Kain Shu
Kain Shu
Thank you for your review. I used a combination of `isort`, `black`, and `blackdoc`. You can refer to this file for specific commands: `backend/Makefile`, it's also a good idea to...
@karanchellani hi, Any progress?
> Hi @Kain-90 We are using specific loader for pdfs because for pdf documents we are getting better metadata(filesize, page number,etc) from PyMuPDFLoader as compared to UnstructuredFileLoader. Hi, thx for...
I suddenly realized that the attribute `filesize` is not fetched via PyMuPDFLoader, but is returned via this method when uploading the file, so what other richer `metadata` seems to be...
And for the PDF file type, the following code will make it simpler to obtain the page number. ``` def load_document_content(file_path): if Path(file_path).suffix.lower() == ".pdf": return UnstructuredFileLoader( file_path, mode="paged", autodetect_encoding=True...
I've read related issues, and some people have encountered the same problem as me, that is, **occasional errors, not every time**, this [issue](https://github.com/langgenius/dify/issues/4993) is marked as complete, but in fact,...
> Please upgrade the sandbox to 0.2.10. Thanks for your reply. It's been upgraded to 0.2.10, but i encountered the same issue again, and under the same reproduction conditions, another...
> Please upgrade the sandbox to 0.2.10. Is there any progress?
@crazywoola Hi, is it solved?
I recommend integrating Langchain Smith into your project, so you can see the prompts that are being sent to llm. This can help you quickly identify the real problem.