"The model text-davinci-003 has been deprecated"

[ArnaudHureaux]

I just followed the tutorial with a normal PDF

Below the full error :

PS C:\Users\hurea\1MyCode\PERSO\book_summarizer\gpt-summarizer> python summarize.py bap_bam.pdf
Found 1 sections.
Token indices sequence length is longer than the specified maximum sequence length for this model (103563 > 1024). Running this sequence through the model will result in indexing errors
Text extracted from bap_bam.pdf and written to bap_bam.full.txt
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\hurea\1MyCode\PERSO\book_summarizer\gpt-summarizer\summarize.py", line 268, in generate_summary
completions = openai.Completion.create(
^^^^^^^^^^^^^^^^^^^^^^^^^
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\hurea\1MyCode\PERSO\book_summarizer\gpt-summarizer\summarize.py", line 268, in generate_summary
completions = openai.Completion.create(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\hurea\AppData\Local\Programs\Python\Python311\Lib\site-packages\openai\api_resources\completion.py", line 25, in create
return super().create(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\hurea\AppData\Local\Programs\Python\Python311\Lib\site-packages\openai\api_resources\abstract\engine_api_resource.py", line 153, in create
response, _, api_key = requestor.request(
^^^^^^^^^^^^^^^^^^
File "C:\Users\hurea\AppData\Local\Programs\Python\Python311\Lib\site-packages\openai\api_requestor.py", line 226, in request
resp, got_stream = self._interpret_response(result, stream)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\hurea\AppData\Local\Programs\Python\Python311\Lib\site-packages\openai\api_requestor.py", line 619, in _interpret_response
self._interpret_response_line(
File "C:\Users\hurea\AppData\Local\Programs\Python\Python311\Lib\site-packages\openai\api_requestor.py", line 682, in _interpret_response_line
raise self.handle_error_response(
openai.error.InvalidRequestError: The model text-davinci-003 has been deprecated, learn more here: https://platform.openai.com/docs/deprecations

[scottleibrand]

Yeah, the approach taken in this repo isn't needed any more. You can simply paste your entire text into GPT-4-Turbo with a "please summarize this" prompt of whatever level of detail you want. Claude 2 is also good for long-context tasks like that.