feat: Introduce weighted and rrf reranker implementations

Signed-off-by: Varsha Prasad Narsing <varshaprasad96@gmail.com>

llama_stack/providers/inline/vector_io/faiss/faiss.py

@@ -137,6 +137,8 @@ class FaissIndex(EmbeddingIndex):
         query_string: str,
         k: int,
         score_threshold: float,
+        reranker_type: str,
+        reranker_params: dict[str, Any] | None = None,
     ) -> QueryChunksResponse:
         raise NotImplementedError("Hybrid search is not supported in FAISS")