."""
         metadata = {

libs/community/langchain_community/document_loaders/hugging_face_dataset.py

@@ -1,5 +1,5 @@
 import json
-from typing import Iterator, List, Mapping, Optional, Sequence, Union
+from typing import Iterator, Mapping, Optional, Sequence, Union
 
 from langchain_core.documents import Document
 
@@ -84,10 +84,6 @@ class HuggingFaceDatasetLoader(BaseLoader):
             for row in dataset[key]
         )
 
-    def load(self) -> List[Document]:
-        """Load documents."""
-        return list(self.lazy_load())
-
     def parse_obj(self, page_content: Union[str, object]) -> str:
         if isinstance(page_content, object):
             return json.dumps(page_content)

libs/community/langchain_community/document_loaders/hugging_face_model.py

@@ -106,7 +106,3 @@ class HuggingFaceModelLoader(BaseLoader):
                 page_content=readme_content,
                 metadata=model,
             )
-
-    def load(self) -> List[Document]:
-        """Load model information, including README content."""
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/joplin.py

@@ -91,6 +91,3 @@ class JoplinLoader(BaseLoader):
 
     def lazy_load(self) -> Iterator[Document]:
         yield from self._get_notes()
-
-    def load(self) -> List[Document]:
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/larksuite.py

@@ -1,6 +1,6 @@
 import json
 import urllib.request
-from typing import Any, Iterator, List
+from typing import Any, Iterator
 
 from langchain_core.documents import Document
 
@@ -46,7 +46,3 @@ class LarkSuiteDocLoader(BaseLoader):
             "title": metadata_json["data"]["document"]["title"],
         }
         yield Document(page_content=text, metadata=metadata)
-
-    def load(self) -> List[Document]:
-        """Load LarkSuite (FeiShu) document."""
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/max_compute.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from typing import Any, Iterator, List, Optional, Sequence
+from typing import Any, Iterator, Optional, Sequence
 
 from langchain_core.documents import Document
 
@@ -78,6 +78,3 @@ class MaxComputeLoader(BaseLoader):
             else:
                 metadata = {k: v for k, v in row.items() if k not in page_content_data}
             yield Document(page_content=page_content, metadata=metadata)
-
-    def load(self) -> List[Document]:
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/mediawikidump.py

@@ -1,6 +1,6 @@
 import logging
 from pathlib import Path
-from typing import Iterator, List, Optional, Sequence, Union
+from typing import Iterator, Optional, Sequence, Union
 
 from langchain_core.documents import Document
 
@@ -87,11 +87,6 @@ class MWDumpLoader(BaseLoader):
             metadata = {"source": page.title}
             return Document(page_content=text, metadata=metadata)
 
-    def load(self) -> List[Document]:
-        """Load from a file path."""
-
-        return [doc for doc in self.lazy_load()]
-
     def lazy_load(
         self,
     ) -> Iterator[Document]:

libs/community/langchain_community/document_loaders/merge.py

@@ -23,10 +23,6 @@ class MergedDataLoader(BaseLoader):
             for document in data:
                 yield document
 
-    def load(self) -> List[Document]:
-        """Load docs."""
-        return list(self.lazy_load())
-
     async def alazy_load(self) -> AsyncIterator[Document]:
         """Lazy load docs from each individual loader."""
         for loader in self.loaders:

libs/community/langchain_community/document_loaders/onedrive.py

@@ -91,7 +91,3 @@ class OneDriveLoader(O365BaseLoader):
         if self.object_ids:
             for blob in self._load_from_object_ids(drive, self.object_ids):
                 yield from blob_parser.lazy_parse(blob)
-
-    def load(self) -> List[Document]:
-        """Load all documents."""
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/onenote.py

@@ -109,18 +109,6 @@ class OneNoteLoader(BaseLoader, BaseModel):
                 else:
                     request_url = ""
 
-    def load(self) -> List[Document]:
-        """
-        Get pages from OneNote notebooks.
-
-        Returns:
-            A list of Documents with attributes:
-                - page_content
-                - metadata
-                    - title
-        """
-        return list(self.lazy_load())
-
     def _get_page_content(self, page_id: str) -> str:
         """Get page content from OneNote API"""
         request_url = self.onenote_api_base_url + f"/pages/{page_id}/content"

libs/community/langchain_community/document_loaders/open_city_data.py

@@ -1,4 +1,4 @@
-from typing import Iterator, List
+from typing import Iterator
 
 from langchain_core.documents import Document
 
@@ -37,8 +37,3 @@ class OpenCityDataLoader(BaseLoader):
                     "source": self.city_id + "_" + self.dataset_id,
                 },
             )
-
-    def load(self) -> List[Document]:
-        """Load records."""
-
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/pdf.py

@@ -157,10 +157,6 @@ class PyPDFLoader(BasePDFLoader):
         super().__init__(file_path, headers=headers)
         self.parser = PyPDFParser(password=password, extract_images=extract_images)
 
-    def load(self) -> List[Document]:
-        """Load given path as pages."""
-        return list(self.lazy_load())
-
     def lazy_load(
         self,
     ) -> Iterator[Document]:

libs/community/langchain_community/document_loaders/pubmed.py

@@ -1,4 +1,4 @@
-from typing import Iterator, List, Optional
+from typing import Iterator, Optional
 
 from langchain_core.documents import Document
 
@@ -32,9 +32,6 @@ class PubMedLoader(BaseLoader):
             top_k_results=load_max_docs,
         )
 
-    def load(self) -> List[Document]:
-        return list(self._client.lazy_load_docs(self.query))
-
     def lazy_load(self) -> Iterator[Document]:
         for doc in self._client.lazy_load_docs(self.query):
             yield doc

libs/community/langchain_community/document_loaders/readthedocs.py

@@ -84,10 +84,6 @@ class ReadTheDocsLoader(BaseLoader):
                     text = self._clean_data(f.read())
                 yield Document(page_content=text, metadata={"source": str(p)})
 
-    def load(self) -> List[Document]:
-        """Load documents."""
-        return list(self.lazy_load())
-
     def _clean_data(self, data: str) -> str:
         from bs4 import BeautifulSoup
 

libs/community/langchain_community/document_loaders/recursive_url_loader.py

@@ -314,7 +314,3 @@ class RecursiveUrlLoader(BaseLoader):
             return iter(results or [])
         else:
             return self._get_child_links_recursive(self.url, visited)
-
-    def load(self) -> List[Document]:
-        """Load web pages."""
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/rocksetdb.py

@@ -100,9 +100,6 @@ class RocksetLoader(BaseLoader):
             # ignore
             pass
 
-    def load(self) -> List[Document]:
-        return list(self.lazy_load())
-
     def lazy_load(self) -> Iterator[Document]:
         query_results = self.client.Queries.query(
             sql=self.query

libs/community/langchain_community/document_loaders/rspace.py

@@ -124,6 +124,3 @@ class RSpaceLoader(BaseLoader):
                 yield d
         else:
             raise ValueError("Unknown global ID type")
-
-    def load(self) -> List[Document]:
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/sharepoint.py

@@ -54,7 +54,3 @@ class SharePointLoader(O365BaseLoader):
         if self.object_ids:
             for blob in self._load_from_object_ids(drive, self.object_ids):
                 yield from blob_parser.lazy_parse(blob)
-
-    def load(self) -> List[Document]:
-        """Load all documents."""
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/snowflake_loader.py

@@ -122,7 +122,3 @@ class SnowflakeLoader(BaseLoader):
             metadata = {k: v for k, v in row.items() if k in metadata_columns}
             doc = Document(page_content=page_content, metadata=metadata)
             yield doc
-
-    def load(self) -> List[Document]:
-        """Load data into document objects."""
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/sql_database.py

@@ -104,9 +104,6 @@ class SQLDatabaseLoader(BaseLoader):
 
             yield Document(page_content=page_content, metadata=metadata)
 
-    def load(self) -> List[Document]:
-        return list(self.lazy_load())
-
     @staticmethod
     def page_content_default_mapper(
         row: sa.RowMapping, column_names: Optional[List[str]] = None

libs/community/langchain_community/document_loaders/tencent_cos_directory.py

@@ -1,4 +1,4 @@
-from typing import Any, Iterator, List
+from typing import Any, Iterator
 
 from langchain_core.documents import Document
 
@@ -19,9 +19,6 @@ class TencentCOSDirectoryLoader(BaseLoader):
         self.bucket = bucket
         self.prefix = prefix
 
-    def load(self) -> List[Document]:
-        return list(self.lazy_load())
-
     def lazy_load(self) -> Iterator[Document]:
         """Load documents."""
         try:

libs/community/langchain_community/document_loaders/tencent_cos_file.py

@@ -1,6 +1,6 @@
 import os
 import tempfile
-from typing import Any, Iterator, List
+from typing import Any, Iterator
 
 from langchain_core.documents import Document
 
@@ -21,9 +21,6 @@ class TencentCOSFileLoader(BaseLoader):
         self.bucket = bucket
         self.key = key
 
-    def load(self) -> List[Document]:
-        return list(self.lazy_load())
-
     def lazy_load(self) -> Iterator[Document]:
         """Load documents."""
         try:

libs/community/langchain_community/document_loaders/tensorflow_datasets.py

@@ -1,4 +1,4 @@
-from typing import Callable, Dict, Iterator, List, Optional
+from typing import Callable, Dict, Iterator, Optional
 
 from langchain_core.documents import Document
 
@@ -75,6 +75,3 @@ class TensorflowDatasetLoader(BaseLoader):
 
     def lazy_load(self) -> Iterator[Document]:
         yield from self._tfds_client.lazy_load()
-
-    def load(self) -> List[Document]:
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/tidb.py

@@ -65,7 +65,3 @@ class TiDBLoader(BaseLoader):
                 )
                 metadata = {col: row_data[col] for col in self.metadata_columns}
                 yield Document(page_content=page_content, metadata=metadata)
-
-    def load(self) -> List[Document]:
-        """Load TiDB data into document objects."""
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/tomarkdown.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from typing import Iterator, List
+from typing import Iterator
 
 import requests
 from langchain_core.documents import Document
@@ -28,7 +28,3 @@ class ToMarkdownLoader(BaseLoader):
         text = response.json()["article"]
         metadata = {"source": self.url}
         yield Document(page_content=text, metadata=metadata)
-
-    def load(self) -> List[Document]:
-        """Load file."""
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/toml.py

@@ -1,6 +1,6 @@
 import json
 from pathlib import Path
-from typing import Iterator, List, Union
+from typing import Iterator, Union
 
 from langchain_core.documents import Document
 
@@ -18,10 +18,6 @@ class TomlLoader(BaseLoader):
         """Initialize the TomlLoader with a source file or directory."""
         self.source = Path(source)
 
-    def load(self) -> List[Document]:
-        """Load and return all documents."""
-        return list(self.lazy_load())
-
     def lazy_load(self) -> Iterator[Document]:
         """Lazily load the TOML documents from the source file or directory."""
         import tomli

libs/community/langchain_community/document_loaders/weather.py

@@ -2,7 +2,7 @@
 from __future__ import annotations
 
 from datetime import datetime
-from typing import Iterator, List, Optional, Sequence
+from typing import Iterator, Optional, Sequence
 
 from langchain_core.documents import Document
 
@@ -43,9 +43,3 @@ class WeatherDataLoader(BaseLoader):
             metadata = {"queried_at": datetime.now()}
             content = self.client.run(place)
             yield Document(page_content=content, metadata=metadata)
-
-    def load(
-        self,
-    ) -> List[Document]:
-        """Load weather data for the given locations."""
-        return list(self.lazy_load())

libs/community/langchain_community/document_loaders/web_base.py

@@ -251,10 +251,6 @@ class WebBaseLoader(BaseLoader):
             metadata = _build_metadata(soup, path)
             yield Document(page_content=text, metadata=metadata)
 
-    def load(self) -> List[Document]:
-        """Load text from the url(s) in web_path."""
-        return list(self.lazy_load())
-
     def aload(self) -> List[Document]:
         """Load text from the urls in web_path async into Documents."""
 

libs/langchain/tests/unit_tests/indexes/test_indexing.py

@@ -36,10 +36,6 @@ class ToyLoader(BaseLoader):
     ) -> Iterator[Document]:
         yield from self.documents
 
-    def load(self) -> List[Document]:
-        """Load the documents from the source."""
-        return list(self.lazy_load())
-
     async def alazy_load(
         self,
     ) -> AsyncIterator[Document]: