Update app.py

app.py

@@ -91,28 +91,29 @@ if task_choice == "Data Generation":
     num_to_generate = st.number_input("How many examples to generate?", min_value=1, max_value=50, value=10)
 
     # System prompt generation
-    system_prompt = f"You are a professional {classification_type.lower()} expert. Your role is to generate data for {domain}.\n\n"
+    system_prompt = f"You are a professional {classification_type.lower()} expert. Your role is to generate {num_to_generate} data examples for {domain}. "
+    system_prompt += f"Each example should have a label and consist of between {min_words} and {max_words} words. "
+    system_prompt += "Use the following labels: " + ", ".join(labels) + ". "
+
     if few_shot_examples:
         system_prompt += "Use the following few-shot examples as a reference:\n"
         for example in few_shot_examples:
             system_prompt += f"Example: {example['content']}, Label: {example['label']}\n"
-    system_prompt += f"Each example should have between {min_words} and {max_words} words.\n"
-    system_prompt += "Think step by step while generating the examples."
+    
+    system_prompt += "Please only provide the examples in the following format:\n"
+    system_prompt += "Example: <text>, Label: <label>\n"
 
     st.write("System Prompt:")
     st.code(system_prompt)
 
     if st.button("Generate Examples"):
-        # Break generation into smaller chunks if needed to ensure enough examples
         all_generated_examples = []
         remaining_examples = num_to_generate
 
         with st.spinner("Generating..."):
             while remaining_examples > 0:
-                # Generating examples in chunks to avoid token limits
                 chunk_size = min(remaining_examples, 5)
                 try:
-                    # Append the new chunk system prompt
                     st.session_state.messages.append({"role": "system", "content": system_prompt})
 
                     stream = client.chat.completions.create(
@@ -126,9 +127,10 @@ if task_choice == "Data Generation":
                         max_tokens=3000,
                     )
 
-                    # Parse the response and break it into individual examples
                     response = st.write_stream(stream)
-                    generated_examples = response.split("\n")[:chunk_size]  # Assuming each example is on a new line
+
+                    # Split the response into individual examples, assuming each example starts with 'Example: '
+                    generated_examples = response.split("Example: ")[1:chunk_size+1]  # Extract up to the chunk size
 
                     # Store the new examples
                     all_generated_examples.extend(generated_examples)
@@ -141,7 +143,7 @@ if task_choice == "Data Generation":
 
         # Display all generated examples
         for idx, example in enumerate(all_generated_examples):
-            st.write(f"Example {idx+1}: {example}")
+            st.write(f"Example {idx+1}: {example.strip()}")
 
         # Update session state to prevent repetition of old prompts
         st.session_state.messages = []  # Clear messages after each generation