diff --git a/docs/docs/integrations/retrievers/flashrank-reranker.ipynb b/docs/docs/integrations/retrievers/flashrank-reranker.ipynb
index 93697614cd7..bdd4ed6d762 100644
--- a/docs/docs/integrations/retrievers/flashrank-reranker.ipynb
+++ b/docs/docs/integrations/retrievers/flashrank-reranker.ipynb
@@ -53,7 +53,10 @@
     "def pretty_print_docs(docs):\n",
     "    print(\n",
     "        f\"\\n{'-' * 100}\\n\".join(\n",
-    "            [f\"Document {i+1}:\\n\\n\" + d.page_content for i, d in enumerate(docs)]\n",
+    "            [\n",
+    "                f\"Document {i+1}:\\n\\n{d.page_content}\\nMetadata: {d.metadata}\"\n",
+    "                for i, d in enumerate(docs)\n",
+    "            ]\n",
     "        )\n",
     "    )"
    ]
@@ -316,6 +319,8 @@
     ").load()\n",
     "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)\n",
     "texts = text_splitter.split_documents(documents)\n",
+    "for idx, text in enumerate(texts):\n",
+    "    text.metadata[\"id\"] = idx\n",
     "\n",
     "embedding = OpenAIEmbeddings(model=\"text-embedding-ada-002\")\n",
     "retriever = FAISS.from_documents(texts, embedding).as_retriever(search_kwargs={\"k\": 20})\n",
diff --git a/libs/langchain/langchain/retrievers/document_compressors/flashrank_rerank.py b/libs/langchain/langchain/retrievers/document_compressors/flashrank_rerank.py
index 273aff3d44c..a05fd8c6e1c 100644
--- a/libs/langchain/langchain/retrievers/document_compressors/flashrank_rerank.py
+++ b/libs/langchain/langchain/retrievers/document_compressors/flashrank_rerank.py
@@ -59,16 +59,20 @@ class FlashrankRerank(BaseDocumentCompressor):
         callbacks: Optional[Callbacks] = None,
     ) -> Sequence[Document]:
         passages = [
-            {"id": i, "text": doc.page_content} for i, doc in enumerate(documents)
+            {"id": i, "text": doc.page_content, "meta": doc.metadata}
+            for i, doc in enumerate(documents)
         ]
 
         rerank_request = RerankRequest(query=query, passages=passages)
         rerank_response = self.client.rerank(rerank_request)[: self.top_n]
         final_results = []
+
         for r in rerank_response:
+            metadata = r["meta"]
+            metadata["relevance_score"] = r["score"]
             doc = Document(
                 page_content=r["text"],
-                metadata={"id": r["id"], "relevance_score": r["score"]},
+                metadata=metadata,
             )
             final_results.append(doc)
         return final_results