Update app.py

app.py

@@ -80,7 +80,7 @@ MAX_CATEGORIES = 8
 with gr.Blocks(title="Historical Text Analyser", css=".prose { word-break: break-word; }") as demo:
     gr.Markdown("# Historical Text Analyser")
     gr.Markdown("""
-        First, a **Conceptual AI**, powered by a generative AI Large Language Model (LLM) such as OpenAI's GPT-4, Anthropic's Claude, or Google's Gemini, suggests labels based on your chosen historical topic. These labels are grouped into broader categories (e.g. Economic Policies, Significant Events) to help focus your research. 
+        First, a **Conceptual AI**, powered by a generative AI Large Language Model (LLM) such as OpenAI's GPT-4, Anthropic's Claude, or Google's Gemini, suggests labels based on your chosen historical topic. These labels are grouped into broader categories (e.g. Economic Policies, Significant Events) to help focus your research.
         Second, an **Extraction AI**, powered by the GLiNER model, scans your source text to find and highlight matching entities - instances where those labels appear in the document - with high accuracy.
         ### Understanding Entities and Labels ###
         In text analysis, this process is often called Named Entity Recognition (NER).
@@ -91,7 +91,7 @@ with gr.Blocks(title="Historical Text Analyser", css=".prose { word-break: break
     
     gr.Markdown("--- \n## Step 1: Generate Labels")
     with gr.Row():
-        topic = gr.Textbox(label="Enter a Historical Topic", info="e.g. Second World War, Victorian women, Chartism", placeholder="e.g. Britain during the Second World War")
+        topic = gr.Textbox(label="Enter a Historical Topic", placeholder="e.g. Britain during the Second World War")
         provider = gr.Dropdown(choices=list(MODEL_OPTIONS.keys()), label="Choose AI Model")
     with gr.Row():
         openai_key = gr.Textbox(label="OpenAI API Key", type="password")