Update app.py

app.py

@@ -41,14 +41,28 @@ def calculate_distances(embeddings, query_embedding, metric):
         distances = -dot_similarity(embeddings, [query_embedding])  # Negated for consistency with other metrics
     return distances.flatten()
 
+def wrap_text(text, width=40):
+    """
+    Inserts HTML line breaks for Plotly hover text.
+    :param text: The text to wrap.
+    :param width: The maximum line width before wrapping.
+    :return: Text with line breaks inserted.
+    """
+    wrapped_text = '<br>'.join([text[i:i+width] for i in range(0, len(text), width)])
+    return wrapped_text
+
 def generate_plotly_figure(query, pdf_file, metric):
     logging.info("Generating plot with Plotly.")
     query_embedding = model.encode([query])[0]
     text = process_pdf(pdf_file.name)
     embeddings, sentences = create_embeddings(text)
+    
+    # Wrap text for each sentence
+    sentences_wrapped = [wrap_text(sentence) for sentence in sentences]
+    all_sentences_wrapped = sentences_wrapped + [wrap_text(query)]  # Apply wrapping to the query as well
+    
     all_embeddings = np.vstack([embeddings, query_embedding])
-    all_sentences = sentences + [query]
-
+    
     umap_transform = umap.UMAP(n_neighbors=15, min_dist=0.0, n_components=2, random_state=42)
     umap_embeddings = umap_transform.fit_transform(all_embeddings)
     
@@ -59,10 +73,10 @@ def generate_plotly_figure(query, pdf_file, metric):
     colors.append('red')  # For the query
     
     fig = go.Figure(data=go.Scatter(x=umap_embeddings[:-1, 0], y=umap_embeddings[:-1, 1], mode='markers',
-                                    marker=dict(color=colors[:-1]), text=all_sentences[:-1],
-                                    name='Sentences'))
+                                    marker=dict(color=colors[:-1]), text=all_sentences_wrapped[:-1],
+                                    name='Sentences', hoverinfo='text'))
     fig.add_trace(go.Scatter(x=[umap_embeddings[-1, 0]], y=[umap_embeddings[-1, 1]], mode='markers',
-                             marker=dict(color='red'), text=[query], name='Query'))
+                             marker=dict(color='red'), text=[all_sentences_wrapped[-1]], name='Query', hoverinfo='text'))
     fig.update_layout(title="UMAP Projection of Sentences with Query Highlight", xaxis_title="UMAP 1", yaxis_title="UMAP 2")
     
     logging.info("Plotly figure created successfully.")
@@ -82,7 +96,7 @@ iface = gr.Interface(
         gr.Radio(choices=["cosine", "euclidean", "manhattan", "dot"], label="Distance Metric")
     ],
     outputs=gr.Plot(),
-    title="PDF Content Visualizer",
+    title="Semantic Search Visualizer",
     description="""This tool allows you to upload a PDF document, input a query, and visualize the context of the document 
     as it relates to your query. It uses UMAP for dimensionality reduction and highlights the query and its closest contexts 
     within the document based on the selected distance metric. Choose from cosine, Euclidean, Manhattan, or dot product metrics