Update app.py

app.py

@@ -1,40 +1,43 @@
 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()
+from transformers import pipeline
+from huggingface_hub import InferenceClient
+from PIL import Image
+import base64
 
 # 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
+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')
 
-# File uploader
+# Retrieve the Hugging Face API Key from secrets
+huggingface_api_key = st.secrets["huggingface_api_key"]
+
+# Initialize the image captioning pipeline
+image_captioner = pipeline(
+    "image-to-text",
+    model="Salesforce/blip-image-captioning-large",
+    use_auth_token=huggingface_api_key
+)
+
+# Initialize the language model client
+client = InferenceClient(token=huggingface_api_key)
+
+# File uploader allows user to add their own image
 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
+    image = Image.open(uploaded_file)
+    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)
+        st.image(image, caption=uploaded_file.name, width=image_width, use_column_width=False)
+else:
+    st.warning("Please upload an image.")
 
 # Toggle for showing additional details input
 show_details = st.checkbox("Add details about the image.", value=False)
@@ -42,70 +45,77 @@ 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:"
+        "The details could include specific information that is important to include in the alt text or reflect why the image is being used:"
     )
+else:
+    additional_details = ""
 
 # 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")
+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 convey the essential information conveyed by the image in eight or fewer clear and concise sentences. "
+    "As an expert in image accessibility and alternative text, thoroughly describe the image caption 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 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()
+    with st.spinner("Analyzing the image..."):
+        # Get the caption from the image using the image captioning model
+        caption_response = image_captioner(image)
+        image_caption = caption_response[0]['generated_text']
 
         # 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. "
+                "As an expert in image accessibility and alternative text, succinctly describe the image caption 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 that serves as effective alternative text for accessibility purposes."
+                "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}"
-            )
+        # Include additional details if provided
+        if additional_details:
+            prompt_text += f"\n\nInclude the additional context provided by the user in your description:\n{additional_details}"
+
+        # Create the prompt for the language model
+        full_prompt = f"{prompt_text}\n\nImage Caption: {image_caption}"
+
+        # Prepare messages for chat interface
+        messages = [
+            {"role": "user", "content": full_prompt}
+        ]
 
-        # Query the model
+        # Use the language model to generate the alt text description
         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}")
+            # Stream the response from the language model
+            stream = client.chat(
+                model="meta-llama/Llama-2-7b-chat-hf",
+                messages=messages,
+                stream=True
+            )
+
+            # Stream the response
+            full_response = ""
+            message_placeholder = st.empty()
+            for chunk in stream:
+                if 'generated_text' in chunk:
+                    content = chunk['generated_text']
+                    full_response += content
+                    message_placeholder.markdown(full_response + "▌")
+            # Final update after stream ends
+            message_placeholder.markdown(full_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.")
+    st.write("Please upload an image and click 'Analyze the Image' to generate alt text.")