docs: update aws_dynamodb integration doc (#15666)

- **Description:** - Updated the docs for the memory integration module `aws_dynamodb.ipynb` - **Issue:** - #15664 - **Dependencies:** - N/A
6 months ago · 167a0ac5f5
parent 32ec56194b
commit 167a0ac5f5
1 changed files with 111 additions and 84 deletions
--- a/docs/docs/integrations/memory/aws_dynamodb.ipynb
+++ b/docs/docs/integrations/memory/aws_dynamodb.ipynb
@ -9,25 +9,40 @@
    "\n",
    ">[Amazon AWS DynamoDB](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/dynamodb/index.html) is a fully managed `NoSQL` database service that provides fast and predictable performance with seamless scalability.\n",
    "\n",
-    "This notebook goes over how to use `DynamoDB` to store chat message history."
+    "This notebook goes over how to use `DynamoDB` to store chat message history with `DynamoDBChatMessageHistory` class."
   ]
  },
  {
   "cell_type": "markdown",
-   "id": "3f608be0",
+   "id": "9bcbd170",
   "metadata": {},
   "source": [
-    "First make sure you have correctly configured the [AWS CLI](https://docs.aws.amazon.com/cli/latest/userguide/cli-chap-configure.html). Then make sure you have installed `boto3`."
+    "## Setup\n",
+    "\n",
+    "First make sure you have correctly configured the [AWS CLI](https://docs.aws.amazon.com/cli/latest/userguide/cli-chap-configure.html). Then make sure you have installed the `langchain-community` package, so we need to install that. We also need to install the `boto3` package.\n",
+    "\n",
+    "```bash\n",
+    "pip install -U langchain-community boto3\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fdec429d",
+   "metadata": {},
+   "source": [
+    "It's also helpful (but not needed) to set up [LangSmith](https://smith.langchain.com/) for best-in-class observability"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
-   "id": "3a7e89c2-4c55-4a66-91ec-9bf9a37467eb",
+   "id": "47d3f725",
   "metadata": {},
   "outputs": [],
   "source": [
-    "!pip install boto3"
+    "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass()"
   ]
  },
  {
@ -35,7 +50,9 @@
   "id": "030d784f",
   "metadata": {},
   "source": [
-    "Next, create the `DynamoDB` Table where we will be storing messages:"
+    "## Create Table\n",
+    "\n",
+    "Now, create the `DynamoDB` Table where we will be storing messages:"
   ]
  },
  {
@ -99,20 +116,17 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 5,
   "id": "64fc465e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
-       "[HumanMessage(content='hi!', additional_kwargs={}, example=False),\n",
-       " AIMessage(content='whats up?', additional_kwargs={}, example=False),\n",
-       " HumanMessage(content='hi!', additional_kwargs={}, example=False),\n",
-       " AIMessage(content='whats up?', additional_kwargs={}, example=False)]"
+       "[HumanMessage(content='hi!'), AIMessage(content='whats up?')]"
      ]
     },
-     "execution_count": 12,
+     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
@ -152,7 +166,7 @@
   "id": "97f8578a",
   "metadata": {},
   "source": [
-    "## DynamoDBChatMessageHistory With Different Keys Composite Keys\n",
+    "## DynamoDBChatMessageHistory With Composite Keys\n",
    "The default key for DynamoDBChatMessageHistory is ```{\"SessionId\": self.session_id}```, but you can modify this to match your table design.\n",
    "\n",
    "### Primary Key Name\n",
@ -181,16 +195,6 @@
     "text": [
      "0\n"
     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "[HumanMessage(content='hello, composite dynamodb table!', additional_kwargs={}, example=False)]"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
    }
   ],
   "source": [
@ -213,8 +217,27 @@
    "composite_table.meta.client.get_waiter(\"table_exists\").wait(TableName=\"CompositeTable\")\n",
    "\n",
    "# Print out some data about the table.\n",
-    "print(composite_table.item_count)\n",
-    "\n",
+    "print(composite_table.item_count)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "f462660f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessage(content='hello, composite dynamodb table!')]"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
    "my_key = {\n",
    "    \"PK\": \"session_id::0\",\n",
    "    \"SK\": \"langchain_history\",\n",
@ -234,112 +257,116 @@
  },
  {
   "cell_type": "markdown",
-   "id": "3b33c988",
+   "id": "131e42d2",
   "metadata": {},
   "source": [
-    "## Agent with DynamoDB Memory"
+    "## Chaining\n",
+    "\n",
+    "We can easily combine this message history class with [LCEL Runnables](/docs/expression_language/how_to/message_history)\n",
+    "\n",
+    "To do this we will want to use OpenAI, so we need to install that"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": 1,
-   "id": "0264134f",
+   "execution_count": null,
+   "id": "cbd0e91e",
   "metadata": {},
   "outputs": [],
   "source": [
-    "from langchain.agents import AgentType, Tool, initialize_agent\n",
-    "from langchain.memory import ConversationBufferMemory\n",
-    "from langchain_experimental.utilities import PythonREPL\n",
+    "from typing import Optional\n",
+    "\n",
+    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
+    "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
    "from langchain_openai import ChatOpenAI"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": 15,
-   "id": "f92d9499",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "message_history = DynamoDBChatMessageHistory(table_name=\"SessionTable\", session_id=\"1\")\n",
-    "memory = ConversationBufferMemory(\n",
-    "    memory_key=\"chat_history\", chat_memory=message_history, return_messages=True\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "1167eeba",
+   "execution_count": null,
+   "id": "d8cecb08",
   "metadata": {},
   "outputs": [],
   "source": [
-    "python_repl = PythonREPL()\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\"system\", \"You are a helpful assistant.\"),\n",
+    "        MessagesPlaceholder(variable_name=\"history\"),\n",
+    "        (\"human\", \"{question}\"),\n",
+    "    ]\n",
+    ")\n",
    "\n",
-    "# You can create the tool to pass to an agent\n",
-    "tools = [\n",
-    "    Tool(\n",
-    "        name=\"python_repl\",\n",
-    "        description=\"A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.\",\n",
-    "        func=python_repl.run,\n",
-    "    )\n",
-    "]"
+    "chain = prompt | ChatOpenAI()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
-   "id": "06c6e5ba",
+   "id": "88ec540f",
   "metadata": {},
   "outputs": [],
   "source": [
-    "llm = ChatOpenAI(temperature=0)\n",
-    "agent_chain = initialize_agent(\n",
-    "    tools,\n",
-    "    llm,\n",
-    "    agent=AgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION,\n",
-    "    verbose=True,\n",
-    "    memory=memory,\n",
+    "chain_with_history = RunnableWithMessageHistory(\n",
+    "    chain,\n",
+    "    lambda session_id: DynamoDBChatMessageHistory(\n",
+    "        table_name=\"SessionTable\", session_id=session_id\n",
+    "    ),\n",
+    "    input_messages_key=\"question\",\n",
+    "    history_messages_key=\"history\",\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
-   "id": "952a3103",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent_chain.run(input=\"Hello!\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "54c4aaf4",
+   "id": "9e9969fb",
   "metadata": {},
   "outputs": [],
   "source": [
-    "agent_chain.run(input=\"Who owns Twitter?\")"
+    "# This is where we configure the session id\n",
+    "config = {\"configurable\": {\"session_id\": \"<SESSION_ID>\"}}"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": null,
-   "id": "f9013118",
+   "execution_count": 9,
+   "id": "eb73f547",
   "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Hello Bob! How can I assist you today?')"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
   "source": [
-    "agent_chain.run(input=\"My name is Bob.\")"
+    "chain_with_history.invoke({\"question\": \"Hi! I'm bob\"}, config=config)"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": null,
-   "id": "405e5315",
+   "execution_count": 10,
+   "id": "7daa3508",
   "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Your name is Bob! Is there anything specific you would like assistance with, Bob?')"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
   "source": [
-    "agent_chain.run(input=\"Who am I?\")"
+    "chain_with_history.invoke({\"question\": \"Whats my name\"}, config=config)"
   ]
  }
 ],