Update app.py

app.py

@@ -81,9 +81,8 @@ def highlight_matching_words(text: str, query: str) -> str:
             highlighted.append(token)
     return ''.join(highlighted)
 
-def find_similar(query: str, books: List[str], limit: int = 50) -> List[Dict[str, Any]]:
+def find_similar(query: str, books: List[str], limit: int = 50, search_method: str = "vector") -> List[Dict[str, Any]]:
     try:
-        query_vector = model.encode([query])[0]
         client = weaviate.connect_to_weaviate_cloud(
             cluster_url=WEAVIATE_URL,
             auth_credentials=Auth.api_key(WEAVIATE_API_KEY),
@@ -94,15 +93,42 @@ def find_similar(query: str, books: List[str], limit: int = 50) -> List[Dict[str
             if books:
                 selected_books = [VULGATE_BOOKS[book] for book in books]
                 filter_condition = Filter.by_property("book").contains_any(selected_books)
-            response = vulgate.query.near_vector(
-                near_vector=query_vector,
-                limit=limit,
-                return_metadata=MetadataQuery(distance=True),
-                filters=filter_condition
-            )
+
+            # Always encode the query vector since we need it for both vector and hybrid search
+            query_vector = model.encode([query])[0]
+
+            if search_method == "vector":
+                response = vulgate.query.near_vector(
+                    near_vector=query_vector,
+                    limit=limit,
+                    return_metadata=MetadataQuery(distance=True),
+                    filters=filter_condition
+                )
+            elif search_method == "bm25":
+                response = vulgate.query.bm25(
+                    query=query,
+                    limit=limit,
+                    filters=filter_condition
+                )
+            else:  # hybrid
+                response = vulgate.query.hybrid(
+                    query=query,
+                    vector=query_vector,
+                    limit=limit,
+                    filters=filter_condition
+                )
+
             results = []
             for obj in response.objects:
                 highlighted_text = highlight_matching_words(obj.properties["text"], query)
+                
+                # Handle different types of scores
+                similarity = 1.0  # default value
+                if hasattr(obj.metadata, 'distance') and obj.metadata.distance is not None:
+                    similarity = 1 - obj.metadata.distance
+                elif hasattr(obj.metadata, 'score') and obj.metadata.score is not None:
+                    similarity = obj.metadata.score
+                
                 results.append({
                     "Reference": f"{obj.properties['book']} {obj.properties['chapter']}:{obj.properties['verse']}",
                     "Book": obj.properties["book"],
@@ -110,7 +136,7 @@ def find_similar(query: str, books: List[str], limit: int = 50) -> List[Dict[str
                     "Verse": obj.properties["verse"],
                     "Text": highlighted_text,
                     "RawText": obj.properties["text"],
-                    "Similarity": round(1 - obj.metadata.distance, 3)
+                    "Similarity": round(similarity, 3)
                 })
             return results
         finally:
@@ -124,7 +150,18 @@ def format_results_html(results: List[Dict[str, Any]]) -> str:
     if "Error" in results[0]:
         return f'<div style="color:red">Error: {results[0]["Error"]}</div>'
     html = [
-        '<style>td,th{padding:8px;}th{background:#f4f1e9;}tr:nth-child(even){background:#f9f9f9;}tr:hover{background:#e6e2d3;}table{border-radius:8px;overflow:hidden;box-shadow:0 2px 8px #e6e2d3;}td{vertical-align:top;}</style>',
+        '<style>',
+        '/* Light mode styles */',
+        'td,th{padding:8px;}th{background:#f4f1e9;}tr:nth-child(even){background:#f9f9f9;}tr:hover{background:#e6e2d3;}table{border-radius:8px;overflow:hidden;box-shadow:0 2px 8px #e6e2d3;}td{vertical-align:top;}',
+        '/* Dark mode styles */',
+        '@media (prefers-color-scheme: dark) {',
+        '  th { background: #232323; color: #f4f1e9; }',
+        '  tr:nth-child(even) { background: #232323; }',
+        '  tr:hover { background: #333333; }',
+        '  table { box-shadow: 0 2px 8px #111; }',
+        '  td { color: #f4f1e9; }',
+        '}',
+        '</style>',
         '<table style="border-collapse:collapse;width:100%;font-size:1em;">',
         '<thead><tr>'
         '<th>Reference</th><th>Text</th><th>Similarity</th><th>Book</th><th>Chapter</th><th>Verse</th>'
@@ -142,10 +179,10 @@ def format_results_html(results: List[Dict[str, Any]]) -> str:
     html.append('</tbody></table>')
     return ''.join(html)
 
-def search(query: str, books: List[str], limit: int) -> str:
+def search(query: str, books: List[str], limit: int, search_method: str) -> str:
     if not query.strip():
         return "<div>Please enter a search query.</div>"
-    results = find_similar(query, books, limit)
+    results = find_similar(query, books, limit, search_method)
     return format_results_html(results)
 
 with gr.Blocks(title="Latin Vulgate Verse Similarity Search") as demo:
@@ -170,26 +207,32 @@ with gr.Blocks(title="Latin Vulgate Verse Similarity Search") as demo:
                 multiselect=True
             )
     with gr.Row():
-        limit = gr.Slider(
-            minimum=1,
-            maximum=50,
-            value=20,
-            step=1,
-            label="Number of results"
-        )
+        with gr.Column(scale=1):
+            search_method = gr.Radio(
+                choices=["vector", "bm25", "hybrid"],
+                label="Search Method",
+                value="vector"
+            )
+        with gr.Column(scale=1):
+            limit = gr.Slider(
+                minimum=1,
+                maximum=50,
+                value=20,
+                step=1,
+                label="Number of results"
+            )
     with gr.Row():
         search_btn = gr.Button("Search", variant="primary")
     output = gr.HTML(label="Results")
 
-
     search_btn.click(
         fn=search,
-        inputs=[query, book_select, limit],
+        inputs=[query, book_select, limit, search_method],
         outputs=output
     )
     query.submit(
         fn=search,
-        inputs=[query, book_select, limit],
+        inputs=[query, book_select, limit, search_method],
         outputs=output
     )
 if __name__ == "__main__":