mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-04 12:39:32 +00:00
community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463)
Moved the following modules to new package langchain-community in a backwards compatible fashion: ``` mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community ``` Moved the following to core ``` mv langchain/langchain/utils/json_schema.py core/langchain_core/utils mv langchain/langchain/utils/html.py core/langchain_core/utils mv langchain/langchain/utils/strings.py core/langchain_core/utils cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py rm langchain/langchain/utils/env.py ``` See .scripts/community_split/script_integrations.sh for all changes
This commit is contained in:
60
libs/community/langchain_community/document_loaders/text.py
Normal file
60
libs/community/langchain_community/document_loaders/text.py
Normal file
@@ -0,0 +1,60 @@
|
||||
import logging
|
||||
from typing import List, Optional
|
||||
|
||||
from langchain_core.documents import Document
|
||||
|
||||
from langchain_community.document_loaders.base import BaseLoader
|
||||
from langchain_community.document_loaders.helpers import detect_file_encodings
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class TextLoader(BaseLoader):
|
||||
"""Load text file.
|
||||
|
||||
|
||||
Args:
|
||||
file_path: Path to the file to load.
|
||||
|
||||
encoding: File encoding to use. If `None`, the file will be loaded
|
||||
with the default system encoding.
|
||||
|
||||
autodetect_encoding: Whether to try to autodetect the file encoding
|
||||
if the specified encoding fails.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
file_path: str,
|
||||
encoding: Optional[str] = None,
|
||||
autodetect_encoding: bool = False,
|
||||
):
|
||||
"""Initialize with file path."""
|
||||
self.file_path = file_path
|
||||
self.encoding = encoding
|
||||
self.autodetect_encoding = autodetect_encoding
|
||||
|
||||
def load(self) -> List[Document]:
|
||||
"""Load from file path."""
|
||||
text = ""
|
||||
try:
|
||||
with open(self.file_path, encoding=self.encoding) as f:
|
||||
text = f.read()
|
||||
except UnicodeDecodeError as e:
|
||||
if self.autodetect_encoding:
|
||||
detected_encodings = detect_file_encodings(self.file_path)
|
||||
for encoding in detected_encodings:
|
||||
logger.debug(f"Trying encoding: {encoding.encoding}")
|
||||
try:
|
||||
with open(self.file_path, encoding=encoding.encoding) as f:
|
||||
text = f.read()
|
||||
break
|
||||
except UnicodeDecodeError:
|
||||
continue
|
||||
else:
|
||||
raise RuntimeError(f"Error loading {self.file_path}") from e
|
||||
except Exception as e:
|
||||
raise RuntimeError(f"Error loading {self.file_path}") from e
|
||||
|
||||
metadata = {"source": self.file_path}
|
||||
return [Document(page_content=text, metadata=metadata)]
|
Reference in New Issue
Block a user