Update app.py

app.py

@@ -26,60 +26,7 @@ def topk_candidates(query, candidates, k):
 
 def create_gradio_interface():
     with gr.Blocks(theme=gr.themes.Soft()) as demo:
-        gr.Markdown("""
-        # WordLlama Gradio Demo
         
-        **WordLlama** is a fast, lightweight NLP toolkit that handles tasks like fuzzy deduplication, similarity, and ranking with minimal inference-time dependencies and is optimized for CPU hardware.
-
-        For more details, visit the [WordLlama GitHub repository](https://github.com/dleemiller/WordLlama).
-
-        ## Examples
-
-        **Calculate Similarity**
-
-        ```python
-        from wordllama import WordLlama
-
-        # Load the default WordLlama model
-        wl = WordLlama.load()
-
-        # Calculate similarity between two sentences
-        similarity_score = wl.similarity("i went to the car", "i went to the pawn shop")
-        print(similarity_score)  # Output: 0.06641249096796882
-        ```
-
-        **Rank Documents**
-
-        ```python
-        query = "i went to the car"
-        candidates = ["i went to the park", "i went to the shop", "i went to the truck", "i went to the vehicle"]
-        ranked_docs = wl.rank(query, candidates)
-        print(ranked_docs)
-        # Output:
-        # [
-        #   ('i went to the vehicle', 0.7441646856486314),
-        #   ('i went to the truck', 0.2832691551894259),
-        #   ('i went to the shop', 0.19732814982305436),
-        #   ('i went to the park', 0.15101404519322253)
-        # ]
-        ```
-
-        **Additional Inference Methods**
-
-        ```python
-        # Fuzzy Deduplication
-        wl.deduplicate(candidates, threshold=0.8)
-
-        # Clustering with K-means
-        wl.cluster(docs, k=5, max_iterations=100, tolerance=1e-4)
-
-        # Filtering Candidates
-        wl.filter(query, candidates, threshold=0.3)
-
-        # Top-k Candidates
-        wl.topk(query, candidates, k=3)
-        ```
-        """)
 
         with gr.Tab("Similarity"):
             with gr.Row():
@@ -179,6 +126,61 @@ def create_gradio_interface():
                 inputs=[topk_query, candidates_topk, k],
             )
 
+        gr.Markdown("""
+        # WordLlama Gradio Demo
+        
+        **WordLlama** is a fast, lightweight NLP toolkit that handles tasks like fuzzy deduplication, similarity, and ranking with minimal inference-time dependencies and is optimized for CPU hardware.
+
+        For more details, visit the [WordLlama GitHub repository](https://github.com/dleemiller/WordLlama).
+
+        ## Examples
+
+        **Calculate Similarity**
+
+        ```python
+        from wordllama import WordLlama
+
+        # Load the default WordLlama model
+        wl = WordLlama.load()
+
+        # Calculate similarity between two sentences
+        similarity_score = wl.similarity("i went to the car", "i went to the pawn shop")
+        print(similarity_score)  # Output: 0.06641249096796882
+        ```
+
+        **Rank Documents**
+
+        ```python
+        query = "i went to the car"
+        candidates = ["i went to the park", "i went to the shop", "i went to the truck", "i went to the vehicle"]
+        ranked_docs = wl.rank(query, candidates)
+        print(ranked_docs)
+        # Output:
+        # [
+        #   ('i went to the vehicle', 0.7441646856486314),
+        #   ('i went to the truck', 0.2832691551894259),
+        #   ('i went to the shop', 0.19732814982305436),
+        #   ('i went to the park', 0.15101404519322253)
+        # ]
+        ```
+
+        **Additional Inference Methods**
+
+        ```python
+        # Fuzzy Deduplication
+        wl.deduplicate(candidates, threshold=0.8)
+
+        # Clustering with K-means
+        wl.cluster(docs, k=5, max_iterations=100, tolerance=1e-4)
+
+        # Filtering Candidates
+        wl.filter(query, candidates, threshold=0.3)
+
+        # Top-k Candidates
+        wl.topk(query, candidates, k=3)
+        ```
+        """)
+
     return demo
 
 # Create and launch the Gradio interface