Spaces:

Yashvj123
/

MediAssist

Running

File size: 15,819 Bytes

import streamlit as st
import cv2
import numpy as np
import tempfile
import os
import easyocr
from PIL import Image, ImageDraw, ImageFont
from translate import Translator

from langchain.prompts import PromptTemplate
from langchain.chains import LLMChain
from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace
from transformers import pipeline

# Set API keys
os.environ["HUGGINGFACEHUB_API_KEY"] = os.getenv("HF")
os.environ["HF_TOKEN"] = os.getenv("HF")

# Function to save text as an image
def save_text_as_image(text, file_path):
    font = ImageFont.load_default()
    lines = text.split('\n')
    max_width = max([font.getbbox(line)[2] for line in lines]) + 20
    line_height = font.getbbox(text)[3] + 10
    img_height = line_height * len(lines) + 20

    img = Image.new("RGB", (max_width, img_height), "white")
    draw = ImageDraw.Draw(img)
    y = 10
    for line in lines:
        draw.text((10, y), line, font=font, fill="black")
        y += line_height

    img.save(file_path)
    return file_path

# Setup
st.set_page_config(page_title="MediAssist 💊", layout="wide")

st.markdown("""
    <style>
    .stButton>button {
        background-color: #4CAF50;
        color: white;
        font-weight: bold;
        padding: 8px 20px;
        border-radius: 8px;
    }
    </style>
""", unsafe_allow_html=True)

st.title("💊 MediAssist - Prescription Analyzer")
st.markdown("##### Upload your prescription, get AI-based medicine insights, translate and download!")

uploaded_file = st.file_uploader("📤 Upload Prescription Image (JPG/PNG)", type=["jpg", "jpeg", "png"])

if uploaded_file:
    with tempfile.NamedTemporaryFile(delete=False, suffix=".png") as temp_file:
        temp_file.write(uploaded_file.read())
        orig_path = temp_file.name

    # Preprocess Image
    image = cv2.imread(orig_path)
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    _, binary_inv = cv2.threshold(gray, 128, 255, cv2.THRESH_BINARY_INV)
    kernel = np.ones((3, 3), np.uint8)
    dilated = cv2.dilate(binary_inv, kernel, iterations=1)

    dilated_path = orig_path.replace(".png", "_dilated.png")
    cv2.imwrite(dilated_path, dilated)

    # OCR
    reader = easyocr.Reader(['en'])
    text_list = reader.readtext(dilated, detail=0)
    text = "\n".join(text_list)

    # Display
    col1, col2 = st.columns([1, 2])
    with col1:
        st.image(dilated, caption="Preprocessed Prescription", channels="GRAY", use_container_width=True)
    with col2:
        st.success("✅ Image Uploaded and Preprocessed")
        st.markdown("#### 📝 Extracted Text from Image")
        st.code(text)

    # Prompt
    template = """
    You are a helpful medical assistant.
    Here is a prescription text extracted from an image:
    {prescription_text}
    Please do the following:
    1. Extract only the medicine names.
    2. For each, give:
       - Dosage and Timing
       - Possible Side Effects
       - Special Instructions
    Format in bullet points, medicine-wise.
    """
    prompt = PromptTemplate(input_variables=["prescription_text"], template=template)

    llm_model = HuggingFaceEndpoint(
        repo_id="aaditya/Llama3-OpenBioLLM-70B",
        provider="nebius",
        temperature=0.6,
        max_new_tokens=300,
        task="conversational"
    )
    
    llm = ChatHuggingFace(
        llm=llm_model,
        repo_id="aaditya/Llama3-OpenBioLLM-70B",
        provider="nebius",
        temperature=0.6,
        max_new_tokens=300,
        task="conversational"
    )
    
    chain = LLMChain(llm=llm, prompt=prompt)

    if st.button("🔍 Analyze Extracted Text"):
        with st.spinner("Analyzing with LLM..."):
            response = chain.run(prescription_text=text)
        st.markdown("#### 💡 Analyzed Medicine Info")
        st.text_area("Output", response, height=300)

        # Save txt and image
        txt_path = "prescription_output.txt"
        with open(txt_path, "w") as f:
            f.write(response)

        img_path = "prescription_output.png"
        save_text_as_image(response, img_path)

        # Target language code (like 'hi' for Hindi, 'mr' for Marathi, 'gu' for Gujarati)
        target_lang = "hi"  
        
        translator = Translator(to_lang=target_lang)
        hindi_text = translator.translate(response)

        # # Translation to Hindi
        # translator = pipeline("translation", model="Helsinki-NLP/opus-mt-en-hi")
        # hindi_text = translator(response, max_length=400)[0]['translation_text']

        st.markdown("#### 🌐 Translate to Hindi")
        st.text_area("Translated (Hindi)", hindi_text, height=300)

        st.markdown("#### 📥 Download Options")
        colA, colB, colC, colD = st.columns(4)
        with colA:
            st.download_button("⬇️ Download TXT", data=response, file_name="medicine_analysis.txt")
        with colB:
            with open(img_path, "rb") as img_file:
                st.download_button("🖼️ Download Image", data=img_file, file_name="medicine_analysis.png", mime="image/png")
        with colC:
            st.download_button("⬇️ Hindi TXT", data=hindi_text, file_name="hindi_medicine_analysis.txt")
        with colD:
            hindi_img_path = "hindi_output.png"
            save_text_as_image(hindi_text, hindi_img_path)
            with open(hindi_img_path, "rb") as hindi_img_file:
                st.download_button("🖼️ Hindi Image", data=hindi_img_file, file_name="hindi_output.png", mime="image/png")

    # Cleanup
    os.remove(orig_path)
    os.remove(dilated_path)
else:
    st.markdown("<center><i>📸 Upload a prescription image to get started</i></center>", unsafe_allow_html=True)





# import streamlit as st
# import cv2
# import numpy as np
# import tempfile
# import os
# import easyocr

# from langchain.prompts import PromptTemplate
# from langchain.chains import LLMChain
# from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace

# # Set Hugging Face API keys
# os.environ["HUGGINGFACEHUB_API_KEY"] = os.getenv("HF")
# os.environ["HF_TOKEN"] = os.getenv("HF")

# # Streamlit page setup
# st.set_page_config(
#     page_title="MediAssist - Prescription Analyzer",
#     layout="wide",
#     page_icon="💊"
# )

# st.sidebar.title("💊 MediAssist")
# st.sidebar.markdown("Analyze prescriptions with ease using AI")
# st.sidebar.markdown("---")
# st.sidebar.markdown("🔗 **Connect with me:**")
# st.sidebar.markdown("""
# <div style='display: flex; gap: 10px;'>
#     <a href="https://github.com/Yashvj22" target="_blank">
#         <img src="https://img.shields.io/badge/GitHub-100000?style=for-the-badge&logo=github&logoColor=white" style="height:30px;">
#     </a>
#     <a href="https://www.linkedin.com/in/yash-jadhav-454b0a237/" target="_blank">
#         <img src="https://img.shields.io/badge/LinkedIn-0A66C2?style=for-the-badge&logo=linkedin&logoColor=white" style="height:30px;">
#     </a>
# </div>
# """, unsafe_allow_html=True)
# st.sidebar.markdown("---")

# st.markdown("""
#     <h1 style='text-align: center; color: #4A90E2;'>🧠 MediAssist</h1>
#     <h3 style='text-align: center;'>Prescription Analyzer using AI and OCR</h3>
#     <p style='text-align: center;'>Upload a doctor's prescription image, and MediAssist will extract, translate, and explain it for you.</p>
#     <br>
# """, unsafe_allow_html=True)

# uploaded_file = st.file_uploader("📤 Upload Prescription Image (JPG/PNG)", type=["jpg", "jpeg", "png"])

# if uploaded_file:
#     with tempfile.NamedTemporaryFile(delete=False, suffix=".png") as temp_file:
#         temp_file.write(uploaded_file.read())
#         orig_path = temp_file.name

#     # Preprocessing
#     image = cv2.imread(orig_path)
#     gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
#     _, binary_inv = cv2.threshold(gray, 128, 255, cv2.THRESH_BINARY_INV)
#     kernel = np.ones((3, 3), np.uint8)
#     dilated = cv2.dilate(binary_inv, kernel, iterations=1)

#     # Save preprocessed image for future reference/removal
#     dilated_path = orig_path.replace(".png", "_dilated.png")
#     cv2.imwrite(dilated_path, dilated)

#     # OCR using EasyOCR
#     reader = easyocr.Reader(['en'])
#     text_list = reader.readtext(dilated, detail=0)
#     text = "\n".join(text_list)

#     # Prompt Template
#     template = """
#         You are a helpful medical assistant.

#         Here is a prescription text extracted from an image:

#         {prescription_text}

#         Please do the following:

#         1. Extract only the medicine names mentioned in the prescription (ignore any other text).
#         2. For each medicine, provide:
#            - When to take it (timing and dosage)
#            - Possible side effects
#            - Any special instructions

#         Format your answer as bullet points, listing only medicines and their details.
#     """
#     prompt = PromptTemplate(input_variables=["prescription_text"], template=template)

#     llm_model = HuggingFaceEndpoint(
#         repo_id="aaditya/Llama3-OpenBioLLM-70B",
#         provider="nebius",
#         temperature=0.6,
#         max_new_tokens=300,
#         task="conversational"
#     )

#     llm = ChatHuggingFace(
#         llm=llm_model,
#         repo_id="aaditya/Llama3-OpenBioLLM-70B",
#         provider="nebius",
#         temperature=0.6,
#         max_new_tokens=300,
#         task="conversational"
#     )

#     chain = LLMChain(llm=llm, prompt=prompt)

#     col1, col2 = st.columns([1, 2])

#     with col1:
#         st.image(dilated, caption="Preprocessed Prescription", channels="GRAY", use_container_width=True)

#     with col2:
#         st.success("✅ Prescription Uploaded & Preprocessed Successfully")
#         st.markdown("### 📜 Extracted Text")
#         st.code(text)

#         if st.button("🔍 Analyze Text"):
#             with st.spinner("Analyzing..."):
#                 response = chain.run(prescription_text=text)
#             st.success(response)

#     # Cleanup temp files
#     os.remove(orig_path)
#     os.remove(dilated_path)

# else:
#     st.markdown("<center><i>Upload a prescription image to begin analysis.</i></center>", unsafe_allow_html=True)





# import streamlit as st
# import cv2
# import numpy as np
# import tempfile
# import os
# # import pytesseract
# import easyocr

# # from langchain.document_loaders.image import UnstructuredImageLoader
# # from langchain_community.document_loaders import UnstructuredImageLoader
# from langchain.prompts import PromptTemplate
# from langchain.chains import LLMChain
# from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace

# # Set Hugging Face API keys
# os.environ["HUGGINGFACEHUB_API_KEY"] = os.getenv("HF")
# os.environ["HF_TOKEN"] = os.getenv("HF")

# st.set_page_config(
#     page_title="MediAssist - Prescription Analyzer",
#     layout="wide",
#     page_icon="💊"
# )

# st.sidebar.title("💊 MediAssist")
# st.sidebar.markdown("Analyze prescriptions with ease using AI")
# st.sidebar.markdown("---")

# st.sidebar.markdown("🔗 **Connect with me:**")
# st.sidebar.markdown("""
# <div style='display: flex; gap: 10px;'>
#     <a href="https://github.com/Yashvj22" target="_blank">
#         <img src="https://img.shields.io/badge/GitHub-100000?style=for-the-badge&logo=github&logoColor=white" style="height:30px;">
#     </a>
#     <a href="https://www.linkedin.com/in/yash-jadhav-454b0a237/" target="_blank">
#         <img src="https://img.shields.io/badge/LinkedIn-0A66C2?style=for-the-badge&logo=linkedin&logoColor=white" style="height:30px;">
#     </a>
# </div>
# """, unsafe_allow_html=True)
# st.sidebar.markdown("---")

# st.markdown("""
#     <h1 style='text-align: center; color: #4A90E2;'>🧠 MediAssist</h1>
#     <h3 style='text-align: center;'>Prescription Analyzer using AI and OCR</h3>
#     <p style='text-align: center;'>Upload a doctor's prescription image, and MediAssist will extract, translate, and explain it for you.</p>
#     <br>
# """, unsafe_allow_html=True)

# uploaded_file = st.file_uploader("📤 Upload Prescription Image (JPG/PNG)", type=["jpg", "jpeg", "png"])

# if uploaded_file:
#     with tempfile.NamedTemporaryFile(delete=False, suffix=".png") as temp_file:
#         temp_file.write(uploaded_file.read())
#         orig_path = temp_file.name

#     # Step 1: Read and preprocess image
#     image = cv2.imread(orig_path)
#     gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
#     _, binary_inv = cv2.threshold(gray, 128, 255, cv2.THRESH_BINARY_INV)
#     kernel = np.ones((3, 3), np.uint8)
#     dilated = cv2.dilate(binary_inv, kernel, iterations=1)

#     reader = easyocr.Reader(['en'])
#     text_list = reader.readtext(dilated, detail=0)
#     text = "\n".join(text_list)

#     # text = pytesseract.image_to_string(dilated)

#     # Save preprocessed image for OCR
#     # dilated_path = orig_path.replace(".png", "_dilated.png")
#     # cv2.imwrite(dilated_path, dilated)

#     # loader = UnstructuredImageLoader(dilated_path)
#     # documents = loader.load()
#     # extracted_text = "\n".join([doc.page_content for doc in documents])

#     template = """
#         You are a helpful medical assistant.
        
#         Here is a prescription text extracted from an image:
        
#         {prescription_text}
        
#         Please do the following:
        
#         1. Extract only the medicine names mentioned in the prescription (ignore any other text).
#         2. For each medicine, provide:
#            - When to take it (timing and dosage)
#            - Possible side effects
#            - Any special instructions
        
#         Format your answer as bullet points, listing only medicines and their details.
#     """
#     prompt = PromptTemplate(input_variables=["prescription_text"], template=template)

#     llm_model = HuggingFaceEndpoint(
#         repo_id="aaditya/Llama3-OpenBioLLM-70B",
#         provider="nebius",
#         temperature=0.6,
#         max_new_tokens=300,
#         task="conversational"
#     )

#     model = ChatHuggingFace(
#         llm=llm_model,
#         repo_id="aaditya/Llama3-OpenBioLLM-70B",
#         provider="nebius",
#         temperature=0.6,
#         max_new_tokens=300,
#         task="conversational"
#     )
    
#     chain = LLMChain(llm=model, prompt=prompt)

   
#     col1, col2 = st.columns([1, 2])

#     with col1:
#         st.image(dilated, caption="Preprocessed Prescription", channels="GRAY", use_container_width=True)

#     with col2:
#         st.success("✅ Prescription Uploaded & Preprocessed Successfully")

#         st.markdown("### 📜 Extracted Text")
#         st.code(text)
    
#         # st.code(extracted_text)

#         if st.button("🔍 Analyze Text"):
#             with st.spinner("Analyzing..."):
#                 response = chain.run(prescription_text=text)
#                 # response = chain.run(prescription_text=extracted_text)
#             st.success(response)

#     # Cleanup temp files
#     os.remove(orig_path)
#     os.remove(dilated_path)

# else:
#     st.markdown("<center><i>Upload a prescription image to begin analysis.</i></center>", unsafe_allow_html=True)



        # st.markdown("### 🌐 Translated Text")
        # st.code("पेरासिटामोल 500 मिलीग्राम\nभोजन के बाद दिन में दो बार 1 गोली लें", language='text')

        # st.markdown("### ⏱️ Tablet Timing & Instructions")
        # st.info("- Morning after breakfast\n- Night after dinner\n- Take with water\n- Do not exceed 2 tablets in 24 hours")

        # st.markdown("### ⚠️ Possible Side Effects")
        # st.warning("- Nausea\n- Dizziness\n- Liver damage (on overdose)")

    # os.remove(temp_path)
    # os.remove(orig_path)
    # os.remove(dilated_path)