Fixed indentation error at line 142

simple_search_engine/search_engine.py

@@ -140,38 +140,39 @@ class SimpleSearchEngine:
         return results
 
     def search_hybrid(self, query: str, top_k: int = 5, alpha: float = 0.5):
-    if self.vectorizer is None or self.doc_tfidf is None or self.bm25 is None:
-        raise RuntimeError("Indexes not built. Call build_index() first.")
-
-    # TF-IDF scores
-    query_vec = self.vectorizer.transform([query])
-    tfidf_scores = linear_kernel(query_vec, self.doc_tfidf).flatten()
-
-    # BM25 scores
-    q_tokens = _tokenize(query)
-    bm25_scores = np.array(self.bm25.get_scores(q_tokens), dtype=float)
-
-    # Normalize
-    tfidf_norm = self._minmax_normalize(tfidf_scores)
-    bm25_norm = self._minmax_normalize(bm25_scores)
-
-    # Combine
-    hybrid_scores = alpha * tfidf_norm + (1 - alpha) * bm25_norm
-    print(f"[DEBUG][HYBRID] query={query} alpha={alpha}")
-    print("[DEBUG][HYBRID] top5_hybrid=", hybrid_scores[hybrid_scores.argsort()[::-1][:5]])
-
-    ranked_idx = hybrid_scores.argsort()[::-1][:top_k]
-
-    results = []
-    for idx in ranked_idx:
-        doc = self.documents[int(idx)]
-        snippet = doc["text"][:200] + ("..." if len(doc["text"]) > 200 else "")
-        results.append({
-            "score": float(hybrid_scores[int(idx)]),
-            "title": doc["title"],
-            "url": doc["url"],
-            "path": doc["path"],
-            "snippet": snippet,
-        })
-
-    return results
+        if self.vectorizer is None or self.doc_tfidf is None or self.bm25 is None:
+            raise RuntimeError("Indexes not built. Call build_index() first.")
+    
+        # TF-IDF scores
+        query_vec = self.vectorizer.transform([query])
+        tfidf_scores = linear_kernel(query_vec, self.doc_tfidf).flatten()
+    
+        # BM25 scores
+        q_tokens = _tokenize(query)
+        bm25_scores = np.array(self.bm25.get_scores(q_tokens), dtype=float)
+    
+        # Normalize
+        tfidf_norm = self._minmax_normalize(tfidf_scores)
+        bm25_norm = self._minmax_normalize(bm25_scores)
+    
+        # Combine
+        hybrid_scores = alpha * tfidf_norm + (1 - alpha) * bm25_norm
+        print(f"[DEBUG][HYBRID] query={query} alpha={alpha}")
+        print("[DEBUG][HYBRID] top5_hybrid=",
+              hybrid_scores[hybrid_scores.argsort()[::-1][:5]])
+    
+        ranked_idx = hybrid_scores.argsort()[::-1][:top_k]
+    
+        results = []
+        for idx in ranked_idx:
+            doc = self.documents[int(idx)]
+            snippet = doc["text"][:200] + ("..." if len(doc["text"]) > 200 else "")
+            results.append({
+                "score": float(hybrid_scores[int(idx)]),
+                "title": doc["title"],
+                "url": doc["url"],
+                "path": doc["path"],
+                "snippet": snippet,
+            })
+    
+        return results