update deps and links

Author: tylerhutcherson

python-recipes/agents/03_memory_agent.ipynb

@@ -41,7 +41,7 @@
         "## Short-term Memory\n",
         "The agent tracks chat history using Redis through LangGraph's [checkpointer](https://github.com/redis-developer/langgraph-redis). Each node in the graph (Retrieve Memories, Respond, Summarize) saves its state to Redis, including conversation history and thread metadata.\n",
         "\n",
-        "<img src=\"resources/short-term-memory.png\" style=\"width: 100%; max-width: 400px;\">\n",
+        "<img src=\"https://github.com/redis-developer/redis-ai-resources/blob/feat/update-memory-agent-recipe/python-recipes/agents/resources/short-term-memory.png?raw=true\" style=\"width: 100%; max-width: 400px;\">\n",
         "\n",
         "To prevent context window pollution, the agent summarizes conversations when they exceed a configurable length.\n",
         "\n",
@@ -51,11 +51,19 @@
         "- **Episodic**: User preferences and experiences\n",
         "- **Semantic**: General travel knowledge\n",
         "\n",
-        "<img src=\"resources/long-term-memory.png\" style=\"width: 100%; max-width: 600px;\">\n",
+        "<img src=\"https://github.com/redis-developer/redis-ai-resources/blob/feat/update-memory-agent-recipe/python-recipes/agents/resources/long-term-memory.png?raw=true\" style=\"width: 100%; max-width: 600px;\">\n",
         "\n",
         ">**NOTE**: These memory types align with the [CoALA](https://arxiv.org/abs/2309.02427) paper's concepts. Our agent's procedural memory is encoded in its Python workflow."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Let's Begin\n",
+        "<a href=\"https://colab.research.google.com/github/redis-developer/redis-ai-resources/blob/main/python-recipes/agents/03_memory_agent.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -79,7 +87,7 @@
       },
       "outputs": [],
       "source": [
-        "%pip install langchain-openai langgraph-checkpoint langgraph langgraph-checkpoint-redis langchain-redis"
+        "%pip install langchain-openai langgraph-checkpoint langgraph langgraph-checkpoint-redis pydantic"
       ]
     },
     {
@@ -143,6 +151,8 @@
       },
       "outputs": [],
       "source": [
+        "# NBVAL_SKIP\n",
+        "\n",
         "%%sh\n",
         "curl -fsSL https://packages.redis.io/gpg | sudo gpg --dearmor -o /usr/share/keyrings/redis-archive-keyring.gpg\n",
         "echo \"deb [signed-by=/usr/share/keyrings/redis-archive-keyring.gpg] https://packages.redis.io/deb $(lsb_release -cs) main\" | sudo tee /etc/apt/sources.list.d/redis.list\n",
@@ -581,8 +591,6 @@
       },
       "outputs": [],
       "source": [
-        "\n",
-        "\n",
         "from datetime import datetime\n",
         "from typing import List, Optional, Union\n",
         "\n",
@@ -751,7 +759,7 @@
         "\n",
         "> NOTE: **This tutorial uses tool-based memory** for optimal balance of control and efficiency.\n",
         "\n",
-        "<img src=\"resources/memory-agents.png\" alt=\"Memory Agents Diagram\" width=\"250\">"
+        "<img src=\"https://github.com/redis-developer/redis-ai-resources/blob/feat/update-memory-agent-recipe/python-recipes/agents/resources/memory-agents.png?raw=true\" alt=\"Memory Agents Diagram\" width=\"250\">"
       ]
     },
     {
@@ -1145,7 +1153,6 @@
       },
       "outputs": [],
       "source": [
-        "\n",
         "from langchain_core.messages import HumanMessage\n",
         "from langgraph.graph.message import MessagesState\n",
         "\n",
@@ -1727,6 +1734,8 @@
         }
       ],
       "source": [
+        "# NBVAL_SKIP\n",
+        "\n",
         "try:\n",
         "    user_id = input(\"Enter a user ID: \") or \"demo_user\"\n",
         "    thread_id = input(\"Enter a thread ID: \") or \"demo_thread\"\n",
@@ -1780,6 +1789,7 @@
         }
       ],
       "source": [
+        "# NBVAL_SKIP\n",
         "res = retrieve_memories_tool.invoke({\"query\": \"Travel, activity, and dietary preferences\", \"memory_type\": [\"episodic\", \"semantic\"]})\n",
         "res.split(\"\\n\")"
       ]