run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-08-26 16:56:36 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

No result (NO_CONTENT_HERE) #51

New Issue
Closed
opened 2026-02-16 00:16:44 -05:00 by yindo · 3 comments
yindo commented 2026-02-16 00:16:44 -05:00
Owner
Copy Link
Copy Source

Originally created by @jwpark1985 on GitHub (Mar 18, 2024).

Hello,
After installing the new version (v0.10.40), I see many NO_CONTENT_HERE results with the pdf files, which have contents (about 10% of the documents returns NO_CONTENT_HERE).

The sampled documents are here: pdf1, pdf2, pdf3, pdf4.

This is the code that I used:

parser = LlamaParse(
    api_key=LLAMA_CLOUD_API_KEY,  # can also be set in your env as LLAMA_CLOUD_API_KEY
    result_type="markdown",  # "markdown" and "text" are available
    num_workers=1, # if multiple files passed, split in `num_workers` API calls
    verbose=True,
    language="en" 
)

documents = parser.load_data(inputs) # inputs are the documents stored in my local storage
Originally created by @jwpark1985 on GitHub (Mar 18, 2024). Hello, After installing the new version (v0.10.40), I see many NO_CONTENT_HERE results with the pdf files, which have contents (about 10% of the documents returns NO_CONTENT_HERE). The sampled documents are here: [pdf1](https://drive.google.com/file/d/1ExKtekqYHGLOVQ416CfFiPZrLJPd1KVa/view?usp=sharing), [pdf2](https://drive.google.com/file/d/1F1xxPLlGTo2Ci0e5_tAVSe2uMQ6hRvAp/view?usp=sharing), [pdf3](https://drive.google.com/file/d/10lfqnDt0Tb1Qg49VtchrB0H3UZuRac1g/view?usp=sharing), [pdf4](https://drive.google.com/file/d/1Q4PSUQ5qzY3kLLi5688RomP9kcQQUlXn/view?usp=sharing). This is the code that I used: ``` parser = LlamaParse( api_key=LLAMA_CLOUD_API_KEY, # can also be set in your env as LLAMA_CLOUD_API_KEY result_type="markdown", # "markdown" and "text" are available num_workers=1, # if multiple files passed, split in `num_workers` API calls verbose=True, language="en" ) documents = parser.load_data(inputs) # inputs are the documents stored in my local storage ```
yindo closed this issue 2026-02-16 00:16:44 -05:00
yindo commented 2026-02-16 00:16:44 -05:00
Author
Owner
Copy Link
Copy Source

@solanpaa commented on GitHub (Mar 22, 2024):

I see the same with long files, e.g., https://data.consilium.europa.eu/doc/document/ST-5662-2024-INIT/en/pdf.

But when I extract only a few pages and submit those, then it parses fine.

@solanpaa commented on GitHub (Mar 22, 2024): I see the same with long files, e.g., https://data.consilium.europa.eu/doc/document/ST-5662-2024-INIT/en/pdf. But when I extract only a few pages and submit those, then it parses fine.
yindo commented 2026-02-16 00:16:44 -05:00
Author
Owner
Copy Link
Copy Source

@jwpark1985 commented on GitHub (Mar 24, 2024):

Thanks, Solanpaa. It makes sense for you case. However, because the above pdf files are 1-page document, I can't reduce the amount of pages.

@jwpark1985 commented on GitHub (Mar 24, 2024): Thanks, Solanpaa. It makes sense for you case. However, because the above pdf files are 1-page document, I can't reduce the amount of pages.
yindo commented 2026-02-16 00:16:44 -05:00
Author
Owner
Copy Link
Copy Source

@jwpark1985 commented on GitHub (Mar 25, 2024):

From yesterday, I could get results correctly (maybe version update?). I close this issue.

@jwpark1985 commented on GitHub (Mar 25, 2024): From yesterday, I could get results correctly (maybe version update?). I close this issue.
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#51
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?