From d9743f684e81bba348c1ceb39fbd04787f620d45 Mon Sep 17 00:00:00 2001
From: Vadym Barda <vadym@langchain.dev>
Date: Fri, 1 Nov 2024 09:57:16 -0400
Subject: [PATCH] docs: update annotation in tutorial (#2293)

---
 docs/docs/tutorials/reflexion/reflexion.ipynb | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/docs/docs/tutorials/reflexion/reflexion.ipynb b/docs/docs/tutorials/reflexion/reflexion.ipynb
index 102f48175..a9a1ea87d 100644
--- a/docs/docs/tutorials/reflexion/reflexion.ipynb
+++ b/docs/docs/tutorials/reflexion/reflexion.ipynb
@@ -46,8 +46,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install -U --quiet  langgraph langchain_anthropic\n",
-    "%pip install -U --quiet tavily-python"
+    "%pip install -U --quiet langgraph langchain_anthropic tavily-python"
    ]
   },
   {
@@ -189,7 +188,7 @@
     "        self.runnable = runnable\n",
     "        self.validator = validator\n",
     "\n",
-    "    def respond(self, state: list):\n",
+    "    def respond(self, state: dict):\n",
     "        response = []\n",
     "        for attempt in range(3):\n",
     "            response = self.runnable.invoke(\n",
@@ -622,12 +621,6 @@
     "2. The 'reflections' can be paired with additional external feedback (such as validators), to further guide the actor.\n",
     "3. In the paper, 1 environment (AlfWorld) uses external memory. It does this by storing summaries of the reflections to an external store and using them in subsequent trials/invocations."
    ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "39e44dd6",
-   "metadata": {},
-   "source": []
   }
  ],
  "metadata": {
@@ -646,7 +639,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.12.3"
   }
  },
  "nbformat": 4,