Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import requests | |
| # Hugging Face API setup | |
| API_URL = "https://api-inference.huggingface.co/models/meta-llama/Llama-3.2-11B-Vision-Instruct" | |
| headers = {"Authorization": f"Bearer {st.secrets['huggingface_api_key']}"} | |
| # Function to query the model | |
| def query_image(image_data, prompt_text): | |
| # Prepare the payload | |
| payload = { | |
| "inputs": { | |
| "image": image_data, | |
| "text": prompt_text | |
| } | |
| } | |
| response = requests.post(API_URL, headers=headers, json=payload) | |
| return response.json() | |
| # 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 # Desired width in pixels | |
| st.image('MTSS.ai_Logo.png', width=image_width) | |
| st.header('VisionTexts™ | Accessibility') | |
| st.subheader('Image Alt Text Creator') | |
| # File uploader | |
| uploaded_file = st.file_uploader("Upload an image", type=["jpg", "png", "jpeg"]) | |
| if uploaded_file: | |
| # Display the uploaded image | |
| image_width = 200 # 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( | |
| "Include specific information important for the alt text or reflect why the image is being used:" | |
| ) | |
| # Toggle for modifying the prompt for complex images | |
| complex_image = st.checkbox("Is this a complex image?", value=False) | |
| if complex_image: | |
| st.caption( | |
| "By selecting this, the app will create a description exceeding 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") | |
| # 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 convey the essential information conveyed by the image 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 button has been pressed | |
| if uploaded_file is not None and analyze_button: | |
| with st.spinner("Analyzing the image ..."): | |
| # Read the image file | |
| image_bytes = uploaded_file.read() | |
| # 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 convey the essential information conveyed by the image 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 that serves as effective alternative text 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}" | |
| ) | |
| # Query the model | |
| try: | |
| response = query_image(image_bytes, prompt_text) | |
| # Extract the generated text from the response | |
| if isinstance(response, dict) and 'generated_text' in response: | |
| alt_text = response['generated_text'] | |
| elif isinstance(response, list) and 'generated_text' in response[0]: | |
| alt_text = response[0]['generated_text'] | |
| else: | |
| alt_text = "No description generated." | |
| # Display the generated alt text | |
| st.markdown(f"**Generated Alt Text:** {alt_text}") | |
| 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.") |