update hybrid_retriever_tool file

tools/hybrid_retriever_tool.py

@@ -23,9 +23,9 @@ class HybridRetrieverTool(RagTool):
         self._tavily = TavilyClient(api_key=os.getenv("TAVILY_API_KEY"))
         self._client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
 
-    def _build_corpus(self, topic):
+    def _build_corpus(self, topic: str):
         """Fetch up-to-date search results."""
-        results = self.tavily.search(query=topic, max_results=30)
+        results = self._tavily.search(query=topic, max_results=30)
         corpus = [r.get("content", "").strip() for r in results.get("results", []) if r.get("content")]
         return corpus
     
@@ -42,8 +42,8 @@ class HybridRetrieverTool(RagTool):
         bm25_scores = np.array(bm25.get_scores(query.split()))
 
         # semantic relevance
-        emb_corpus = self.embedder.encode(corpus, convert_to_numpy=True, normalize_embeddings=True)
-        emb_query = self.embedder.encode(query, convert_to_numpy=True, normalize_embeddings=True)
+        emb_corpus = self._embedder.encode(corpus, convert_to_numpy=True, normalize_embeddings=True)
+        emb_query = self._embedder.encode(query, convert_to_numpy=True, normalize_embeddings=True)
         sem_scores = np.dot(emb_corpus, emb_query)
 
         # Normalize scores
@@ -57,12 +57,12 @@ class HybridRetrieverTool(RagTool):
         top_passages = [corpus[i] for i in top_indices]
         return "\n\n".join(top_passages)
     
-    def summarize_passages(self, topic, passages):
+    def summarize_passages(self, topic: str, passages):
         if isinstance(passages, str):
             passages = [passages]
         text_block = "\n".join(passages)
         try:
-            response = self.client.chat.completions.create(
+            response = self._client.chat.completions.create(
                 model="gpt-4o-mini",
                 messages=[
                     {"role": "system", "content": "You are an expert summarizer."},