DocumentStatus (document.py)

Tracks and manages document processing lifecycle states (draft, review, approved, archived).

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
@Time    : 2023/6/8 14:03
@Author  : alexanderwu
@File    : document.py
@Desc    : Classes and Operations Related to Files in the File System.
"""
from enum import Enum
from pathlib import Path
from typing import Optional, Union

import pandas as pd
from llama_index.core import Document, SimpleDirectoryReader
from llama_index.core.node_parser import SimpleNodeParser
from llama_index.readers.file import PDFReader
from pydantic import BaseModel, ConfigDict, Field
from tqdm import tqdm

from metagpt.logs import logger
from metagpt.repo_parser import RepoParser


def validate_cols(content_col: str, df: pd.DataFrame):
    if content_col not in df.columns:
        raise ValueError("Content column not found in DataFrame.")


def read_data(data_pat

... (truncated -- full source via MCP)