101–110 of 114 posts
Earlier quoted context omitted.
Only last week there was a HN thread about how the author said they just used chatgpt to make the entire thing and as a result the code is beyond bad. I don't think I'd trust it.
>I don't think I'd trust it. You can audit the code yourself then. What's stopping you?
I decided to create pdfequips.com when a friend kept sending me PDF files for translation, realizing the widespread need for PDF solutions Now, it serves as a central hub for PDF management, offering conversion tools like PDF to Word and CSV, as well as OCR technology Over the past year, I extensively developed the website, leveraging a wide range of open-source tools on both the front-end and back-end.
I think it looks like a nice tool, naysayers notwithstanding. I don't have sensitive PDFs and, though I would probably not use it for my tax return, I'll use it for other stuff. For my level of security, I'm happy enough with your promise to delete the stuff right away.
this is how the code looks like on the server side for most of the tools:
```python ... @after_this_request def remove_file(response): os.remove(tmp_file.name) return response return response ``` i don't have any reason to keep them.
Earlier quoted context omitted.
I think it looks like a nice tool, naysayers notwithstanding. I don't have sensitive PDFs and, though I would probably not use it for my tax return, I'll use it for other stuff. For my level of security, I'm happy enough with your promise to delete the stuff right away.
i appreciate your trust, and yeah belive me i'm deleting the files right after the processing, the way it works is that i'm saving the files uploaded as a tmp file then process it then delete them after the response. this is how the code looks like on the server side for most of the tools: ```python ... @after_this_request def remove_file(response): os.remove(tmp_file.name) return response return response ``` i don't…
I have 85,000 PDF documents, collected over a few decades. What I really want is a semantic interface to those PDF documents. Find me "all PDF files which mention ", or "show me any PDF with python example code", or "all PDF's before 2011 on the subject of coding standards for SIL-4". I keep thinking this is out there somewhere, but whenever something new comes along I get bogged down in the details of setting it up.…
Have you tried Paperless NGX?
I have 85,000 PDF documents, collected over a few decades. What I really want is a semantic interface to those PDF documents. Find me "all PDF files which mention ", or "show me any PDF with python example code", or "all PDF's before 2011 on the subject of coding standards for SIL-4". I keep thinking this is out there somewhere, but whenever something new comes along I get bogged down in the details of setting it up.…
This is what I use for that https://github.com/simon987/sist2
I have 85,000 PDF documents, collected over a few decades. What I really want is a semantic interface to those PDF documents. Find me "all PDF files which mention ", or "show me any PDF with python example code", or "all PDF's before 2011 on the subject of coding standards for SIL-4". I keep thinking this is out there somewhere, but whenever something new comes along I get bogged down in the details of setting it up.…
You can do this locally with your favourite LLM and Open WebUI: https://github.com/open-webui/open-webui
Earlier quoted context omitted.
Only last week there was a HN thread about how the author said they just used chatgpt to make the entire thing and as a result the code is beyond bad. I don't think I'd trust it.
>I don't think I'd trust it. You can audit the code yourself then. What's stopping you?