Update app.py

app.py

@@ -42,84 +42,206 @@ def process_nlp(system_message):
     colorized_text = colorize_text(system_message['content'])
     return colorized_text
 
+# # define color combinations for different parts of speech
+# COLORS = {
+#     "NOUN": "#5e5e5e",  # Dark gray
+#     "VERB": "#ff6936",  # Orange
+#     "ADJ": "#4363d8",   # Blue
+#     "ADV": "#228b22",   # Green
+#     "digit": "#9a45d6", # Purple
+#     "punct": "#ffcc00", # Yellow
+#     "quote": "#b300b3"  # Magenta
+# }
+
+# # define color combinations for individuals with dyslexia
+# DYSLEXIA_COLORS = {
+#     "NOUN": "#5e5e5e",
+#     "VERB": "#ff6936",
+#     "ADJ": "#4363d8",
+#     "ADV": "#228b22",
+#     "digit": "#9a45d6",
+#     "punct": "#ffcc00",
+#     "quote": "#b300b3"
+# }
+
+# # define a muted background color
+# BACKGROUND_COLOR = "#f5f5f5"  # Light gray
+
+# # define font and size
+# FONT = "Arial"
+# FONT_SIZE = "14px"
+
+# # load the English language model
+# nlp = spacy.load('en_core_web_sm')
+
+# def colorize_text(text, colors=DYSLEXIA_COLORS, background_color=None):
+#     if colors is None:
+#         colors = COLORS
+#     colorized_text = ""
+#     lines = text.split("\n")
+    
+#     # set background color
+#     if background_color is None:
+#         background_color = BACKGROUND_COLOR
+    
+#     # iterate over the lines in the text
+#     for line in lines:
+#         # parse the line with the language model
+#         doc = nlp(line)
+#         # iterate over the tokens in the line
+#         for token in doc:
+#             # check if the token is an entity
+#             if token.ent_type_:
+#                 # use dyslexia colors for entity if available
+#                 if colors == COLORS:
+#                     color = DYSLEXIA_COLORS.get(token.pos_, None)
+#                 else:
+#                     color = colors.get(token.pos_, None)
+#                 # check if a color is available for the token
+#                 if color is not None:
+#                     colorized_text += (
+#                         f'<span style="color: {color}; '
+#                         f'background-color: {background_color}; '
+#                         f'font-family: {FONT}; '
+#                         f'font-size: {FONT_SIZE}; '
+#                         f'font-weight: bold; '
+#                         f'text-decoration: none; '
+#                         f'padding-right: 0.5em;">'  # Add space between tokens
+#                         f"{token.text}</span>"
+#                     )
+#                 else:
+#                     colorized_text += (
+#                         f'<span style="font-family: {FONT}; '
+#                         f'font-size: {FONT_SIZE}; '
+#                         f'font-weight: bold; '
+#                         f'text-decoration: none; '
+#                         f'padding-right: 0.5em;">'  # Add space between tokens
+#                         f"{token.text}</span>"
+#                     )
+#             else:
+#                 # check if a color is available for the token
+#                 color = colors.get(token.pos_, None)
+#                 if color is not None:
+#                     colorized_text += (
+#                         f'<span style="color: {color}; '
+#                         f'background-color: {background_color}; '
+#                         f'font-family: {FONT}; '
+#                         f'font-size: {FONT_SIZE}; '
+#                         f'font-weight: bold; '
+#                         f'text-decoration: none; '
+#                         f'padding-right: 0.5em;">'  # Add space between tokens
+#                         f"{token.text}</span>"
+#                     )
+#                 elif token.is_digit:
+#                     colorized_text += (
+#                         f'<span style="color: {colors["digit"]}; '
+#                         f'background-color: {background_color}; '
+#                         f'font-family: {FONT}; '
+#                         f'font-size: {FONT_SIZE}; '
+#                         f'font-weight: bold; '
+#                         f'text-decoration: none; '
+#                         f'padding-right: 0.5em;">'  # Add space between tokens
+#                         f"{token.text}</span>"
+#                     )
+#                 elif token.is_punct:
+#                     colorized_text += (
+#                         f'<span style="color: {colors["punct"]}; '
+#                         f'background-color: {background_color}; '
+#                         f'font-family: {FONT}; '
+#                         f'font-size: {FONT_SIZE}; '
+#                         f'font-weight: bold; '
+#                         f'text-decoration: none; '
+#                         f'padding-right: 0.5em;">'  # Add space between tokens
+#                         f"{token.text}</span>"
+#                     )
+#                 elif token.is_quote:
+#                     colorized_text += (
+#                         f'<span style="color: {colors["quote"]}; '
+#                         f'background-color: {background_color}; '
+#                         f'font-family: {FONT}; '
+#                         f'font-size: {FONT_SIZE}; '
+#                         f'text-decoration: none; '
+#                         f'padding-right: 0.5em;">'  # Add space between tokens
+#                         f"{token.text}</span>"
+#                     )
+#                 else:
+#                     colorized_text += (
+#                         f'<span style="font-family: {FONT}; '
+#                         f'font-size: {FONT_SIZE}; '
+#                         f'font-weight: bold; '
+#                         f'text-decoration: none; '
+#                         f'padding-right: 0.5em;">'  # Add space between tokens
+#                         f"{token.text}</span>"
+#                     )
+#         colorized_text += "<br>"
+    
+#     return colorized_text
+
 # define color combinations for different parts of speech
 COLORS = {
-    "NOUN": "#5e5e5e",  # Dark gray
-    "VERB": "#ff6936",  # Orange
-    "ADJ": "#4363d8",   # Blue
-    "ADV": "#228b22",   # Green
-    "digit": "#9a45d6", # Purple
-    "punct": "#ffcc00", # Yellow
-    "quote": "#b300b3"  # Magenta
+    "NOUN": "#FF3300",
+    "VERB": "#008000",
+    "ADJ": "#1E90FF",
+    "ADV": "#FF8C00",
+    "digit": "#FF1493",
+    "punct": "#8B0000",
+    "quote": "#800080",
 }
 
 # define color combinations for individuals with dyslexia
 DYSLEXIA_COLORS = {
-    "NOUN": "#5e5e5e",
-    "VERB": "#ff6936",
-    "ADJ": "#4363d8",
-    "ADV": "#228b22",
-    "digit": "#9a45d6",
-    "punct": "#ffcc00",
-    "quote": "#b300b3"
+    "NOUN": "#1E90FF",
+    "VERB": "#006400",
+    "ADJ": "#00CED1",
+    "ADV": "#FF8C00",
+    "digit": "#FF1493",
+    "punct": "#A0522D",
+    "quote": "#800080",
 }
 
 # define a muted background color
-BACKGROUND_COLOR = "#f5f5f5"  # Light gray
+BACKGROUND_COLOR = "#EAEAEA"
 
 # define font and size
-FONT = "Arial"
-FONT_SIZE = "14px"
-
-# load the English language model
-nlp = spacy.load('en_core_web_sm')
+FONT = "Georgia"
+FONT_SIZE = "18px"
 
-def colorize_text(text, colors=DYSLEXIA_COLORS, background_color=None):
+def colorize_text(text, colors=None, background_color=None):
     if colors is None:
         colors = COLORS
     colorized_text = ""
     lines = text.split("\n")
-    
+
     # set background color
     if background_color is None:
         background_color = BACKGROUND_COLOR
-    
-    # iterate over the lines in the text
+
     for line in lines:
-        # parse the line with the language model
         doc = nlp(line)
-        # iterate over the tokens in the line
         for token in doc:
-            # check if the token is an entity
             if token.ent_type_:
                 # use dyslexia colors for entity if available
                 if colors == COLORS:
                     color = DYSLEXIA_COLORS.get(token.pos_, None)
                 else:
                     color = colors.get(token.pos_, None)
-                # check if a color is available for the token
                 if color is not None:
                     colorized_text += (
                         f'<span style="color: {color}; '
                         f'background-color: {background_color}; '
                         f'font-family: {FONT}; '
                         f'font-size: {FONT_SIZE}; '
-                        f'font-weight: bold; '
-                        f'text-decoration: none; '
-                        f'padding-right: 0.5em;">'  # Add space between tokens
+                        f'text-decoration: underline;">'
                         f"{token.text}</span>"
                     )
                 else:
                     colorized_text += (
                         f'<span style="font-family: {FONT}; '
                         f'font-size: {FONT_SIZE}; '
-                        f'font-weight: bold; '
-                        f'text-decoration: none; '
-                        f'padding-right: 0.5em;">'  # Add space between tokens
+                        f'text-decoration: underline;">'
                         f"{token.text}</span>"
                     )
             else:
-                # check if a color is available for the token
                 color = colors.get(token.pos_, None)
                 if color is not None:
                     colorized_text += (
@@ -127,9 +249,7 @@ def colorize_text(text, colors=DYSLEXIA_COLORS, background_color=None):
                         f'background-color: {background_color}; '
                         f'font-family: {FONT}; '
                         f'font-size: {FONT_SIZE}; '
-                        f'font-weight: bold; '
-                        f'text-decoration: none; '
-                        f'padding-right: 0.5em;">'  # Add space between tokens
+                        f'text-decoration: underline;">'
                         f"{token.text}</span>"
                     )
                 elif token.is_digit:
@@ -138,9 +258,7 @@ def colorize_text(text, colors=DYSLEXIA_COLORS, background_color=None):
                         f'background-color: {background_color}; '
                         f'font-family: {FONT}; '
                         f'font-size: {FONT_SIZE}; '
-                        f'font-weight: bold; '
-                        f'text-decoration: none; '
-                        f'padding-right: 0.5em;">'  # Add space between tokens
+                        f'text-decoration: underline;">'
                         f"{token.text}</span>"
                     )
                 elif token.is_punct:
@@ -149,9 +267,7 @@ def colorize_text(text, colors=DYSLEXIA_COLORS, background_color=None):
                         f'background-color: {background_color}; '
                         f'font-family: {FONT}; '
                         f'font-size: {FONT_SIZE}; '
-                        f'font-weight: bold; '
-                        f'text-decoration: none; '
-                        f'padding-right: 0.5em;">'  # Add space between tokens
+                        f'text-decoration: underline;">'
                         f"{token.text}</span>"
                     )
                 elif token.is_quote:
@@ -160,25 +276,20 @@ def colorize_text(text, colors=DYSLEXIA_COLORS, background_color=None):
                         f'background-color: {background_color}; '
                         f'font-family: {FONT}; '
                         f'font-size: {FONT_SIZE}; '
-                        f'text-decoration: none; '
-                        f'padding-right: 0.5em;">'  # Add space between tokens
+                        f'text-decoration: underline;">'
                         f"{token.text}</span>"
                     )
                 else:
                     colorized_text += (
                         f'<span style="font-family: {FONT}; '
                         f'font-size: {FONT_SIZE}; '
-                        f'font-weight: bold; '
-                        f'text-decoration: none; '
-                        f'padding-right: 0.5em;">'  # Add space between tokens
+                        f'text-decoration: underline;">'
                         f"{token.text}</span>"
                     )
+            colorized_text += " "
         colorized_text += "<br>"
-    
     return colorized_text
 
-
-
 # def colorize_text(text):
 #     colorized_text = ""
 #     lines = text.split("\n")
@@ -300,7 +411,7 @@ def transcribe(audio, text, submit_update=None):
     with concurrent.futures.ThreadPoolExecutor() as executor:
         prompt = [{"text": f"{message['role']}: {message['content']}\n\n"} for message in messages]
         system_message = openai.ChatCompletion.create(
-            model="gpt-3.5-turbo",
+            model="gpt-4",
             messages=messages,
             max_tokens=2000
         )["choices"][0]["message"]