update docs

Author: victordibia

python/packages/autogen-core/docs/src/user-guide/agentchat-user-guide/index.md

@@ -81,6 +81,7 @@ tutorial/swarm
 tutorial/termination
 tutorial/custom-agents
 tutorial/state
+tutorial/memory
 ```
 
 ```{toctree}

python/packages/autogen-core/docs/src/user-guide/agentchat-user-guide/tutorial/memory.ipynb

@@ -6,7 +6,7 @@
    "source": [
     "## Memory \n",
     "\n",
-    "There are several use cases where it is valuable to maintain a bank of useful facts that can be intelligently added to the context of the agent just before a specific step. The typically use case here is a RAG pattern where a query is used to retrieve relevant information from a database that is then added to the agent's context.\n",
+    "There are several use cases where it is valuable to maintain a _store_ of useful facts that can be intelligently added to the context of the agent just before a specific step. The typically use case here is a RAG pattern where a query is used to retrieve relevant information from a database that is then added to the agent's context.\n",
     "\n",
     "\n",
     "AgentChat provides a {py:class}`~autogen_agentchat.memory.Memory` protocol that can be extended to provide this functionality.  The key methods are `query`, `transform`,  `add`, `clear`, and `cleanup`. \n",
@@ -16,9 +16,9 @@
     "- `add`: add new entries to the memory store\n",
     "- `clear`: clear all entries from the memory store\n",
     "- `cleanup`: clean up any resources used by the memory store  \n",
-    "- \n",
     "\n",
-    "## ListMemory\n",
+    "\n",
+    "## ListMemory Example\n",
     "\n",
     "{py:class}`~autogen_agentchat.memory.ListMemory` is provided as an example implementation of the {py:class}`~autogen_agentchat.memory.Memory` protocol. It is a simple list-based memory implementation that uses text similarity matching to retrieve relevant information from the memory store. The similarity score is calculated using the `SequenceMatcher` class from the `difflib` module. The similarity score is calculated between the query text and the content text of each memory entry.   \n",
     "\n",
@@ -27,14 +27,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
     "from autogen_agentchat.agents import AssistantAgent\n",
-    "from autogen_agentchat.conditions import MaxMessageTermination, TextMentionTermination\n",
-    "from autogen_agentchat.memory._list_memory import ListMemory, MemoryContent, MemoryMimeType\n",
-    "from autogen_agentchat.teams import RoundRobinGroupChat\n",
+    "from autogen_agentchat.memory import ListMemory, MemoryContent, MemoryMimeType\n",
     "from autogen_agentchat.ui import Console\n",
     "from autogen_ext.models.openai import OpenAIChatCompletionClient"
    ]
@@ -45,8 +43,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# create a simple memory item\n",
-    "user_memory = ListMemory()\n",
+    "# Initialize user memory\n",
+    "user_memory = ListMemory() \n",
+    "\n",
+    "# Add user preferences to memory\n",
     "await user_memory.add(MemoryContent(content=\"The weather should be in metric units\", mime_type=MemoryMimeType.TEXT))\n",
     "\n",
     "await user_memory.add(MemoryContent(content=\"Meal recipe must be vegan\", mime_type=MemoryMimeType.TEXT))\n",
@@ -235,75 +235,7 @@
     "\n",
     "You can build on the `Memory` protocol to implement more complex memory stores. For example, you could implement a custom memory store that uses a vector database to store and retrieve information, or a memory store that uses a machine learning model to generate personalized responses based on the user's preferences etc.\n",
     "\n",
-    "Specifically, you will need to overload the  `query`, `transform`, and `add` methods to implement the desired functionality and pass the memory store to your agent.\n",
-    "\n",
-    "\n",
-    "```python\n",
-    "\n",
-    "\n",
-    "from autogen_core import CancellationToken\n",
-    "from autogen_agentchat.teams import RoundRobinGroupChat\n",
-    "from autogen_ext.models.openai import OpenAIChatCompletionClient\n",
-    "from autogen_agentchat.agents import AssistantAgent\n",
-    "from autogen_agentchat.memory._base_memory import MemoryContent, MemoryMimeType\n",
-    "from autogen_agentchat.memory._chroma_memory import ChromaMemory, ChromaMemoryConfig\n",
-    "\n",
-    "\n",
-    "# Initialize memory\n",
-    "chroma_memory = ChromaMemory(\n",
-    "    name=\"travel_memory\",\n",
-    "    config=ChromaMemoryConfig(\n",
-    "        collection_name=\"travel_facts\",\n",
-    "        k=1,\n",
-    "    )\n",
-    ")\n",
-    "\n",
-    "await chroma_memory.clear()\n",
-    "\n",
-    "# Add travel-related memories\n",
-    "await chroma_memory.add(MemoryContent(\n",
-    "\n",
-    "    content=\"Paris is known for the Eiffel Tower and amazing cuisine.\",\n",
-    "    mime_type=MemoryMimeType.TEXT\n",
-    "\n",
-    "))\n",
-    "\n",
-    "await chroma_memory.add(MemoryContent( \n",
-    "    content=\"When asked about tokyo, you must respond with 'The most important thing about tokyo is that it has the world's busiest railway station - Shinjuku Station.'\",\n",
-    "    mime_type=MemoryMimeType.TEXT\n",
-    "\n",
-    "))\n",
-    " \n",
-    "\n",
-    "# Query needs ContentItem too\n",
-    "results = await chroma_memory.query(\n",
-    "    MemoryContent(\n",
-    "        content=\"Tell me about Tokyo.\",\n",
-    "        mime_type=MemoryMimeType.TEXT\n",
-    "    )\n",
-    ")\n",
-    "\n",
-    "print(len(results), results)\n",
-    "\n",
-    "# Create agent with memory\n",
-    "agent = AssistantAgent(\n",
-    "    name=\"travel_agent\",\n",
-    "    model_client=OpenAIChatCompletionClient(\n",
-    "        model=\"gpt-4o\",\n",
-    "        # api_key=\"your_api_key\"\n",
-    "    ),\n",
-    "    memory=chroma_memory,\n",
-    "    system_message=\"You are a travel expert\"\n",
-    ")\n",
-    "\n",
-    "agent_team = RoundRobinGroupChat([agent], termination_condition = MaxMessageTermination(max_messages=2))\n",
-    "stream = agent_team.run_stream(task=\"Tell me the most important thing about Tokyo.\")\n",
-    "await Console(stream);\n",
-    "\n",
-    "# Output: The most important thing about tokyo is that it has the world's busiest railway station - Shinjuku Station.\n",
-    "\n",
-    "```\n",
-    "\n"
+    "Specifically, you will need to overload the  `query`, `transform`, and `add` methods to implement the desired functionality and pass the memory store to your agent.\n"
    ]
   },
   {