import streamlit as st
import base64
from huggingface_hub import InferenceClient

# Function to encode the image to base64
def encode_image(image_file):
    return base64.b64encode(image_file.getvalue()).decode("utf-8")

# Streamlit page setup
st.set_page_config(page_title="MTSS Image Accessibility Alt Text Generator", layout="centered", initial_sidebar_state="auto")

# Add the image with a specified width
image_width = 300  # Set the desired width in pixels
st.image('MTSS.ai_Logo.png', width=image_width)

st.header('VisionTexts™ | Accessibility')
st.subheader('Image Alt Text Creator')

# Initialize the Hugging Face InferenceClient with the API key from Streamlit secrets
client = InferenceClient(api_key=st.secrets["huggingface_api_key"])

# File uploader
uploaded_file = st.file_uploader("Upload an image", type=["jpg", "png", "jpeg"])

if uploaded_file:
    # Display the uploaded image with specified width
    image_width = 200  # Set the desired width in pixels
    with st.expander("Image", expanded=True):
        st.image(uploaded_file, caption=uploaded_file.name, width=image_width, use_column_width=False)

# Toggle for showing additional details input
show_details = st.checkbox("Add details about the image.", value=False)

if show_details:
    # Text input for additional details about the image
    additional_details = st.text_area(
        "The details could include specific information that is important to include in the alt text or reflect why the image is being used:",
        disabled=not show_details
    )

# Toggle for modifying the prompt for complex images
complex_image = st.checkbox("Is this a complex image?", value=False)

if complex_image:
    # Caption explaining the impact of the complex image toggle
    st.caption(
        "By clicking this toggle, it will instruct the app to create a description that exceeds the 125-character limit. "
        "Add the description in a placeholder behind the image and 'Description in the content placeholder' in the alt text box."
    )

# Button to trigger the analysis
analyze_button = st.button("Analyze the Image", type="secondary")

# Optimized prompt for complex images
complex_image_prompt_text = (
    "As an expert in image accessibility and alternative text, thoroughly describe the image provided. "
    "Provide a brief description using not more than 500 characters that conveys the essential information in eight or fewer clear and concise sentences. "
    "Skip phrases like 'image of' or 'picture of.' "
    "Your description should form a clear, well-structured, and factual paragraph that avoids bullet points, focusing on creating a seamless narrative."
)

# Check if an image has been uploaded and if the analyze button has been pressed
if uploaded_file is not None and analyze_button:

    with st.spinner("Analyzing the image ..."):
        # Encode the image
        base64_image = encode_image(uploaded_file)

        # Determine which prompt to use based on the complexity of the image
        if complex_image:
            prompt_text = complex_image_prompt_text
        else:
            prompt_text = (
                "As an expert in image accessibility and alternative text, succinctly describe the image provided in less than 125 characters. "
                "Provide a brief description using not more than 125 characters that conveys the essential information in three or fewer clear and concise sentences for use as alt text. "
                "Skip phrases like 'image of' or 'picture of.' "
                "Your description should form a clear, well-structured, and factual paragraph that avoids bullet points and newlines, focusing on creating a seamless narrative for accessibility purposes."
            )

        if show_details and additional_details:
            prompt_text += (
                f"\n\nInclude the additional context provided by the user in your description:\n{additional_details}"
            )

        # Create the payload for the completion request
        messages = [
            {
                "role": "user",
                "content": [
                    {"type": "text", "text": prompt_text},
                    {
                        "type": "image",
                        "image": {
                            # Provide the image bytes directly
                            "bytes": base64.b64decode(base64_image)
                        },
                    },
                ],
            }
        ]

        # Make the request to the Hugging Face API
        try:
            # Send the request to the model
            completion = client.chat_completions(
                model="meta-llama/Llama-3.2-11B-Vision-Instruct",
                messages=messages,
                max_new_tokens=1200
            )

            # Extract the assistant's response
            assistant_response = completion.get("choices")[0]["message"]["content"]

            # Display the response
            st.markdown(assistant_response)

            st.success('Powered by MTSS GPT. AI can make mistakes. Consider checking important information.')
        except Exception as e:
            st.error(f"An error occurred: {e}")
else:
    # Warning for user action required
    if not uploaded_file and analyze_button:
        st.warning("Please upload an image.")