Find answers from the community

Updated 2 years ago

Does anyone know of a way to

Does anyone know of a way to automatically pass in a filename as doc_id when using SimpleDirectoryReader? Kapa AI believes there is a way to use use_filename_as_id=True but it is not working E.g.

Plain Text

# Load documents with filenames as document IDs
documents = SimpleDirectoryReader('path/to/your/data', use_filename_as_id=True).load_data()

5 comments

LLogan M

No way currently.

You could use the filename_fn to set the extra_info field of each document, and then iterate over the documents and manually change each doc_id to match it's filename

Although thats pretty annoying. I can make a PR to do this more automatically

eelmegatan26

@Logan M As always, thank you.

LLogan M

https://github.com/jerryjliu/llama_index/pull/6055 PR opened 🙂

eelmegatan26

Awesome

LLogan M

Should be available in v0.6.21! 🙂

Add a reply