🐛 Error in worker causing IndexError

[G4st3r21]

📜 Description

I encountered an issue while using the upload endpoint of the DocsGPT API. After successfully uploading a file and receiving the response with the status "ok" and a task ID, I observed an error in the worker logs. The error message states the following:

[2023-11-29 15:31:49,384: WARNING/ForkPoolWorker-1] inputs/5203382281/file_84.pdf
[2023-11-29 15:31:49,424: WARNING/ForkPoolWorker-1] <Response [200]>
[2023-11-29 15:31:49,431: WARNING/ForkPoolWorker-1] Grouping small documents
[2023-11-29 15:31:49,432: WARNING/ForkPoolWorker-1] Separating large documents
[2023-11-29 15:31:49,436: ERROR/ForkPoolWorker-1] Task application.api.user.tasks.ingest[eade116a-470f-4e9f-a69f-4c5f084151f6] raised unexpected: IndexError('list index out of range')
Traceback (most recent call last):
File "/usr/local/lib/python3.10/site-packages/celery/app/trace.py", line 451, in trace_task
R = retval = fun(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/celery/app/trace.py", line 734, in protected_call
return self.run(*args, **kwargs)
File "/app/application/api/user/tasks.py", line 6, in ingest
resp = ingest_worker(self, directory, formats, name_job, filename, user)
File "/app/application/worker.py", line 94, in ingest_worker
call_openai_api(docs, full_path, self)
File "/app/application/parser/open_ai_func.py", line 38, in call_openai_api
docs_init = [docs[0]]
IndexError: list index out of range

It seems that the error occurred when the worker was trying to process the file file_84.pdf. The IndexError indicates that the list index was out of range in the call_openai_api function.

Could you please investigate this issue and provide a solution? Let me know if you need any additional information. Thank you!

👟 Reproduction steps

1. Send a file using the upload endpoint.
2. Receive an "ok" response with a task_id.

👍 Expected behavior

I expected the file to be processed without any errors and to receive a successful response.

👎 Actual Behavior with Screenshots

The worker encountered an IndexError: list index out of range while processing the file.

💻 Operating system

Linux

What browsers are you seeing the problem on?

No response

🤖 What development environment are you experiencing this bug on?

Docker

🔒 Did you set the correct environment variables in the right path? List the environment variable names (not values please!)

No response

📃 Provide any additional context for the Bug.

No response

📖 Relevant log output

No response

👀 Have you spent some time to check if this bug has been raised before?

• I checked and didn't find similar issue

🔗 Are you willing to submit PR?

None

🧑‍⚖️ Code of Conduct

• I agree to follow this project's Code of Conduct