talkingwallace / chatgpt-paper-reader Goto Github PK

请问下，我在python运行完pdf之后，在python console”输入“session. question('Authors of this paper?')”
但是得到的回答是
Traceback (most recent call last):
File "", line 1, in
NameError: name 'session' is not defined
请问这种情况，应该如何解决

After inputting the API KEY and proxy address, it still faces some errors when running the program. (saddd)
Must I use a USA proxy to run the program if I am in China?🤔

Got this error:
openai.error.InvalidRequestError: This model's maximum context length is 4097 tokens. However, your messages resulted in 7328 tokens. Please reduce the length of the messages.

Is it possible to break the paper into multiple pieces then query one paper piece at a time to avoid this issue?

Hi,

Thank you for sharing this app. I just want to ask if you can provide your requirement.txt in README.md, so we don't need to install them one by one when running it.

openai.error.InvalidRequestError: This model's maximum context length is 4097 tokens. However, your messages resulted in 4425 tokens. Please reduce the length of the messages.

PyPDF2.errors.EmptyFileError: Cannot read an empty file.

Right after I upload the pdf, and click Start Analyze.
The feedback that I got at "Ask question about your PDF" is always: I'm sorry, I still don't have enough information to provide you with a specific answer. Can you please provide me with the title of the paper or any additional information so I can assist you better?

Its support just one pdf or multiple? thanks you

I upload the alexnet.pdf and click start analyse ,it return an Error.
And I check the IDE it show this.

Beep....Beep....Beep.... Parsing
Traceback (most recent call last):
File "C:\ProgramData\Anaconda3\lib\site-packages\gradio\routes.py", line 292, in run_predict
output = await app.blocks.process_api(
File "C:\ProgramData\Anaconda3\lib\site-packages\gradio\blocks.py", line 1007, in process_api
result = await self.call_function(fn_index, inputs, iterator, request)
File "C:\ProgramData\Anaconda3\lib\site-packages\gradio\blocks.py", line 848, in call_function
prediction = await anyio.to_thread.run_sync(
File "C:\ProgramData\Anaconda3\lib\site-packages\anyio\to_thread.py", line 28, in run_sync
return await get_asynclib().run_sync_in_worker_thread(func, *args, cancellable=cancellable,
File "C:\ProgramData\Anaconda3\lib\site-packages\anyio_backends_asyncio.py", line 818, in run_sync_in_worker_thread
return await future
File "C:\ProgramData\Anaconda3\lib\site-packages\anyio_backends_asyncio.py", line 754, in run
result = context.run(func, *args)
File "F:\yjj\ChatGPT-Paper-Reader\gui.py", line 15, in analyse
return self.session.summarize(self.paper)
File "F:\yjj\ChatGPT-Paper-Reader\gpt_reader\pdf_reader.py", line 30, in summarize
paper = self.bot.read_paper(paper)
File "F:\yjj\ChatGPT-Paper-Reader\gpt_reader\bot\openai.py", line 139, in read_paper
titles = self.parse_pdf_title(paper.pdf_path)
File "F:\yjj\ChatGPT-Paper-Reader\gpt_reader\bot\openai.py", line 72, in parse_pdf_title
for page_layout in extract_pages(pdf_path):
File "C:\ProgramData\Anaconda3\lib\site-packages\pdfminer\high_level.py", line 203, in extract_pages
with open_filename(pdf_file, "rb") as fp:
File "C:\ProgramData\Anaconda3\lib\site-packages\pdfminer\utils.py", line 59, in init
raise TypeError("Unsupported input type: %s" % type(filename))
TypeError: Unsupported input type: <class 'tempfile._TemporaryFileWrapper'>

I copy it to the GPT4,it answered me :

The error is caused by the pdfminer.high_level.extract_pages() function expecting a file path (a string) or a file-like object as its argument, but it appears to be receiving a tempfile._TemporaryFileWrapper object instead.

To fix this issue, you should pass a proper file path or a file-like object to the extract_pages() function. You can make the following changes in your gpt_reader\bot\openai.py file:

1.If you are using a temporary file, make sure to call the name attribute to get the file path before passing it to the extract_pages() function:

temp_file_path = tempfile_object.name
for page_layout in extract_pages(temp_file_path):

2.Alternatively, if you want to pass a file-like object, you can open the temporary file in binary mode and pass it to the extract_pages() function:

with open(tempfile_object.name, "rb") as file_object:
for page_layout in extract_pages(file_object):

By ensuring that you are passing the correct file path or file-like object to the extract_pages() function, you should be able to avoid the TypeError raised in your script.

Traceback (most recent call last):
File "D:\Anaconda3\lib\site-packages\gradio\routes.py", line 393, in run_predict
output = await app.get_blocks().process_api(
File "D:\Anaconda3\lib\site-packages\gradio\blocks.py", line 1069, in process_api
result = await self.call_function(
File "D:\Anaconda3\lib\site-packages\gradio\blocks.py", line 878, in call_function
prediction = await anyio.to_thread.run_sync(
File "D:\Anaconda3\lib\site-packages\anyio\to_thread.py", line 28, in run_sync
return await get_asynclib().run_sync_in_worker_thread(func, *args, cancellable=cancellable, File "D:\Anaconda3\lib\site-packages\anyio_backends_asyncio.py", line 818, in run_sync_in_worker_thread
return await future
File "D:\Anaconda3\lib\site-packages\anyio_backends_asyncio.py", line 754, in run
result = context.run(func, *args)
File "c:\Users\Administrator\Desktop\Paper-Reader\gui.py", line 14, in analyse
return self.session.read_pdf_and_summarize(pdf_file)
File "c:\Users\Administrator\Desktop\Paper-Reader\gpt_reader\pdf_reader.py", line 100, in read_pdf_and_summarize
pdf_reader = PdfReader(pdf_path)
File "D:\Anaconda3\lib\site-packages\PyPDF2_reader.py", line 319, in init
self.read(stream)
File "D:\Anaconda3\lib\site-packages\PyPDF2_reader.py", line 1414, in read
self._basic_validation(stream)
File "D:\Anaconda3\lib\site-packages\PyPDF2_reader.py", line 1455, in _basic_validation
raise EmptyFileError("Cannot read an empty file")

Despite placing the key correctly, when I click start analyse I get the message "error". it even doesn't work with the template PDF.

一直是上传状态 ，为什么不能上传，无报错日志

When I ran the GUI version of this Python code and selected alexnet.pdf as an example to analyze, I got the following error:

File "/opt/homebrew/lib/python3.10/site-packages/pdfminer/utils.py", line 59, in init raise TypeError("Unsupported input type: %s" % type(filename))
TypeError: Unsupported input type: <class 'tempfile._TemporaryFileWrapper'>"

My Gradio version is 3.15.0.

raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

由于msg 长度永远为2 zip(msg[1::2], msg[2::2])，导致drop_conversation 总对于过长的信息只是保留，并没有截断。

openai.error.RateLimitError: Rate limit reached for default-gpt-3.5-turbo in organization org-PanV93eoQzPe3QALIzkJ8Iof on requests per min. Limit: 3 / min. Please try again in 20s.

请问这是因为访问频率过快吗？怎么解决这个问题呢？

Python version:
Python 3.9.7

pdfminer version:
pdfminer==20191125 from the repo's requirements.txt

Problem:

After installing all dependencies and running python example.py, there are functions in pdfminer that don't exist in the installed library.

Error Message:

ImportError: cannot import name 'HOCRConverter' from 'pdfminer.converter' (/Users/junkim/Development/projects/ai/ChatGPT-Paper-Reader/pdf-gpt/lib/python3.9/site-packages/pdfminer/converter.py)

After commenting out the HOCRConverter from
from .converter import ( XMLConverter, HTMLConverter, TextConverter, PDFPageAggregator, HOCRConverter, ),

from .utils import open_filename, FileOrName, AnyIO
also isn't able to import the three functions open_filename, FileOrName, and AnyIO.

Would love to figure out what's going wrong and be able to check out the program!

AttributeError: module 'openai' has no attribute 'ChatCompletion'

File "C:\Users\shiel\AppData\Roaming\Python\Python310\site-packages\PyPDF2_reader.py", line 1414, in read
self._basic_validation(stream)
File "C:\Users\shiel\AppData\Roaming\Python\Python310\site-packages\PyPDF2_reader.py", line 1455, in _basic_validation
raise EmptyFileError("Cannot read an empty file")
PyPDF2.errors.EmptyFileError: Cannot read an empty file

When I tried to use it to analyze the paper, it gave me this error

这里是否应该为ret = self.bot_core.communicate(self.question_msg)？