run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-08-27 01:15:06 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

Cannot process same PDF file twice #199

New Issue
Closed
opened 2026-02-16 00:17:07 -05:00 by yindo · 8 comments
yindo commented 2026-02-16 00:17:07 -05:00
Owner
Copy Link
Copy Source

Originally created by @jaikb on GitHub (Jul 22, 2024).

We're facing a big issue right now where we can't process the same PDF twice. The first time I try to parse it, it works fine then the second time I'm getting this error:

[{'detail': 'Result not found. Check job status to see if it has completed.', 'job_id': '66cf8baf-923d-43bb-8d7f-d3f95a89a79c', 'file_path': 'pdf-document.pdf'}]
Originally created by @jaikb on GitHub (Jul 22, 2024). We're facing a big issue right now where we can't process the same PDF twice. The first time I try to parse it, it works fine then the second time I'm getting this error: ``` [{'detail': 'Result not found. Check job status to see if it has completed.', 'job_id': '66cf8baf-923d-43bb-8d7f-d3f95a89a79c', 'file_path': 'pdf-document.pdf'}] ```
yindo added the bug label 2026-02-16 00:17:07 -05:00
yindo closed this issue 2026-02-16 00:17:07 -05:00
yindo commented 2026-02-16 00:17:07 -05:00
Author
Owner
Copy Link
Copy Source

@tkcoding commented on GitHub (Jul 23, 2024):

solution and explanation is here : https://github.com/run-llama/llama_parse/issues/278

@tkcoding commented on GitHub (Jul 23, 2024): solution and explanation is here : https://github.com/run-llama/llama_parse/issues/278
yindo commented 2026-02-16 00:17:07 -05:00
Author
Owner
Copy Link
Copy Source

@jaikb commented on GitHub (Jul 23, 2024):

@tkcoding I saw that solution and adding the invalidate_cache = True to my parser object did not fix the code. Reference below the code I am using:

parser_gpt4o = LlamaParse(
        api_key=environ.get("LLAMA_CLOUD_API_KEY"),
        result_type="markdown",
        verbose=True,
        language="en",
        gpt4o_mode=True,
        gpt4o_api_key=environ.get("LLAMAPARSE_OPENAI_API_KEY"),
        ignore_errors=False,
        invalidate_cache=True,
    )

document = parser_gpt4o.get_json_result(file_path)
@jaikb commented on GitHub (Jul 23, 2024): @tkcoding I saw that solution and adding the `invalidate_cache = True` to my parser object did not fix the code. Reference below the code I am using: ``` parser_gpt4o = LlamaParse( api_key=environ.get("LLAMA_CLOUD_API_KEY"), result_type="markdown", verbose=True, language="en", gpt4o_mode=True, gpt4o_api_key=environ.get("LLAMAPARSE_OPENAI_API_KEY"), ignore_errors=False, invalidate_cache=True, ) document = parser_gpt4o.get_json_result(file_path) ```
yindo commented 2026-02-16 00:17:07 -05:00
Author
Owner
Copy Link
Copy Source

@adreichert commented on GitHub (Jul 23, 2024):

I'm able to cause the issue. Below is the full code. While the jobs are marked as SUCCESS, I'm unable to download the results.

Parse

Python Code

from os import environ
import sys

file_path = sys.argv[1]
parser_gpt4o = LlamaParse(
    api_key=environ["LLAMA_CLOUD_API_KEY"],
    verbose=True,
    gpt4o_mode=True,
    gpt4o_api_key=environ["LLAMAPARSE_OPENAI_API_KEY"],
    ignore_errors=False,
    invalidate_cache=True,
    do_not_cache=True,
)
try:
    print("Markdown")
    print(parser_gpt4o.load_data(file_path))
except KeyError as e:
    print("Error: ", e)
print("JSON")
print(parser_gpt4o.get_json_result(file_path))

Shell Output

Markdown
Started parsing the file under job_id a45e687b-7901-43ec-ab79-de9407e977c8
Error while parsing the file '/Users/areichert/Desktop/pronto-forms.pdf': 'text'
Error:  'text'
JSON
Started parsing the file under job_id 78df4a75-bfaf-47c7-a347-05f6db0a8ec5
[{'detail': 'Result not found. Check job status to see if it has completed.', 'job_id': '78df4a75-bfaf-47c7-a347-05f6db0a8ec5', 'file_path': '/Users/areichert/Desktop/pronto-forms.pdf'}]

Job Marked As Success But Cannot Download.

curl -X 'GET' \
  'https://api.cloud.llamaindex.ai/api/parsing/job/78df4a75-bfaf-47c7-a347-05f6db0a8ec5' \
  -H 'accept: application/json' \
  -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY"
echo
curl -X 'GET' \
  'https://api.cloud.llamaindex.ai/api/parsing/job/78df4a75-bfaf-47c7-a347-05f6db0a8ec5/result/markdown' \
  -H 'accept: application/json' \
  -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY"

{"id":"78df4a75-bfaf-47c7-a347-05f6db0a8ec5","status":"SUCCESS"}
{"detail":"Result not found. Check job status to see if it has completed."}%
@adreichert commented on GitHub (Jul 23, 2024): I'm able to cause the issue. Below is the full code. While the jobs are marked as `SUCCESS`, I'm unable to download the results. # Parse ## Python Code ```from llama_parse import LlamaParse from os import environ import sys file_path = sys.argv[1] parser_gpt4o = LlamaParse( api_key=environ["LLAMA_CLOUD_API_KEY"], verbose=True, gpt4o_mode=True, gpt4o_api_key=environ["LLAMAPARSE_OPENAI_API_KEY"], ignore_errors=False, invalidate_cache=True, do_not_cache=True, ) try: print("Markdown") print(parser_gpt4o.load_data(file_path)) except KeyError as e: print("Error: ", e) print("JSON") print(parser_gpt4o.get_json_result(file_path)) ``` ## Shell Output ``` Markdown Started parsing the file under job_id a45e687b-7901-43ec-ab79-de9407e977c8 Error while parsing the file '/Users/areichert/Desktop/pronto-forms.pdf': 'text' Error: 'text' JSON Started parsing the file under job_id 78df4a75-bfaf-47c7-a347-05f6db0a8ec5 [{'detail': 'Result not found. Check job status to see if it has completed.', 'job_id': '78df4a75-bfaf-47c7-a347-05f6db0a8ec5', 'file_path': '/Users/areichert/Desktop/pronto-forms.pdf'}] ``` # Job Marked As Success But Cannot Download. ``` curl -X 'GET' \ 'https://api.cloud.llamaindex.ai/api/parsing/job/78df4a75-bfaf-47c7-a347-05f6db0a8ec5' \ -H 'accept: application/json' \ -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" echo curl -X 'GET' \ 'https://api.cloud.llamaindex.ai/api/parsing/job/78df4a75-bfaf-47c7-a347-05f6db0a8ec5/result/markdown' \ -H 'accept: application/json' \ -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" ``` ``` {"id":"78df4a75-bfaf-47c7-a347-05f6db0a8ec5","status":"SUCCESS"} {"detail":"Result not found. Check job status to see if it has completed."}% ```
yindo commented 2026-02-16 00:17:07 -05:00
Author
Owner
Copy Link
Copy Source

@emorling commented on GitHub (Jul 24, 2024):

I can confirm this, I have same issue.

@emorling commented on GitHub (Jul 24, 2024): I can confirm this, I have same issue.
yindo commented 2026-02-16 00:17:07 -05:00
Author
Owner
Copy Link
Copy Source

@tkcoding commented on GitHub (Jul 24, 2024):

@tkcoding I saw that solution and adding the invalidate_cache = True to my parser object did not fix the code. Reference below the code I am using:

parser_gpt4o = LlamaParse(
        api_key=environ.get("LLAMA_CLOUD_API_KEY"),
        result_type="markdown",
        verbose=True,
        language="en",
        gpt4o_mode=True,
        gpt4o_api_key=environ.get("LLAMAPARSE_OPENAI_API_KEY"),
        ignore_errors=False,
        invalidate_cache=True,
    )

document = parser_gpt4o.get_json_result(file_path)

I couldn't replicate this issue by using the same setup you have there, I tried to run the document three times and it went through OK.

Did you try other document ?

@tkcoding commented on GitHub (Jul 24, 2024): > @tkcoding I saw that solution and adding the `invalidate_cache = True` to my parser object did not fix the code. Reference below the code I am using: > > ``` > parser_gpt4o = LlamaParse( > api_key=environ.get("LLAMA_CLOUD_API_KEY"), > result_type="markdown", > verbose=True, > language="en", > gpt4o_mode=True, > gpt4o_api_key=environ.get("LLAMAPARSE_OPENAI_API_KEY"), > ignore_errors=False, > invalidate_cache=True, > ) > > document = parser_gpt4o.get_json_result(file_path) > ``` I couldn't replicate this issue by using the same setup you have there, I tried to run the document three times and it went through OK. Did you try other document ?
yindo commented 2026-02-16 00:17:07 -05:00
Author
Owner
Copy Link
Copy Source

@emorling commented on GitHub (Jul 24, 2024):

Did you try other document ?

I found it reproducable with any .txt document

@emorling commented on GitHub (Jul 24, 2024): > Did you try other document ? I found it reproducable with any .txt document
yindo commented 2026-02-16 00:17:07 -05:00
Author
Owner
Copy Link
Copy Source

@tkcoding commented on GitHub (Jul 24, 2024):

@jaikb @emorling @adreichert
I think I figured out what happened .
TL;DR
Basically it failed at sending the document to gpt4o which is kind of "deprecated" by now.

The old 'gpt4o_mode=True' doesnt work as expected anymore. Dev team have introduced new args which should be working for your test case .

I tested out on a .txt and it threw connection exception when processed second time, after I change to vendor_multimodel args as below then it's working now.

LlamaParse(
            verbose=True,
            ignore_errors=False,
            invalidate_cache=True,
            do_not_cache=True,
            vendor_multimodal_api_key=environ["LLAMAPARSE_OPENAI_API_KEY"],
            vendor_multimodal_model_name = 'gpt4o_mini',
            use_vendor_multimodal_model=True
        )
@tkcoding commented on GitHub (Jul 24, 2024): @jaikb @emorling @adreichert I think I figured out what happened . TL;DR Basically it failed at sending the document to gpt4o which is kind of "deprecated" by now. The old 'gpt4o_mode=True' doesnt work as expected anymore. Dev team have introduced new args which should be working for your test case . I tested out on a .txt and it threw connection exception when processed second time, after I change to vendor_multimodel args as below then it's working now. ``` LlamaParse( verbose=True, ignore_errors=False, invalidate_cache=True, do_not_cache=True, vendor_multimodal_api_key=environ["LLAMAPARSE_OPENAI_API_KEY"], vendor_multimodal_model_name = 'gpt4o_mini', use_vendor_multimodal_model=True )
yindo commented 2026-02-16 00:17:07 -05:00
Author
Owner
Copy Link
Copy Source

@hexapode commented on GitHub (Jul 26, 2024):

This is now solved in production without the need to invalid_cache=True

@hexapode commented on GitHub (Jul 26, 2024): This is now solved in production without the need to `invalid_cache=True`
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 bug
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#199
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?