New claude-3-5-sonnet-20241022 model. Add prompt to improve structure following capability

app.py

@@ -89,6 +89,7 @@ models = ["gpt-4-turbo",
           "claude-3-sonnet-20240229", 
           "claude-3-opus-20240229", 
           "claude-3-5-sonnet-20240620",
+          "claude-3-5-sonnet-20241022",
           "gemini-1.5-pro"
           #"llama3-70b-8192",
           ]
@@ -235,9 +236,10 @@ def get_language(struct_lang, copy_lang):
 
 def post_process(text):
     # text = text.strip().replace('<br>', '  ')
-    with open(f"postprocess_{time.time()}.txt", "w") as f:
-        f.write(text)
-    return text
+    # with open(f"postprocess_{time.time()}.txt", "w") as f:
+    #     f.write(text)
+    # return text
+    return text  
 
 
 def get_model(model_name, temperature=0.0):
@@ -364,7 +366,7 @@ def generate(*data):
                     HumanMessage(content=f"""Generate {nversions} versions of the product description for a product with the following information.
 Write in a way that target the customer.
 For each version, write at least {min_length} words and at most {max_length} words.
-Make sure that the structure of each output follows the reference structure.
+Make sure that the structure of each output follows the reference structure. Do not add any additional sentences or structures that are not in the reference structure.
 Make sure to use the tone of voice, rythm, cadence and style of the reference copy for each output.
 Use markdown format for each output.
 Do not include any part of the reference structure in the output.
@@ -378,7 +380,7 @@ Avoid common phrases and cliches such as "Step into something", "Elevate somethi
 For each version, try to write in different style.
 Put each item in the list on a separate line.  
 Rate the quality of each version based on the following criteria:
-    - how well it follows the reference structure.
+    - how well it follows the reference structure. 
     - how well it follows the tone of voice, rythm, cadence and style of the reference copy.
     - how faithful it describes the product features. 
     - how well it avoid the excluded words.                                 
@@ -493,7 +495,7 @@ Excluded words: {excluded_words}"""),]
                     HumanMessage(content=f"""Generate {nversions} versions of the product description for a product with the following information.
 Write in a way that target the customer.  
 For each version, write at least {min_length} words and at most {max_length} words.
-Make sure that the structure of each output follows the reference structure.
+Make sure that the structure of each output follows the reference structure. Do not add any additional sentences or structures that are not in the reference structure.
 Use markdown format for each output.
 Do not include any part of the reference structure in the output.
 Make sure that the structure of each output follows the reference structure.
@@ -505,7 +507,7 @@ Avoid common phrases and cliches such as "Step into something", "Elevate somethi
 For each version, try to write in different style.
 Put each item in the list on a separate line.  
 Rate the quality of each version based on the following criteria:
-    - how well it follows the reference structure.
+    - how well it follows the reference structure. 
     - how faithful it describes the product features. 
     - how well it avoid the excluded words.                                 
     - how well it includes the included words.                                 
@@ -644,7 +646,7 @@ with gr.Blocks() as demo:
             garment_type = gr.Textbox(label="Garment Type", value="all", lines=1, interactive=True) 
             # language = gr.Dropdown(languages, value="American English", interactive=True, label="Language")
             with gr.Accordion(label="Advanced Options", open=False):
-                model = gr.Dropdown(models, value="claude-3-5-sonnet-20240620", interactive=True, label="Model", visible=True)
+                model = gr.Dropdown(models, value="claude-3-5-sonnet-20241022", interactive=True, label="Model", visible=True)
                 temperature = gr.Slider(minimum=0., maximum=1.0, value=0., interactive=True, label="Temperature", visible=True)
                 nversions = gr.Slider(minimum=1, maximum=10, value=5, step=int, interactive=True, label="Number of versions", visible=True)
                 excluded_words = gr.Textbox(label="Excluded words", interactive=True, lines=2)
@@ -670,7 +672,7 @@ with gr.Blocks() as demo:
                 add_output.click(add_output_click, inputs=struct_ref, outputs=struct_ref)
                 remove_output.click(remove_output_click, inputs=struct_ref, outputs=struct_ref)
         with gr.Column():
-            md_output = gr.Markdown(label="Output", show_label=True)
+            md_output = gr.Markdown(label="Output", show_label=True, line_breaks=True)
             json_output = gr.JSON(label="JSON Output")  
         submit.click(generate, inputs=[feature, image, garment_type, model, temperature, nversions,
                                        excluded_words, included_words, glossary_upload, debug, *struct_ref],