Fix all API usage issues in 03_memory_integration notebook

- Fixed len(long_term_memories) to len(long_term_memories.memories)
- Fixed iteration over long_term_memories to long_term_memories.memories
- Fixed empty list [] to actual message creation for working memory
- Fixed if long_term_memories: to if long_term_memories.memories:

Author: abrookins

python-recipes/context-engineering/notebooks/section-3-memory/03_memory_integration.ipynb

@@ -175,7 +175,7 @@
         "    text=user_query,\n",
         "    limit=3\n",
         ")\n",
-        "print(f\"   Relevant memories found: {len(long_term_memories)}\")\n",
+        "print(f\"   Relevant memories found: {len(long_term_memories.memories)}\")\n",
         "\n",
         "# Step 3: Process with LLM\n",
         "print(\"\\n3. Processing with LLM...\")\n",
@@ -192,7 +192,10 @@
         "from agent_memory_client.models import WorkingMemory, MemoryMessage\n",
         "\n",
         "# Convert messages to MemoryMessage format\n",
-        "memory_messages = [MemoryMessage(**msg) for msg in []]\n",
+        "memory_messages = [\n",
+        "    MemoryMessage(role=\"user\", content=user_query),\n",
+        "    MemoryMessage(role=\"assistant\", content=response.content)\n",
+        "]\n",
         "\n",
         "# Create WorkingMemory object\n",
         "working_memory = WorkingMemory(\n",
@@ -249,7 +252,7 @@
         "    text=user_query_2,\n",
         "    limit=3\n",
         ")\n",
-        "print(f\"   Relevant memories found: {len(long_term_memories)}\")\n",
+        "print(f\"   Relevant memories found: {len(long_term_memories.memories)}\")\n",
         "\n",
         "# Step 3: Process with LLM (with conversation history)\n",
         "print(\"\\n3. Processing with LLM...\")\n",
@@ -378,15 +381,15 @@
         "    text=user_query_3,\n",
         "    limit=5\n",
         ")\n",
-        "print(f\"   Relevant memories found: {len(long_term_memories)}\")\n",
-        "if long_term_memories:\n",
+        "print(f\"   Relevant memories found: {len(long_term_memories.memories)}\")\n",
+        "if long_term_memories.memories:\n",
         "    print(\"\\n   Retrieved memories:\")\n",
-        "    for memory in long_term_memories:\n",
+        "    for memory in long_term_memories.memories:\n",
         "        print(f\"   - {memory.text}\")\n",
         "\n",
         "# Step 3: Process with LLM (with long-term context)\n",
         "print(\"\\n3. Processing with LLM...\")\n",
-        "context = \"\\n\".join([f\"- {m.text}\" for m in long_term_memories])\n",
+        "context = \"\\n\".join([f\"- {m.text}\" for m in long_term_memories.memories])\n",
         "system_prompt = f\"\"\"You are a helpful class scheduling agent for Redis University.\n",
         "\n",
         "What you know about this student:\n",
@@ -408,7 +411,10 @@
         "from agent_memory_client.models import WorkingMemory, MemoryMessage\n",
         "\n",
         "# Convert messages to MemoryMessage format\n",
-        "memory_messages = [MemoryMessage(**msg) for msg in []]\n",
+        "memory_messages = [\n",
+        "    MemoryMessage(role=\"user\", content=user_query_3),\n",
+        "    MemoryMessage(role=\"assistant\", content=response.content)\n",
+        "]\n",
         "\n",
         "# Create WorkingMemory object\n",
         "working_memory = WorkingMemory(\n",