diff --git a/examples/rag/langgraph_adaptive_rag_local.ipynb b/examples/rag/langgraph_adaptive_rag_local.ipynb
index ff5a2aaa2..bc89d1d90 100644
--- a/examples/rag/langgraph_adaptive_rag_local.ipynb
+++ b/examples/rag/langgraph_adaptive_rag_local.ipynb
@@ -69,20 +69,18 @@
     "\n",
     "```\n",
     "ollama pull mistral\n",
-    "ollama pull command-r:35b-v0.1-q2_K\n",
     "```"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 64,
+   "execution_count": 2,
    "id": "af8379bd-7eae-4ba6-b632-12e89eab9920",
    "metadata": {},
    "outputs": [],
    "source": [
     "# Ollama model name\n",
-    "local_llm = \"mistral\"\n",
-    "local_llm = \"command-r:35b-v0.1-q2_K\""
+    "local_llm = \"mistral\""
    ]
   },
   {
@@ -117,7 +115,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "f9ff6b99-080d-4827-b2cb-f775543d76f5",
    "metadata": {},
    "outputs": [],
@@ -162,7 +160,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 4,
    "id": "7045e064-e666-4aea-9111-6e9d2007f27e",
    "metadata": {},
    "outputs": [
@@ -203,7 +201,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": 7,
    "id": "813cdcef-8b75-4214-a2ed-b89077b3d287",
    "metadata": {},
    "outputs": [
@@ -245,7 +243,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 65,
+   "execution_count": 8,
    "id": "aeb8b373-0289-4dec-bd4b-8b2701200301",
    "metadata": {},
    "outputs": [
@@ -253,8 +251,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "The agent's memory is supported by a memory stream, which functions as a long-term memory module that records the agents' experiences in natural language. This recorded information is then used to influence the agent's behavior and interaction with other agents.\n",
-      "Memory is also employed by the agent in reflection mechanisms, which create higher-level summaries of past events, and can be accessed for self-reflection.\n"
+      " In an LLM-powered autonomous agent system, the Large Language Model (LLM) functions as the agent's brain. The agent has key components including memory, planning, and reflection mechanisms. The memory component is a long-term memory module that records a comprehensive list of agents’ experience in natural language. It includes a memory stream, which is an external database for storing past experiences. The reflection mechanism synthesizes memories into higher-level inferences over time and guides the agent's future behavior.\n"
      ]
     }
    ],
@@ -286,7 +283,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 54,
+   "execution_count": 9,
    "id": "38345cff-e2d0-436e-aa09-599522a61eed",
    "metadata": {},
    "outputs": [
@@ -296,7 +293,7 @@
        "{'score': 'yes'}"
       ]
      },
-     "execution_count": 54,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -326,7 +323,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 55,
+   "execution_count": 10,
    "id": "9771caa1-5542-47c3-8354-aeeafcf51964",
    "metadata": {},
    "outputs": [
@@ -336,7 +333,7 @@
        "{'score': 'yes'}"
       ]
      },
-     "execution_count": 55,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -366,7 +363,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 56,
+   "execution_count": 11,
    "id": "830ba5f7-9c8d-4c01-83b1-e4d51d40d48f",
    "metadata": {},
    "outputs": [
@@ -376,7 +373,7 @@
        "' What is agent memory and how can it be effectively utilized in vector database retrieval?'"
       ]
      },
-     "execution_count": 56,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -409,7 +406,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 57,
+   "execution_count": 12,
    "id": "6c3c1c70-ff84-41e8-bf72-738ed52f2dde",
    "metadata": {},
    "outputs": [],
@@ -434,7 +431,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 58,
+   "execution_count": 13,
    "id": "6e09087e-b2a9-437a-abee-129e426df799",
    "metadata": {},
    "outputs": [],
@@ -458,7 +455,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 59,
+   "execution_count": 14,
    "id": "7c5fa507-77ae-426a-a65f-f518b9525bd0",
    "metadata": {},
    "outputs": [],
@@ -668,7 +665,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 60,
+   "execution_count": 15,
    "id": "450eb313-ca75-4a43-b57e-7034bd3f40bf",
    "metadata": {},
    "outputs": [],
@@ -719,7 +716,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 63,
+   "execution_count": 16,
    "id": "b095c1db-8bd1-4a34-937c-1a9b74ae74ff",
    "metadata": {},
    "outputs": [
@@ -736,20 +733,20 @@
       "\"Node 'web_search':\"\n",
       "'\\n---\\n'\n",
       "---GENERATE---\n",
-      "\"Node 'generate':\"\n",
-      "'\\n---\\n'\n",
       "---CHECK HALLUCINATIONS---\n",
       "---DECISION: GENERATION IS GROUNDED IN DOCUMENTS---\n",
       "---GRADE GENERATION vs QUESTION---\n",
       "---DECISION: GENERATION ADDRESSES QUESTION---\n",
-      "\"Node '__end__':\"\n",
+      "\"Node 'generate':\"\n",
       "'\\n---\\n'\n",
-      "(' The AlphaCodium paper introduces a new approach called AlphaCodium for code '\n",
-      " 'generation by Large Language Models (LLMs). It is a test-based, multi-stage '\n",
-      " 'flow that improves LLM performances on code problems through an iterative '\n",
-      " 'process of generating and fixing code against input-output tests. The '\n",
-      " 'authors tested AlphaCodium on the CodeContests dataset and reported improved '\n",
-      " \"results compared to DeepMind's AlphaCode and AlphaCode2.\")\n"
+      "(' The AlphaCodium paper introduces a new approach for code generation by '\n",
+      " 'Large Language Models (LLMs). It presents AlphaCodium, an iterative process '\n",
+      " 'that involves generating additional data to aid the flow, and testing it on '\n",
+      " 'the CodeContests dataset. The results show that AlphaCodium outperforms '\n",
+      " \"DeepMind's AlphaCode and AlphaCode2 without fine-tuning a model. The \"\n",
+      " 'approach includes a pre-processing phase for problem reasoning in natural '\n",
+      " 'language and an iterative code generation phase with runs and fixes against '\n",
+      " 'tests.')\n"
      ]
     }
    ],
@@ -777,7 +774,7 @@
    "source": [
     "Trace: \n",
     "\n",
-    "https://smith.langchain.com/public/98f3b8d3-b26d-430d-a434-f25273345f56/r"
+    "https://smith.langchain.com/public/81813813-be53-403c-9877-afcd5786ca2e/r"
    ]
   },
   {