Add languages, json. Fix 'here is your copy'

app.py

@@ -22,7 +22,7 @@ structure = \
 
 ## Features and Benefits
 {% for feature in features %}
-### Feature {{ loop.index }}: {{ feature.name | dynamic, direct, 5-6 words }}
+### {{ loop.index }}: {{ feature.name | dynamic, direct, 5-6 words }}
 {{ feature.details | energetic, clear, 3-4 sentences }}
 {% endfor %}
 
@@ -36,6 +36,24 @@ reference = " "
 
 garment_type = "all"
 
+languages = ["American English",
+             "British English",
+             "German",
+             "French",
+             "Chinese",
+             "Spanish",
+             "Dutch",
+             "Italian",
+             "Japanese",
+             "Polish",
+             "Portuguese"]
+
+models = ["gpt-4-turbo", 
+          "gpt-3.5-turbo", 
+          "claude-3-sonnet-20240229", 
+          "claude-3-opus-20240229", 
+          "llama3-70b-8192"]
+
 import base64
 import requests
 
@@ -61,7 +79,7 @@ def get_json(text: str):
     return json.loads(text)
 
 
-def detect_features(image_paths, garment_type):
+def detect_features(image_paths, garment_type, language):
     # Path to your image
     # image_path = "path_to_your_image.jpg"
 
@@ -87,13 +105,14 @@ def detect_features(image_paths, garment_type):
                 "text": """Describe the features of the %s in the photos in less than 100 words.
                 What is the intended use of the %s in this image, use at most 5 words for intended use?
                 Generate alt text for each of the images.
+                Make sure to output the alt text in %s language.
                 If the photo does not contain a garment, return 'No garment detected'.
                 If the photo contains a garment, return the result in in the following JSON format without any preceding or trailing text: 
                 {
                     "features": [list of comma separated features], 
                     "intended_use": [list of comma separated intended uses], 
                     "alt_text": [alt text for image 1, alt text for image 2]
-                }""" % (garment_type, garment_type)
+                }""" % (garment_type, garment_type, language)
                 },
             ] + [{
                 "type": "image_url",
@@ -119,9 +138,9 @@ def detect_features(image_paths, garment_type):
         return "", []
 
 
-def generate(features, image, garment_type, structure, reference, model, temperature):
-    print(f"features {features},\n image {image},\n structure{structure},\n model{model},\n temperature {temperature},\n reference {reference}")
-    image_features, base64_images = detect_features(image, garment_type)
+def generate(features, image, garment_type, structure, reference, model, language, output_types, temperature):
+    print(f"features {features},\n image {image},\n structure{structure},\n model{model},\n language{language},\n temperature {temperature},\n reference {reference}")
+    image_features, base64_images = detect_features(image, garment_type, language)
     detected_features = ""
     intended_use = ""
     alt_texts = []
@@ -136,40 +155,88 @@ def generate(features, image, garment_type, structure, reference, model, tempera
         chat = ChatAnthropic(model_name=model, anthropic_api_key=os.environ["ANTHROPIC_API_KEY"])
     else:
         chat = ChatGroq(model_name=model, api_key=os.environ["GROQ_API_KEY"])
-    messages = [HumanMessage(content=f"""Write a product description of about 200 words for a product with the following key properties. 
+    desc_messages = [
+        SystemMessage(content=f"""You are a helpful assistant that writes product descriptions for ecommerce websites. You write in {language} language."""),
+        HumanMessage(content=f"""Write a product description of about 200 words for a product with the following key properties. 
+                             Make sure that the description follows the structure of the reference structure below. 
+                             Make sure to use markdown format for the output.
+                             Make sure that the entire output is written entirely in {language} language. 
+                             Output the product description only, do not include any preceeding text like "Here is your product description".
+                             Use creative language that is suitable for e-commerce websites. Use a consistent tone of voice throughout the text. 
+                             If the reference text is not empty, produce the product description in the tone of voice and structure of the reference text. 
+                             \n\n {features + detected_features} \n{intended_use} \nReference structure: {structure}\n Reference text: {reference}""")]
+    news_messages = [
+        SystemMessage(content=f"""You are a helpful assistant that writes news letters for ecommerce websites. You write in {language} language."""),
+        HumanMessage(content=f"""Write a news letter of about 200 words for a product with the following key properties. 
                              Make sure that the description follows the structure of the reference structure below. 
                              Make sure to use markdown format for the output.
-                             Output the product description only.
+                             Make sure that the entire output is written entirely in {language} language. 
+                             Output the product description only, do not include any preceeding text like "Here is your product description".
                              Use creative language that is suitable for e-commerce websites. Use a consistent tone of voice throughout the text. 
                              If the reference text is not empty, produce the product description in the tone of voice and structure of the reference text. 
                              \n\n {features + detected_features} \n{intended_use} \nReference structure: {structure}\n Reference text: {reference}""")]
-    chat_response = chat.invoke(messages, temperature=temperature)
-    print(messages[0].content)
+    all_messages = [
+        SystemMessage(content=f"""You are a helpful assistant that writes news letters for ecommerce websites. You write in {language} language."""),
+        HumanMessage(content=f"""Write a news letter and a product description of about 200 words for a product with the following key properties. 
+                             Make sure that the description follows the structure of the reference structure below. 
+                             Make sure to use markdown format for the output.
+                             Make sure that the entire output is written entirely in {language} language. 
+                             Output the product description only, do not include any preceeding text like "Here is your product description".
+                             Use creative language that is suitable for e-commerce websites. Use a consistent tone of voice throughout the text. 
+                             If the reference text is not empty, produce the news letter and product description in the tone of voice and structure of the reference text. 
+                             Return the result in the following JSON format: {{"description": Product description, "news_letter": News letter}}.
+                             \n\n {features + detected_features} \n{intended_use} \nReference structure: {structure}\n Reference text: {reference}""")]
+
+    print(output_types)
+
+    description = ""
+    
+    print(all_messages[1].content)
+
+    response = chat.invoke(desc_messages, temperature=temperature)
+    description = response.content
+    md_content = description 
+
     alt_texts_str = '\n\n### Alt text\n\n' + '\n- ' + '\n- '.join(alt_texts) if len(alt_texts) > 0 else ""
-    result_text = chat_response.content
-    result_md = chat_response.content + alt_texts_str + '\n'.join([f'![Product photo](data:image/png;base64,{base64_image} "{alt_text}")' if base64_image != "" else "" for (base64_image, alt_text) in zip(base64_images, alt_texts)])
-    return result_md, result_text
+
+    alt_text_dict = {k[0]: v for (k, v) in zip(image, alt_texts)} if len(alt_texts) > 0 else {}
+    result_json = {"description": description, "alt_text": alt_text_dict, "language": language}
+    result_md = md_content + alt_texts_str + '\n'.join([f'![Product photo](data:image/png;base64,{base64_image} "{alt_text}")' if base64_image != "" else "" for (base64_image, alt_text) in zip(base64_images, alt_texts)])
+    return result_md, result_json
 
 
-demo = gr.Interface(
-    fn=generate,
-    inputs=[gr.Textbox(features, label="Features"), 
-            gr.Gallery(label="Product image(s)", type="filepath"), 
-            gr.Textbox(garment_type, label="Garment type"),
-            gr.Textbox(structure, label="Structure"), 
-            gr.Textbox(reference, label="Reference copy"),
-            gr.Dropdown(["gpt-4-turbo", "gpt-3.5-turbo", "claude-3-sonnet-20240229", "claude-3-opus-20240229", "llama3-70b-8192"], value="llama3-70b-8192", label="Model"),
-            gr.Slider(minimum=0., maximum=1.0, value=0.5, label="Temperature")],
-    outputs=[gr.Markdown(label="Markdown"), gr.Textbox(label="Raw text")],
-)
 
-# demo.launch()
 
-import argparse
+# demo = gr.Interface(
+#     fn=generate,
+#     inputs=[gr.Textbox(features, label="Features"), 
+#             gr.Gallery(label="Product image(s)", type="filepath"), 
+#             gr.Textbox(garment_type, label="Garment type"),
+#             gr.Textbox(structure, label="Structure"), 
+#             gr.Textbox(reference, label="Reference copy"),
+#             gr.Dropdown(["gpt-4-turbo", "gpt-3.5-turbo", "claude-3-sonnet-20240229", "claude-3-opus-20240229", "llama3-70b-8192"], value="llama3-70b-8192", label="Model"),
+#             gr.Slider(minimum=0., maximum=1.0, value=0.5, label="Temperature")],
+#     outputs=[gr.Markdown(label="Markdown"), gr.Textbox(label="Raw text")],
+# )
 
-parser = argparse.ArgumentParser(description='Run the Gradio demo')
-parser.add_argument('--public', action='store_true', help='Expose the demo to the public')
-args = parser.parse_args()
+with gr.Blocks() as demo:
+    inputs=[gr.Textbox(features, label="Features", lines=3, interactive=True), 
+            gr.Gallery(label="Product image(s)", type="filepath"), 
+            gr.Textbox(garment_type, label="Garment type"),
+            gr.Textbox(structure, label="Structure", lines=10, interactive=True), 
+            gr.Textbox(reference, label="Reference copy", lines=3, interactive=True),
+            gr.Dropdown(models, value="claude-3-sonnet-20240229", label="Model"),
+            gr.Dropdown(languages, label="Language", value="American English"),
+            gr.Slider(minimum=0., maximum=1.0, value=0.5, label="Temperature")]
+    outputs=[gr.Markdown(label="Markdown"), gr.JSON(label="JSON")]
+    submit_button = gr.Button("Submit")
+    submit_button.click(fn=generate, inputs=inputs, outputs=outputs)
+
+# import argparse
+
+# parser = argparse.ArgumentParser(description='Run the Gradio demo')
+# parser.add_argument('--public', action='store_true', help='Expose the demo to the public')
+# args = parser.parse_args()
 
 # if args.public:
 #     demo.launch(share=True)