镜像自地址
https://github.com/binary-husky/gpt_academic.git
已同步 2025-12-06 06:26:47 +00:00
7f0ffa58f0
* first_version * rag document support * RAG interactive prompts added, issues resolved * Resolve conflicts * Resolve conflicts * Resolve conflicts * more file format support * move import * Resolve LlamaIndexRagWorker bug * new resolve * Address import LlamaIndexRagWorker problem * change import order --------- Co-authored-by: binary-husky <qingxu.fu@outlook.com>
23 行
730 B
Python
23 行
730 B
Python
import os
|
|
from llama_index.core import SimpleDirectoryReader
|
|
|
|
supports_format = ['.csv', '.docx', '.epub', '.ipynb', '.mbox', '.md', '.pdf', '.txt', '.ppt',
|
|
'.pptm', '.pptx']
|
|
|
|
|
|
# 修改后的 extract_text 函数，结合 SimpleDirectoryReader 和自定义解析逻辑
|
|
def extract_text(file_path):
|
|
_, ext = os.path.splitext(file_path.lower())
|
|
|
|
# 使用 SimpleDirectoryReader 处理它支持的文件格式
|
|
if ext in supports_format:
|
|
try:
|
|
reader = SimpleDirectoryReader(input_files=[file_path])
|
|
documents = reader.load_data()
|
|
if len(documents) > 0:
|
|
return documents[0].text
|
|
except Exception as e:
|
|
pass
|
|
|
|
return None
|