LlamaIndex

Log inLog into community

Find answers from the community

Updated 4 months ago

I think there is a bug in

I think there is a bug in

At a glance

The community member is having trouble parsing/indexing .ppt files using SimpleDirectoryReader, while .pptx files are working fine. The community members suggest trying llama-parse, which was recently updated to handle more file types, including .ppt. However, there are some issues with the llama-parse API, and the community members discuss potential solutions, including a pull request to extend the file type support. There is no explicitly marked answer, but the community members are collaborating to find a solution.

Useful resources

·

I think there is a bug in SimpleDirectoryReader or the Documentation needs to be updated.
I am unable to parse/index .ppt but the .pptx's are just fine.

Anyone can help/confirm if what needs to be done.
Thanks,

L

s

p

24 comments

Is there an error? Its just using the PptxReader

Attachment

Its using from pptx import Presentation to parse, maybe that package is having trouble reading your file

I might recommend trying llama-parse if you haven't already

It is using pptx reader and just parses .pptx and not .ppt.

Inside pptx module

Attachment

@Logan M llama-parse is limited to pdfs as of now; at least the web version. That I interacted with.
Any Suggestions?

PptxReader parses/processes only .pptx file type not .ppt

llama-parse was recently updated to handle 50+ file types

the .ppt extension is mapped to the PptxReader -- I guess this is an error?

yes

Is this update in API or web_application?

I think just the API -- pip install -U llama-parse

https://github.com/run-llama/llama_parse/blob/main/examples/other_files/demo_ppt_basic.ipynb

awesome; will check it out - thanks

Hey; tried the API here's the error:

Attachment

awe man, I thought it was more robust than that. Maybe it wasn't fully rolled out...

@pld just curious, we have plans to expand that list right?

is there any branch that has that piece that handles .ppt?

yes, we should extend it.

https://github.com/run-llama/llama_parse/pull/110 👀

@Logan M Are there any plans to bring this extended support to llama-index readers?

No plans currently, but I welcome a PR to add any new reader

And how is llama-parse handling the extended format(s)?
is there any code I can look into?

Currently its being provided as a SASS service, with options for on-prem VPC deployments in the future. (So no source code for now)

Add a reply

Sign up and join the conversation on Discord