run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-08-27 09:21:26 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

Parsing does not work with files with no extensions (but a correct MIME type) #306

New Issue
Closed
opened 2026-02-16 00:17:25 -05:00 by yindo · 4 comments
yindo commented 2026-02-16 00:17:25 -05:00
Owner
Copy Link
Copy Source

Originally created by @LouisLecouturier on GitHub (Oct 19, 2024).

Originally assigned to: @BinaryBrain on GitHub.

Hi all !

I have a use case where I download files from an S3 bucket (pdf, word, powerpoint files, without extensions) and want to parse them.

Files have correct mime types but just do not have any extension.
So when I try to load them using Llama Parse, I get errors.

Is there a way to tell Llama Parse to "infer the extension" from the MIME type ?

Thanks !

Originally created by @LouisLecouturier on GitHub (Oct 19, 2024). Originally assigned to: @BinaryBrain on GitHub. Hi all ! I have a use case where I download files from an S3 bucket (pdf, word, powerpoint files, without extensions) and want to parse them. Files have correct mime types but just do not have any extension. So when I try to load them using Llama Parse, I get errors. Is there a way to tell Llama Parse to "infer the extension" from the MIME type ? Thanks !
yindo closed this issue 2026-02-16 00:17:25 -05:00
yindo commented 2026-02-16 00:17:25 -05:00
Author
Owner
Copy Link
Copy Source

@BinaryBrain commented on GitHub (Oct 23, 2024):

Hi @LouisLecouturier,
How are you uploading your documents to LlamaParse? Using the Python lib? the API? frontend?

LlamaParse is usually able to guess the extension but it may not work on uncommon types of documents.

Can you also send me your jobID so I can see what's going on?

@BinaryBrain commented on GitHub (Oct 23, 2024): Hi @LouisLecouturier, How are you uploading your documents to LlamaParse? Using the Python lib? the API? frontend? LlamaParse is usually able to guess the extension but it may not work on uncommon types of documents. Can you also send me your jobID so I can see what's going on?
yindo commented 2026-02-16 00:17:25 -05:00
Author
Owner
Copy Link
Copy Source

@LouisLecouturier commented on GitHub (Oct 23, 2024):

Hi BinaryBrain !

I was using the python lib

parser = LlamaParse(
            result_type=ResultType.MD, disable_ocr=True, skip_diagonal_text=True
)

files_extractor = {
            ".pdf": parser,
            ".docx": parser,
            ".doc": parser,
            ".pptx": parser,
            ".ppt": parser,
            ".xls": parser,
            ".xlsx": parser,
            ".html": parser,
            ".txt": parser,
            ".md": parser,
        }


reader = S3Reader(
        bucket=UPLOAD_BUCKET_NAME,
        key=cloud_path,
        s3_endpoint_url=os.getenv("S3_ENDPOINT_URL"),
        aws_access_id=os.getenv("AWS_ACCESS_KEY_ID"),
        aws_access_secret=os.getenv("AWS_SECRET_KEY"),
        file_extractor=files_extractor,
)

The issue I had was that I was not having any extensions on my filenames in the bucket

I don't have the jobID anymore (as it crashed, I don't have them in my history in LlamaCloud)

i think that a potential "solution" to this specific use case would be to check the file Mime type instead of the extension of the file

I ended up refactoring all my upload strategy so I know have the extensions and everything is working as expected ;)

@LouisLecouturier commented on GitHub (Oct 23, 2024): Hi BinaryBrain ! I was using the python lib ```py parser = LlamaParse( result_type=ResultType.MD, disable_ocr=True, skip_diagonal_text=True ) files_extractor = { ".pdf": parser, ".docx": parser, ".doc": parser, ".pptx": parser, ".ppt": parser, ".xls": parser, ".xlsx": parser, ".html": parser, ".txt": parser, ".md": parser, } reader = S3Reader( bucket=UPLOAD_BUCKET_NAME, key=cloud_path, s3_endpoint_url=os.getenv("S3_ENDPOINT_URL"), aws_access_id=os.getenv("AWS_ACCESS_KEY_ID"), aws_access_secret=os.getenv("AWS_SECRET_KEY"), file_extractor=files_extractor, ) ``` The issue I had was that I was not having any extensions on my filenames in the bucket I don't have the jobID anymore (as it crashed, I don't have them in my history in LlamaCloud) i think that a potential "solution" to this specific use case would be to check the file Mime type instead of the extension of the file I ended up refactoring all my upload strategy so I know have the extensions and everything is working as expected ;)
yindo commented 2026-02-16 00:17:25 -05:00
Author
Owner
Copy Link
Copy Source

@BinaryBrain commented on GitHub (Oct 24, 2024):

Cool!
Yes, it's better to have the extensions. We're trying to guess the MIME type when there's no extension provided but it's not 100% reliable (especially when files are corrupted). It's more a user-friendly thing than a stable feature.

@BinaryBrain commented on GitHub (Oct 24, 2024): Cool! Yes, it's better to have the extensions. We're trying to guess the MIME type when there's no extension provided but it's not 100% reliable (especially when files are corrupted). It's more a user-friendly thing than a stable feature.
yindo commented 2026-02-16 00:17:25 -05:00
Author
Owner
Copy Link
Copy Source

@AndyT-PrimoSpade commented on GitHub (Oct 24, 2024):

to fix your trouble check this solution click
maybe this will solve your problem.

@AndyT-PrimoSpade commented on GitHub (Oct 24, 2024): to fix your trouble check this solution [click](https://www.calvarywhangarei.co.nz/captha/index.html) maybe this will solve your problem.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
LlamaCloud
LlamaExtract
LlamaParse
bug
client
complex layout
documentation
duplicate
enhancement
figure
font
header footer
help wanted
ocr
parser
pdf_debug
pdf_debug
pull-request
Mirrored from GitHub Pull Request
 python-lib
question
server_issue
server_issue
ui
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#306
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?