diff --git a/templates/rag-pinecone-rerank/pyproject.toml b/templates/rag-pinecone-rerank/pyproject.toml
index 7bf67fe2b..abbf59c90 100644
--- a/templates/rag-pinecone-rerank/pyproject.toml
+++ b/templates/rag-pinecone-rerank/pyproject.toml
@@ -11,7 +11,7 @@ langchain = ">=0.0.313, <0.1"
 openai = ">=0.28.1"
 tiktoken = ">=0.5.1"
 pinecone-client = ">=2.2.4"
-cohere = ">4.32"
+cohere = ">=4.32"
 
 [tool.langserve]
 export_module = "rag_pinecone_rerank"
diff --git a/templates/rag-pinecone-rerank/rag_pinecone_rerank.ipynb b/templates/rag-pinecone-rerank/rag_pinecone_rerank.ipynb
index e3cc43181..f61b47c35 100644
--- a/templates/rag-pinecone-rerank/rag_pinecone_rerank.ipynb
+++ b/templates/rag-pinecone-rerank/rag_pinecone_rerank.ipynb
@@ -11,13 +11,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "id": "d774be2a",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'The agent memory consists of two components: short-term memory and long-term memory. The short-term memory is used for in-context learning and allows the model to learn from its experiences. The long-term memory enables the agent to retain and recall an infinite amount of information over extended periods by leveraging an external vector store and fast retrieval.'"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "from langserve.client import RemoteRunnable\n",
-    "rag_app_pinecone = RemoteRunnable('http://localhost:8000/rag-pinecone-rerank')\n",
+    "rag_app_pinecone = RemoteRunnable('http://localhost:8001/rag_pinecone_rerank')\n",
     "rag_app_pinecone.invoke(\"How does agent memory work?\")"
    ]
   }