File size: 12,776 Bytes
3c5c8af
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f76d77f
 
e47c925
ea6a4e1
f76d77f
 
 
 
 
7964be8
 
a507e51
9622677
 
 
8ec3355
9622677
85f9ce0
6ebac3b
8ec3355
 
 
 
9622677
 
 
7c39bed
 
506b62a
3c5c8af
 
a2d596c
9622677
 
 
 
506b62a
9622677
 
 
a009ec6
4996d49
9622677
a2d596c
9622677
 
a2d596c
 
9622677
 
 
 
 
 
 
 
 
dd32d54
a009ec6
9622677
a009ec6
9622677
 
 
 
 
 
 
a009ec6
9622677
 
a009ec6
9622677
 
a009ec6
 
9622677
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a009ec6
9622677
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
506b62a
9622677
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8ec3355
9622677
 
 
 
 
 
3c5c8af
a009ec6
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
# import streamlit as st
# import base64
# import openai 

# # 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="collapsed")

# #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.title('MTSS:grey[.ai]')
# st.header('VisionText™ | Accessibility')
# st.subheader(':green[_Image Alt Text Generator_]')

# # Retrieve the OpenAI API Key from secrets
# openai.api_key = st.secrets["openai_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 with specified width
#     image_width = 100  # 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.toggle("Add details about the image. ", value=False)

# if show_details:
#     # Text input for additional details about the image, shown only if toggle is True
#     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.toggle("Is this a complex image? ", value=False)

# if complex_image:
#     # Text input for additional details about the image, shown only if toggle is True
#     complex_image_details = st.caption(
#         "By clicking this toggle, it will inform MTSS.ai 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 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, if the API key is available, and if the 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 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\nAdditional Context Provided by the User:\n{additional_details}"
#             )

    
#         # Create the payload for the completion request
#         messages = [
#             {
#                 "role": "user",
#                 "content": [
#                     {"type": "text", "text": prompt_text},
#                     {
#                         "type": "image_url",
#                         "image_url": f"data:image/jpeg;base64,{base64_image}",
#                     },
#                 ],
#             }
#         ]
    
#         # Make the request to the OpenAI API
#         try:
#             # Without Stream
            
#             # response = openai.chat.completions.create(
#             #     model="gpt-4-vision-preview", messages=messages, max_tokens=250, stream=False
#             # )
    
#             # Stream the response
#             full_response = ""
#             message_placeholder = st.empty()
#             for completion in openai.chat.completions.create(
#                 model="gpt-4-vision-preview", messages=messages, 
#                 max_tokens=250, stream=True
#             ):
#             #     # Check if there is content to display
#             #     if completion.choices[0].delta.content is not None:
#             #         full_response += completion.choices[0].delta.content
#             #         message_placeholder.markdown(full_response + "▌")
#             # # Final update to placeholder after the stream ends
#             # message_placeholder.markdown(full_response) # stream text
            
#                 # Check if there is content to display
#                 if completion.choices[0].delta.content is not None:
#                     full_response += completion.choices[0].delta.content

#             # Display the response in a text area
#             st.text_area('Response:', value=full_response, height=250, key="response_text_area")
            
#             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:
#     # Warnings for user action required
#     if not uploaded_file and analyze_button:
#         st.warning("Please upload an image.")



import streamlit as st
import base64
import openai 

# 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")
# initial_sidebar_state ("auto" or "expanded" or "collapsed")

#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.title('MTSS:grey[.ai]')
st.header('VisionText™ | Accessibility')
st.subheader(':green[_Image Alt Text Generator_]')

# Retrieve the OpenAI API Key from secrets
openai.api_key = st.secrets["openai_api_key"]

# File uploader allows user to add their own image
# uploaded_file = st.file_uploader("Upload an image", type=["jpg", "png", "jpeg"])

# st.write("Please upload an image in the sidebar.")
st.markdown("<span style='color:green; font-weight:bold;'>Please upload an image in the left sidebar.</span>", unsafe_allow_html=True)

# Move the file uploader to the sidebar
uploaded_file = st.sidebar.file_uploader("Upload an image", type=["jpg", "png", "jpeg"])

if uploaded_file:
    # Display the uploaded image with specified width
    image_width = 100  # Set the desired width in pixels
    with st.expander("Image", expanded=True):
        st.sidebar.image(uploaded_file, caption=uploaded_file.name, width=image_width, use_column_width=False)

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

if show_details:
    # Text input for additional details about the image, shown only if toggle is True
    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.toggle("Is this a complex image? ", value=False)

if complex_image:
    # Text input for additional details about the image, shown only if toggle is True
    complex_image_details = st.caption(
        "By clicking this toggle, it will inform MTSS.ai 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 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, if the API key is available, and if the 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 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\nAdditional Context Provided by the User:\n{additional_details}"
            )

    
        # Create the payload for the completion request
        messages = [
            {
                "role": "user",
                "content": [
                    {"type": "text", "text": prompt_text},
                    {
                        "type": "image_url",
                        "image_url": f"data:image/jpeg;base64,{base64_image}",
                    },
                ],
            }
        ]
    
        # Make the request to the OpenAI API
        try:
            # Without Stream
            
            # response = openai.chat.completions.create(
            #     model="gpt-4-vision-preview", messages=messages, max_tokens=250, stream=False
            # )
    
            # Stream the response
            full_response = ""
            message_placeholder = st.empty()
            for completion in openai.chat.completions.create(
                model="gpt-4-vision-preview", messages=messages, 
                max_tokens=1200, stream=True
            ):
                # Check if there is content to display
                if completion.choices[0].delta.content is not None:
                    full_response += completion.choices[0].delta.content
                    message_placeholder.markdown(full_response + "▌")
            # Final update to placeholder after the stream ends
            message_placeholder.markdown(full_response)

            # # Display the response in a text area
            # st.text_area('Response:', value=full_response, height=250, key="response_text_area")
            
            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:
    # Warnings for user action required
    if not uploaded_file and analyze_button:
        st.warning("Please upload an image.")