Spaces:
Runtime error
Runtime error
File size: 2,407 Bytes
50764c7 ec854f5 50764c7 ec854f5 a7a1018 ec854f5 50764c7 ec854f5 50764c7 ec854f5 50764c7 ec854f5 50764c7 ec854f5 50764c7 ec854f5 50764c7 ec854f5 9f4520a ec854f5 9f4520a ec854f5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
import gradio as gr
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import PyPDF2
import csv
import io
# Load the model and tokenizer
model_name = "your_fine_tuned_model_name" # Replace with your actual model name
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
def process_text(text):
inputs = tokenizer(text, return_tensors="pt", max_length=512, truncation=True)
with torch.no_grad():
outputs = model.generate(**inputs, max_length=1000)
return tokenizer.decode(outputs[0], skip_special_tokens=True)
def extract_text_from_pdf(file):
pdf_reader = PyPDF2.PdfFileReader(file)
text = ""
for page in range(pdf_reader.numPages):
text += pdf_reader.getPage(page).extractText()
return text
def process_csv(file):
content = file.read().decode('utf-8')
csv_reader = csv.reader(io.StringIO(content))
rows = list(csv_reader)
return "\n".join([",".join(row) for row in rows])
def analyze_document(file):
if file.name.endswith('.pdf'):
text = extract_text_from_pdf(file)
elif file.name.endswith('.csv'):
text = process_csv(file)
else:
return "Unsupported file format. Please upload a PDF or CSV file."
prompt = f"Analyze the following procurement document and provide a detailed audit report:\n\n{text}"
return process_text(prompt)
def answer_question(question, context):
prompt = f"Context: {context}\n\nQuestion: {question}\n\nAnswer:"
return process_text(prompt)
with gr.Blocks() as demo:
gr.Markdown("# AuditBidden: AI-Powered Public Procurement Auditor")
with gr.Tab("Document Analysis"):
file_input = gr.File(label="Upload Procurement Document (PDF or CSV)")
analyze_button = gr.Button("Analyze Document")
analysis_output = gr.Textbox(label="Audit Report")
analyze_button.click(analyze_document, inputs=file_input, outputs=analysis_output)
with gr.Tab("Q&A"):
context_input = gr.Textbox(label="Context (paste relevant procurement information)")
question_input = gr.Textbox(label="Question")
answer_button = gr.Button("Get Answer")
answer_output = gr.Textbox(label="Answer")
answer_button.click(answer_question, inputs=[question_input, context_input], outputs=answer_output)
demo.launch() |