Bug描述

RetrieverQueryEngine在传递自定义混合检索器时无法处理response_synthesizer对象，出现以下错误信息：
合成器对象没有'metadata'属性
其中合成器可以是CompactAndRefine、Refine等。

版本

版本：0.10.22

重现步骤

def get_retriever_query_engine_for_cache():

    cache_bm25_retriever = get_BM25_retriever_for_cache()

    cache_vector_retriever = index_storage.index_cache().as_retriever(similarity_top_k=2)

    hybrid_retriever = HybridRetriever(cache_vector_retriever, cache_bm25_retriever)

    reranker = LLMRerank(
            choice_batch_size=20,
            top_n=2,
        )
    response_synthesizer = get_response_synthesizer(structured_answer_filtering=True)

    return RetrieverQueryEngine(
        retriever=hybrid_retriever, 
        response_synthesizer=get_response_synthesizer(response_synthesizer),
        node_postprocessors=[reranker,SimilarityPostprocessor(similarity_cutoff=SIMILARITY_CUTOFF_CACHE_CUSTOM_HYBRID)],
        )

自定义混合检索器：

class HybridRetriever(BaseRetriever):
    def __init__(self, vector_retriever, bm25_retriever):
        self.vector_retriever = vector_retriever
        self.bm25_retriever = bm25_retriever
        super().__init__()

    def _retrieve(self, query, **kwargs):
        bm25_nodes = self.bm25_retriever.retrieve(query, **kwargs)
        vector_nodes = self.vector_retriever.retrieve(query, **kwargs)

        # combine the two lists of nodes
        all_nodes = []
        node_ids = set()
        for n in bm25_nodes + vector_nodes:
            if n.node.node_id not in node_ids:
                all_nodes.append(n)
                node_ids.add(n.node.node_id)
        return all_nodes

相关日志/回溯

• 无响应*