Spaces:
Sleeping
Sleeping
| # -*- coding: utf-8 -*- | |
| """Hackathon_Illuminati.ipynb | |
| Automatically generated by Colaboratory. | |
| Original file is located at | |
| https://colab.research.google.com/drive/1B-SaMQ85UdV9DnqZ6_OWqg8oOAlgcZ5V | |
| # LangChain QA Panel App | |
| This notebook shows how to make this app: | |
| """ | |
| # !pip install transformers | |
| # !pip install easyocr | |
| # !pip install pdf2image | |
| # !apt-get install poppler-utils | |
| # | |
| # ! pip install PyPDF2 | |
| import panel as pn | |
| from transformers import pipeline | |
| from pdf2image import convert_from_path | |
| import easyocr | |
| pn.extension('texteditor', template="bootstrap", sizing_mode='stretch_width') | |
| pn.state.template.param.update( | |
| main_max_width="690px", | |
| header_background="#F08080", | |
| ) | |
| file_input = pn.widgets.FileInput(width=300) | |
| prompt = pn.widgets.TextEditor( | |
| value="", placeholder="Enter your questions here...", height=160, toolbar=False | |
| ) | |
| run_button = pn.widgets.Button(name="Run") | |
| widgets = pn.Row( | |
| pn.Column(prompt, run_button, margin=5), width = 630 | |
| ) | |
| def qa(file, query): | |
| images = convert_from_path(file) | |
| reader = easyocr.Reader(['en']) | |
| result = [] | |
| for i in range(len(images)): | |
| # Save pages as images in the pdf | |
| images[i].save('page'+ str(i) +'.jpg', 'JPEG') | |
| x=str(i) | |
| t='page'+x+'.jpg' | |
| result.append(reader.readtext(t, detail = 0)) | |
| text = "" | |
| for page in result: | |
| page_text = " ".join(page) | |
| text += page_text | |
| model = pipeline("question-answering", model='deepset/roberta-base-squad2') | |
| context = text | |
| result = model(question=query, context=context) | |
| print(f"Answer: {result['answer']}") | |
| return result | |
| convos = [] # list of all panel objects | |
| def qa_result(_): | |
| # saving pdf as a temp file | |
| if file_input.value is not None: | |
| file_input.save("/content/temp.pdf") | |
| prompt_text = prompt.value | |
| if prompt_text: | |
| result = qa(file="/content/temp.pdf", query=prompt_text) | |
| convos.extend([ | |
| pn.Row( | |
| pn.panel("Q: ", width=10), | |
| prompt_text, | |
| width=600 | |
| ), | |
| pn.Row( | |
| pn.panel("A: ", width=10), | |
| pn.Column( | |
| result["answer"], | |
| ) | |
| ) | |
| ]) | |
| #return convos | |
| return pn.Column(*convos, margin=15, width=575, min_height=400) | |
| qa_interactive = pn.panel( | |
| pn.bind(qa_result, run_button), | |
| loading_indicator=True, | |
| ) | |
| output = pn.WidgetBox('*Output will show up here:*', qa_interactive, width=630, scroll=True) | |
| # layout | |
| pn.Column( | |
| pn.pane.Markdown(""" | |
| Question Answering with your PDF file! | |
| 1) Upload a PDF. \n | |
| 2) Type a question and click "Run". | |
| """), | |
| pn.Row(file_input), | |
| output, | |
| widgets | |
| ).servable() |