Open sfc-gh-dong opened 6 months ago
Ignore my earlier comment, upon reading your post better, I realize you know it is an issue with the hidden directory.
documents = SimpleDirectoryReader(
input_dir=data_dir,
exclude_hidden=False,
).load_data()
Describe the bug Llama Index unable to read files in hidden directory .content, so it failed with this error while running python build_index.py Building vector index... Traceback (most recent call last): File "/Users/dong/sfguide-blog-ai-assistant/build_index.py", line 43, in
main()
File "/Users/dong/sfguide-blog-ai-assistant/build_index.py", line 39, in main
build_index(data_dir, knowledge_base_dir)
File "/Users/dong/sfguide-blog-ai-assistant/build_index.py", line 23, in build_index
documents = SimpleDirectoryReader(input_dir=d_dir, required_exts=required_exts, recursive=True).load_data()
File "/Users/dong/sfguide-blog-ai-assistant/ai-assistant/lib/python3.9/site-packages/llama_index/readers/file/base.py", line 143, in init
self.input_files = self._add_files(self.input_dir)
File "/Users/dong/sfguide-blog-ai-assistant/ai-assistant/lib/python3.9/site-packages/llama_index/readers/file/base.py", line 204, in _add_files
raise ValueError(f"No files found in {input_dir}.")
ValueError: No files found in /Users/dong/sfguide-blog-ai-assistant/.content/blogs.
Simply copying the files in .content/blog to another (non hidden) directory works.
URL of where you see the bug https://quickstarts.snowflake.com/guide/build_rag_based_blog_ai_assistant_using_streamlit_openai_and_llamaindex/index.html?index=..%2F..index#3
To Reproduce Steps to reproduce the behavior:
Expected behavior A clear and concise description of what you expected to happen.
Screenshots If applicable, add screenshots to help explain your problem.
Desktop (please complete the following information):
Smartphone (please complete the following information):
Additional context Add any other context about the problem here.