Update app.py

app.py

@@ -48,24 +48,29 @@ def save_text_as_image(text, file_path):
     img.save(file_path)
     return file_path
 
-# Setup UI
-st.set_page_config(page_title="MediAssist 💊", layout="wide")
+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("""
-    <style>
-    .stButton>button {
-        background-color: #4CAF50;
-        color: white;
-        font-weight: bold;
-        padding: 8px 20px;
-        border-radius: 8px;
-    }
-    </style>
+    <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)
 
-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:
@@ -98,35 +103,41 @@ if uploaded_file:
 
     # Prompt LLM
     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.
+        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(
+    llm = HuggingFaceEndpoint(
         repo_id="aaditya/Llama3-OpenBioLLM-70B",
         provider="nebius",
         temperature=0.6,
         max_new_tokens=300,
-        task="conversational"
+        task="text-generation"
     )
     
-    llm = ChatHuggingFace(
-        llm=llm_model,
-        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)
 
@@ -137,7 +148,7 @@ if uploaded_file:
         with st.spinner("Analyzing with LLM..."):
             response = chain.run(prescription_text=text)
         st.markdown("#### 💡 AI-based Medicine Analysis")
-        st.text_area("LLM Output", response, height=300)
+        st.success(response)
 
         # Save txt and image
         txt_path = "medicine_analysis.txt"
@@ -189,7 +200,7 @@ if uploaded_file:
     try:
         os.remove(orig_path)
         os.remove(dilated_path)
-        llm.clear()
+
     except:
         pass