Source code for langchain_community.document_loaders.chatgpt
import datetime
import json
from typing import List
from langchain_core.documents import Document
from langchain_community.document_loaders.base import BaseLoader
[docs]def concatenate_rows(message: dict, title: str) -> str:
"""将消息信息以可读格式组合在一起,准备好供使用。
参数:
message: 要连接的消息
title: 对话框的标题
返回:
连接后的消息
"""
if not message:
return ""
sender = message["author"]["role"] if message["author"] else "unknown"
text = message["content"]["parts"][0]
date = datetime.datetime.fromtimestamp(message["create_time"]).strftime(
"%Y-%m-%d %H:%M:%S"
)
return f"{title} - {sender} on {date}: {text}\n\n"
[docs]class ChatGPTLoader(BaseLoader):
"""从导出的`ChatGPT`数据加载对话。"""
[docs] def __init__(self, log_file: str, num_logs: int = -1):
"""初始化一个类对象。
参数:
log_file:日志文件的路径
num_logs:要加载的日志数量。如果为0,则加载所有日志。
"""
self.log_file = log_file
self.num_logs = num_logs
[docs] def load(self) -> List[Document]:
with open(self.log_file, encoding="utf8") as f:
data = json.load(f)[: self.num_logs] if self.num_logs else json.load(f)
documents = []
for d in data:
title = d["title"]
messages = d["mapping"]
text = "".join(
[
concatenate_rows(messages[key]["message"], title)
for idx, key in enumerate(messages)
if not (
idx == 0
and messages[key]["message"]["author"]["role"] == "system"
)
]
)
metadata = {"source": str(self.log_file)}
documents.append(Document(page_content=text, metadata=metadata))
return documents