mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-10 23:41:28 +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:
@@ -0,0 +1,65 @@
|
||||
import re
|
||||
from pathlib import Path
|
||||
from typing import List
|
||||
|
||||
from langchain_core.documents import Document
|
||||
|
||||
from langchain_community.document_loaders.base import BaseLoader
|
||||
|
||||
|
||||
def concatenate_rows(date: str, sender: str, text: str) -> str:
|
||||
"""Combine message information in a readable format ready to be used."""
|
||||
return f"{sender} on {date}: {text}\n\n"
|
||||
|
||||
|
||||
class WhatsAppChatLoader(BaseLoader):
|
||||
"""Load `WhatsApp` messages text file."""
|
||||
|
||||
def __init__(self, path: str):
|
||||
"""Initialize with path."""
|
||||
self.file_path = path
|
||||
|
||||
def load(self) -> List[Document]:
|
||||
"""Load documents."""
|
||||
p = Path(self.file_path)
|
||||
text_content = ""
|
||||
|
||||
with open(p, encoding="utf8") as f:
|
||||
lines = f.readlines()
|
||||
|
||||
message_line_regex = r"""
|
||||
\[?
|
||||
(
|
||||
\d{1,4}
|
||||
[\/.]
|
||||
\d{1,2}
|
||||
[\/.]
|
||||
\d{1,4}
|
||||
,\s
|
||||
\d{1,2}
|
||||
:\d{2}
|
||||
(?:
|
||||
:\d{2}
|
||||
)?
|
||||
(?:[\s_](?:AM|PM))?
|
||||
)
|
||||
\]?
|
||||
[\s-]*
|
||||
([~\w\s]+)
|
||||
[:]+
|
||||
\s
|
||||
(.+)
|
||||
"""
|
||||
ignore_lines = ["This message was deleted", "<Media omitted>"]
|
||||
for line in lines:
|
||||
result = re.match(
|
||||
message_line_regex, line.strip(), flags=re.VERBOSE | re.IGNORECASE
|
||||
)
|
||||
if result:
|
||||
date, sender, text = result.groups()
|
||||
if text not in ignore_lines:
|
||||
text_content += concatenate_rows(date, sender, text)
|
||||
|
||||
metadata = {"source": str(p)}
|
||||
|
||||
return [Document(page_content=text_content, metadata=metadata)]
|
Reference in New Issue
Block a user