Spaces:
Running
Running
| import streamlit as st | |
| import cv2 | |
| import numpy as np | |
| import tempfile | |
| import os | |
| # import easyocr | |
| from PIL import Image, ImageDraw, ImageFont | |
| from deep_translator import GoogleTranslator | |
| import base64 | |
| from paddleocr import PaddleOCR | |
| from langchain.prompts import PromptTemplate | |
| from langchain.chains import LLMChain | |
| from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace | |
| 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="💊" | |
| ) | |
| def set_background(image_file): | |
| with open(image_file, "rb") as image: | |
| encoded = base64.b64encode(image.read()).decode() | |
| st.markdown( | |
| f""" | |
| <style> | |
| .stApp {{ | |
| background-image: linear-gradient(rgba(0, 0, 0, 0.4), rgba(0, 0, 0, 0.4)), | |
| url("data:image/jpg;base64,{encoded}"); | |
| background-size: cover; | |
| background-repeat: no-repeat; | |
| background-attachment: fixed; | |
| }} | |
| .main-title {{ | |
| color: #ffffff; | |
| text-align: center; | |
| font-size: 3em; | |
| font-weight: 900; | |
| margin-bottom: 0.2em; | |
| text-shadow: 2px 2px 4px rgba(0, 0, 0, 0.7); | |
| }} | |
| .subtitle {{ | |
| color: #f0f0f0; | |
| text-align: center; | |
| font-size: 1.4em; | |
| margin-bottom: 0.5em; | |
| text-shadow: 1px 1px 3px rgba(0, 0, 0, 0.6); | |
| }} | |
| .quote {{ | |
| color: #eeeeee; | |
| text-align: center; | |
| font-style: italic; | |
| font-size: 1.2em; | |
| margin-bottom: 2em; | |
| text-shadow: 1px 1px 3px rgba(0, 0, 0, 0.6); | |
| }} | |
| h1, h3 {{ | |
| color: #ffffff !important; | |
| text-shadow: 2px 2px 5px rgba(0, 0, 0, 0.8); | |
| font-weight: 800; | |
| }} | |
| .stButton>button {{ | |
| width: 100%; | |
| font-size: 1.1em; | |
| padding: 0.8em; | |
| border-radius: 10px; | |
| }} | |
| </style> | |
| """, | |
| unsafe_allow_html=True | |
| ) | |
| # Split large response into smaller chunks (for translation) | |
| # def split_text_into_chunks(text, max_length=450): | |
| # lines = text.split('\n') | |
| # chunks = [] | |
| # current = "" | |
| # for line in lines: | |
| # if len(current) + len(line) + 1 <= max_length: | |
| # current += line + '\n' | |
| # else: | |
| # chunks.append(current.strip()) | |
| # current = line + '\n' | |
| # if current: | |
| # chunks.append(current.strip()) | |
| # return chunks | |
| 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 | |
| set_background("background_img.jpg") | |
| # # OCR | |
| # @st.cache_resource | |
| # def load_easyocr_reader(): | |
| # return easyocr.Reader(['en']) | |
| 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 | |
| # Image 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) | |
| dilated_path = orig_path.replace(".png", "_dilated.png") | |
| cv2.imwrite(dilated_path, dilated) | |
| ocr = PaddleOCR(use_angle_cls=True, lang='en') # use_angle_cls for better orientation handling | |
| result = ocr.ocr(dilated_path, cls=True) | |
| text_list = [line[1][0] for line in result[0]] # Extract only text | |
| text = "\n".join(text_list) | |
| # reader = easyocr.Reader(['en']) | |
| # text_list = reader.readtext(dilated, detail=0) | |
| # text = "\n".join(text_list) | |
| 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") | |
| st.code(text) | |
| # Prompt LLM | |
| template = """ | |
| You are a helpful and structured medical assistant. | |
| Below is a prescription text extracted from an image: | |
| {prescription_text} | |
| Your tasks: | |
| 1. Identify and list only the medicine names mentioned (ignore other irrelevant text). | |
| 2. For each identified medicine, provide the following: | |
| - Dosage and Timing | |
| - Possible Side Effects | |
| - Special Instructions | |
| 🧾 Format your response clearly and neatly as follows: | |
| - Medicine Name 1 | |
| - Dosage and Timing: ... | |
| - Side Effects: ... | |
| - Special Instructions: ... | |
| - Medicine Name 2 | |
| - Dosage and Timing: ... | |
| - Side Effects: ... | |
| - Special Instructions: ... | |
| Ensure each medicine starts with a new bullet point and all details are on separate lines and don't bold any bullet point. | |
| """ | |
| prompt = PromptTemplate(input_variables=["prescription_text"], template=template) | |
| llm_model = HuggingFaceEndpoint( | |
| repo_id="Qwen/Qwen3-235B-A22B", | |
| provider="nebius", | |
| temperature=0.6, | |
| max_new_tokens=300, | |
| task="conversational" | |
| ) | |
| llm = ChatHuggingFace( | |
| llm=llm_model, | |
| repo_id="Qwen/Qwen3-235B-A22B", | |
| provider="nebius", | |
| temperature=0.6, | |
| max_new_tokens=300, | |
| task="conversational" | |
| ) | |
| chain = LLMChain(llm=llm, prompt=prompt) | |
| filtered_output = "" | |
| hindi_text = "" | |
| if st.button("🔍 Analyze Extracted Text"): | |
| with st.spinner("Analyzing with LLM..."): | |
| response = chain.run(prescription_text=text) | |
| parts = response.split("</think>") | |
| if len(parts) > 1: | |
| filtered_output = parts[1].strip() | |
| else: | |
| filtered_output = response | |
| st.markdown("#### 💡 AI-based Medicine Analysis") | |
| st.text_area("LLM Output", filtered_output, height=300) | |
| # Save txt and image | |
| txt_path = "medicine_analysis.txt" | |
| with open(txt_path, "w") as f: | |
| f.write(filtered_output) | |
| img_path = "medicine_analysis.png" | |
| save_text_as_image(filtered_output, img_path) | |
| st.markdown("#### 📥 Download (English)") | |
| col1, col2 = st.columns(2) | |
| with col1: | |
| st.download_button("⬇️ English TXT", data=filtered_output.encode(), file_name="medicine_analysis.txt") | |
| with col2: | |
| with open(img_path, "rb") as img_file: | |
| st.download_button("🖼️ English Image", data=img_file, file_name="medicine_analysis.png", mime="image/png") | |
| # if filtered_output and st.button("🌐 Translate to Hindi"): | |
| # with st.spinner("Translating to Hindi..."): | |
| # def clean_text(text): | |
| # text = text.replace("•", "-") # Replace bullets | |
| # text = re.sub(r"\s{2,}", " ", text) # Remove extra spaces | |
| # text = re.sub(r"[^\w\s,.:-]", "", text) # Keep only safe characters | |
| # return text | |
| # cleaned_output = clean_text(filtered_output) | |
| # try: | |
| # hindi_text = GoogleTranslator(source='en', target='hi').translate(cleaned_output) | |
| # except Exception as e: | |
| # hindi_text = "[Translation failed]" | |
| # # Formatting translated text | |
| # formatted_text = re.sub(r'(?<=\s)-\s', r'\n- ', hindi_text) | |
| # # Add line breaks before keywords | |
| # keywords = ["खुराक और समय", "साइड इफेक्ट्स", "विशेष निर्देश"] | |
| # for kw in keywords: | |
| # formatted_text = formatted_text.replace(f"- {kw}", f"\n - {kw}") | |
| # final_text = formatted_text.strip() | |
| # st.markdown("#### 🌐 Hindi Translation") | |
| # st.text_area("Translated Output (Hindi)", value=final_text, height=300) | |
| # hindi_img_path = "hindi_output.png" | |
| # save_text_as_image(final_text, hindi_img_path) | |
| # st.markdown("#### 📥 Download (Hindi)") | |
| # col3, col4 = st.columns(2) | |
| # with col3: | |
| # st.download_button("⬇️ Hindi TXT", data=final_text.encode(), file_name="hindi_medicine_analysis.txt") | |
| # with col4: | |
| # with open(hindi_img_path, "rb") as img_file: | |
| # st.download_button("🖼️ Hindi Image", data=img_file, file_name="hindi_medicine_analysis.png", mime="image/png") | |
| try: | |
| os.remove(orig_path) | |
| os.remove(dilated_path) | |
| except: | |
| pass | |
| else: | |
| st.markdown("<center><i>📸 Please Upload Scanned prescription image to get best result</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) |