src/streamlit_app.py

import streamlit as st
import cv2
import numpy as np
import tempfile
import os
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 key
os.environ["HUGGINGFACEHUB_API_KEY"] = os.getenv("hf")

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

# Sidebar
st.sidebar.title("😷 Medical Chatbot")
st.sidebar.markdown("Analyze prescriptions with ease using AI")
st.sidebar.markdown("---")

# App Header
st.markdown("""
    <h1 style='text-align: center; color: #4A90E2;'>🧠 Medical Chatbot</h1>
    <h3 style='text-align: center;'>Prescription Analyzer using AI </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)

# File uploader
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)

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

    # Load with LangChain
    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)

    # Set up Hugging Face LLM
    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)

    # Display image and extracted text
    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(extracted_text)

        if st.button("🔍 Analyze Text"):
            with st.spinner("Analyzing..."):
                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)