Skip to content

Commit

Permalink
community[minor]: Add ability to specify file encoding and json encod…
Browse files Browse the repository at this point in the history
…ing for FileChatMessageHistory (#24258)

Description:
Add UTF-8 encoding support

Issue:
Inability to properly handle characters from certain languages (e.g.,
Korean)

Fix:
Implement UTF-8 encoding in FileChatMessageHistory

---------

Co-authored-by: Eugene Yurtsev <[email protected]>
Co-authored-by: Eugene Yurtsev <[email protected]>
  • Loading branch information
3 people authored Jul 19, 2024
1 parent 020cc1c commit 07715f8
Showing 1 changed file with 23 additions and 7 deletions.
30 changes: 23 additions & 7 deletions libs/community/langchain_community/chat_message_histories/file.py
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
import json
from pathlib import Path
from typing import List
from typing import List, Optional

from langchain_core.chat_history import (
BaseChatMessageHistory,
Expand All @@ -11,30 +11,46 @@
class FileChatMessageHistory(BaseChatMessageHistory):
"""Chat message history that stores history in a local file."""

def __init__(self, file_path: str) -> None:
def __init__(
self,
file_path: str,
*,
encoding: Optional[str] = None,
ensure_ascii: bool = True,
) -> None:
"""Initialize the file path for the chat history.
Args:
file_path: The path to the local file to store the chat history.
encoding: The encoding to use for file operations. Defaults to None.
ensure_ascii: If True, escape non-ASCII in JSON. Defaults to True.
"""
self.file_path = Path(file_path)
self.encoding = encoding
self.ensure_ascii = ensure_ascii

if not self.file_path.exists():
self.file_path.touch()
self.file_path.write_text(json.dumps([]))
self.file_path.write_text(
json.dumps([], ensure_ascii=self.ensure_ascii), encoding=self.encoding
)

@property
def messages(self) -> List[BaseMessage]: # type: ignore
"""Retrieve the messages from the local file"""
items = json.loads(self.file_path.read_text())
items = json.loads(self.file_path.read_text(encoding=self.encoding))
messages = messages_from_dict(items)
return messages

def add_message(self, message: BaseMessage) -> None:
"""Append the message to the record in the local file"""
messages = messages_to_dict(self.messages)
messages.append(messages_to_dict([message])[0])
self.file_path.write_text(json.dumps(messages))
self.file_path.write_text(
json.dumps(messages, ensure_ascii=self.ensure_ascii), encoding=self.encoding
)

def clear(self) -> None:
"""Clear session memory from the local file"""
self.file_path.write_text(json.dumps([]))
self.file_path.write_text(
json.dumps([], ensure_ascii=self.ensure_ascii), encoding=self.encoding
)

0 comments on commit 07715f8

Please sign in to comment.