Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import google.generativeai as genai | |
| from transformers import AutoModel, AutoTokenizer | |
| from pdf2image import convert_from_path | |
| import torch | |
| import os | |
| import os | |
| import subprocess | |
| import streamlit as st | |
| import google.generativeai as genai | |
| from transformers import AutoModel, AutoTokenizer | |
| from pdf2image import convert_from_path | |
| import torch | |
| # Ensure Poppler is installed | |
| def install_poppler(): | |
| if not os.path.exists("/usr/bin/pdftoppm"): # Check if Poppler is installed | |
| st.warning("Installing Poppler for PDF processing...") | |
| subprocess.run(["apt-get", "update"]) | |
| subprocess.run(["apt-get", "install", "-y", "poppler-utils"]) | |
| # Load the OCR model | |
| tokenizer = AutoTokenizer.from_pretrained("ucaslcl/GOT-OCR2_0", trust_remote_code=True) | |
| model = AutoModel.from_pretrained("ucaslcl/GOT-OCR2_0", trust_remote_code=True, low_cpu_mem_usage=True, | |
| device_map="cuda" if torch.cuda.is_available() else "cpu", | |
| use_safetensors=True, pad_token_id=tokenizer.eos_token_id).eval() | |
| def extract_text_from_pdf(pdf_path): | |
| """Converts PDF pages to images and extracts text using the GOT-OCR2_0 model.""" | |
| text = "" | |
| try: | |
| images = convert_from_path(pdf_path) | |
| for idx, image in enumerate(images): | |
| image_path = f"temp_page_{idx}.png" | |
| image.save(image_path, "PNG") | |
| extracted_text = model.chat(tokenizer, image_path, ocr_type="ocr") | |
| text += extracted_text + "\n" | |
| os.remove(image_path) # Clean up the temporary image file | |
| except Exception as e: | |
| st.error(f"Error extracting text: {e}") | |
| return text | |
| def analyze_health_data(text): | |
| """Analyzes extracted text using Google Generative AI (Free Tier API).""" | |
| try: | |
| genai.configure(api_key="AIzaSyAY6ZYxOzVV5N7mBZzDJ96WEPJGfuFx-mU") # Replace with your Google API key | |
| model = genai.GenerativeModel("gemini-pro") | |
| response = model.generate_content( | |
| f"Analyze this medical report and provide trends, risks, and health suggestions:\n{text}" | |
| ) | |
| return response.text | |
| except Exception as e: | |
| return f"Error in LLM response: {e}" | |
| def main(): | |
| st.title("Health Report Analyzer") | |
| uploaded_file = st.file_uploader("Upload your health report (PDF)", type=["pdf"]) | |
| if uploaded_file is not None: | |
| pdf_path = "temp.pdf" | |
| with open(pdf_path, "wb") as f: | |
| f.write(uploaded_file.getbuffer()) | |
| with st.spinner("Extracting text from the report..."): | |
| extracted_text = extract_text_from_pdf(pdf_path) | |
| st.subheader("Extracted Report Text:") | |
| st.text_area("Extracted Text", extracted_text[:1000], height=200) | |
| if st.button("Analyze Report"): | |
| with st.spinner("Analyzing..."): | |
| analysis = analyze_health_data(extracted_text) | |
| st.subheader("Health Analysis:") | |
| st.write(analysis) | |
| if __name__ == "__main__": | |
| main() |