Update app.py

app.py

@@ -3,19 +3,17 @@ 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
+from langchain_huggingface import HuggingFaceEndpoint
 
 # 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",
@@ -25,7 +23,6 @@ st.set_page_config(
 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;'>
@@ -53,66 +50,61 @@ if uploaded_file:
         temp_file.write(uploaded_file.read())
         orig_path = temp_file.name
 
-    # Step 1: Read and preprocess 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)
 
+    # 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)
 
-    # 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])
-
+    # 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="mistralai/Mistral-7B-Instruct-v0.3",
-        provider="novita",
+        repo_id="aaditya/Llama3-OpenBioLLM-70B",
+        provider="nebius",
         temperature=0.6,
         max_new_tokens=300,
         task="conversational"
     )
 
-    model = ChatHuggingFace(
+    llm = ChatHuggingFace(
         llm=llm_model,
-        repo_id="mistralai/Mistral-7B-Instruct-v0.3",
-        provider="novita",
+        repo_id="aaditya/Llama3-OpenBioLLM-70B",
+        provider="nebius",
         temperature=0.6,
         max_new_tokens=300,
         task="conversational"
     )
-    
-    chain = LLMChain(llm=model, prompt=prompt)
 
-   
+    chain = LLMChain(llm=llm, prompt=prompt)
+
     col1, col2 = st.columns([1, 2])
 
     with col1:
@@ -120,16 +112,12 @@ if uploaded_file:
 
     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
@@ -141,6 +129,151 @@ else:
 
 
 
+
+
+# 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')