인프런 커뮤니티 질문&답변

안녕하십니까! 강의 잘 듣고 있습니다.
pyzerox를 gpt-4o-mini 모델을 사용하하는 중
아래와 같은 에러가 발생을 합니다.


```

ModuleNotFoundError Traceback (most recent call last) Cell In[13], line 1----> 1 from pyzerox import zerox 2 import asyncio4 ### Model Setup (Use only Vision Models) Refer: https://docs.litellm.ai/docs/providers ### 56 ## placeholder for additional model kwargs which might be required for some models File ~/desktop/langgraph/.venv/lib/python3.12/site-packages/pyzerox/__init__.py:1----> 1 from .core import zerox 2 from .constants.prompts import Prompts 4 DEFAULT_SYSTEM_PROMPT = Prompts.DEFAULT_SYSTEM_PROMPT File ~/desktop/langgraph/.venv/lib/python3.12/site-packages/pyzerox/core/__init__.py:1----> 1 from .zerox import zerox 3all = [ 4"zerox", 5 ] File ~/desktop/langgraph/.venv/lib/python3.12/site-packages/pyzerox/core/zerox.py:1310 from ..constants import PDFConversionDefaultOptions 12 # Package Imports ---> 13 from ..processor import ( 14 convert_pdf_to_images,

...

12 ) 13 from litellm.caching import InMemoryCache 14 from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj ModuleNotFoundError: No module named 'enterprise'
```

!uv pip install py-zerox

from pyzerox import zerox
import asyncio

### Model Setup (Use only Vision Models) Refer: https://docs.litellm.ai/docs/providers ###

## placeholder for additional model kwargs which might be required for some models
kwargs = {}

## system prompt to use for the vision model
custom_system_prompt = None

# to override
# custom_system_prompt = "For the below PDF page, do something..something..." ## example

###################### Example for OpenAI ######################
model = "gpt-4o-mini" ## openai model

# Define main async entrypoint
async def main():
    file_path = "./income_tax.pdf" ## local filepath and file URL supported

    ## process only some pages or all
    select_pages = None ## None for all, but could be int or list(int) page numbers (1 indexed)

    output_dir = "./documents" ## directory to save the consolidated markdown file
    result = await zerox(file_path=file_path, model=model, output_dir=output_dir,
                        custom_system_prompt=custom_system_prompt,select_pages=select_pages, **kwargs)
    return result


# run the main function:
result = asyncio.run(main())

# print markdown result
print(result)

코드는 위와 같습니다.

pyzerox 가 수업 중 litellm 을 사용한다고 하셨는데 (py-zerox 설치시 1.67.4 버전으로 같이 설치됨)
Enterprise용 littellm을 사용하면서 생긴 문제인 것 같은데요

기존 설치된 littellm 을 upgrade 하니 다른 오류인

ModelAccessError: Your provided model can't be accessed. Please make sure you have access to the model and also required environment variables are setup correctly including valid api key(s). Refer: https://docs.litellm.ai/docs/providers (Extra Info: {'model': 'gpt-4o-mini'})

이런 오류가 발생합니다.
현재 사용중인 OPENAI_API_KEY 를 이용해 llm.invoke 시 응답이 잘 오는 걸 봐서는 해당 모델을 사용하는데 문제는 없는 것으로 보입니다.

혹시 지금까지 어떤 문제점이 있는지 알 수 있을지요?