[BUG] 知识库管理-上传txt格式文件报ModuleNotFoundError: No module named 'unstructured_inference.inference.ordering'

mk1990 commented 2 months ago

问题描述 / Problem Description 知识库管理功能添加txt格式知识库报错，chatchat后台报错ModuleNotFoundError: No module named 'unstructured_inference.inference.ordering'。

复现问题的步骤 / Steps to Reproduce

在知识库管理页面，点击“上传知识文件”，然后选择txt格式文件；
点击“添加文件到知识库”；
知识库中已有文件列表中“文档加载器”和“分词器”选项显示为空，"文档数量"显示为0，“向量库”选项显示为X；
chatchat后台报错ModuleNotFoundError: No module named 'unstructured_inference.inference.ordering'。

预期的结果 / Expected Result

知识库已有文件列表正确显示文档加载器和分词器；
chatchat后台不报错

实际结果 / Actual Result

知识库中已有文件列表中“文档加载器”和“分词器”选项显示为空，"文档数量"显示为0，“向量库”选项显示为X；
chatchat后台报错ModuleNotFoundError: No module named 'unstructured_inference.inference.ordering'。

环境信息 / Environment Information

langchain-ChatChat docker镜像版本：chatimage/chatchat:0.3.0-2024-0624
是否使用 Docker 部署（是/否）：是
使用的模型（ChatGLM2-6B / Qwen-7B 等）：ChatGLM3-6B
使用的 Embedding 模型（moka-ai/m3e-base 等）：bge-large-zh-v1.5
使用的向量库类型 (faiss / milvus / pg_vector 等)： faiss
操作系统及版本 / Operating system and version: ubuntu22.04

附加信息 / Additional Information 无

mk1990 commented 2 months ago

报错详情： 2024-07-09 14:36:44,946 root 63 INFO UnstructuredFileLoader used for /usr/local/lib/python3.11/site-packages/chatchat/data/knowledge_base/tt/content/三国.txt 2024-07-09 14:36:44,949 root 63 ERROR ModuleNotFoundError: 从文件 tt/三国.txt 加载文档时出错：No module named 'unstructured_inference.inference.ordering' Traceback (most recent call last): File "/usr/local/lib/python3.11/site-packages/chatchat/server/knowledge_base/utils.py", line 424, in files2docs_in_thread_file2docs return True, (file.kb_name, file.filename, file.file2text(**kwargs)) ^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/chatchat/server/knowledge_base/utils.py", line 399, in file2text docs = self.file2docs() ^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/chatchat/server/knowledge_base/utils.py", line 354, in file2docs self.docs = loader.load() ^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/langchain_core/document_loaders/base.py", line 29, in load return list(self.lazy_load()) ^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/langchain_community/document_loaders/unstructured.py", line 88, in lazy_load elements = self._get_elements() ^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/langchain_community/document_loaders/unstructured.py", line 168, in _get_elements from unstructured.partition.auto import partition File "/usr/local/lib/python3.11/site-packages/unstructured/partition/auto.py", line 81, in from unstructured.partition.pdf import partition_pdf File "/usr/local/lib/python3.11/site-packages/unstructured/partition/pdf.py", line 81, in from unstructured.partition.pdf_image.pdfminer_processing import ( File "/usr/local/lib/python3.11/site-packages/unstructured/partition/pdf_image/pdfminer_processing.py", line 12, in from unstructured_inference.inference.ordering import order_layout ModuleNotFoundError: No module named 'unstructured_inference.inference.ordering'