{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Initialization\n",
"\n",
"### Initializing client\n",
"\n",
"To get started we need to initialize our client. The process for initializing our client is almost identical for both the local deployment and cloud deployment using Langsmith."
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"from langgraph_sdk import get_client\n",
"\n",
"# If you deployed using Langsmith use this option\n",
"# Find this url on your Langsmith deployment page\n",
"example_deployed_url = (\n",
" \"https://ht-unhealthy-buffalo25-39d00f953458585aa9f7b5a4fa-g3ps4aazkq-uc.a.run.app\"\n",
")\n",
"\n",
"# If you deployed locally using langgraph up -c langgraph.json use this option\n",
"# This is the default URL, and you can just call get_client() to use it\n",
"example_local_url = \"http://localhost:8123\"\n",
"\n",
"client = get_client(url=\"whatever-your-url-is\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Selecting an Assistant\n",
"\n",
"To select an assistant we can search the assistants that are hosted on our client, and then select the one we want,"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"assistants = await client.assistants.search()\n",
"assistants = [a for a in assistants if not a[\"config\"]]\n",
"assistant = assistants[0]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"In our example we are only hosting a single assistant, but you have the option to host many, in which case you will most likely want to do more filtering than just selecting the first one. Each assistant is a JSON object with the following format, allowing you to select based on a variety of parameters."
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'assistant_id': 'fe096781-5601-53d2-b2f6-0d3403f7e9ca',\n",
" 'graph_id': 'agent',\n",
" 'created_at': '2024-06-11T20:12:45.862108+00:00',\n",
" 'updated_at': '2024-06-11T20:12:45.862108+00:00',\n",
" 'config': {},\n",
" 'metadata': {'created_by': 'system'}}"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"assistant"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Creating a thread\n",
"\n",
"Threads are what we will actually use to run our graphs (assistants). Each thread will update the same state for the graph, meaning we can run the graph multiple times while the state will persist. We can also look back at our thread history, add meta data to different steps of our thread, and update the thread state manually if we wish. We will dive into all of those topics later in this article, but for now let’s just see how to start a thread:"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"thread = await client.threads.create()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We can examine the structure of our thread, which similar to the assistants object provides us with some information about the thread itself, including its id, timestamps, and metadata:"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'thread_id': '6c2e8002-5712-4388-bed6-0747e9a86e31',\n",
" 'created_at': '2024-06-19T15:58:59.243657+00:00',\n",
" 'updated_at': '2024-06-19T15:58:59.243657+00:00',\n",
" 'metadata': {}}"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"thread"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now we are ready to actually use our graph!\n",
"\n",
"## Invoking the graph\n",
"\n",
"The graph used in this example is a simple example of a StateGraph, but it allows us to show most of the API functionality. The state of our graph is defined as follows:"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"from typing import Annotated, TypedDict\n",
"\n",
"from langchain_core.messages import AnyMessage\n",
"\n",
"from langgraph.graph import add_messages\n",
"\n",
"\n",
"def update_user_info(old_info, new_info):\n",
" if \"name\" not in new_info or new_info[\"age\"] == -1:\n",
" return old_info\n",
" return new_info\n",
"\n",
"\n",
"class UserInformation(TypedDict):\n",
" age: int\n",
" name: str\n",
"\n",
"\n",
"class AgentState(TypedDict):\n",
" messages: Annotated[list[AnyMessage], add_messages]\n",
" user_info: Annotated[UserInformation, update_user_info]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"It is important to note that our member variables can be updated by using the `Annotated` class. This is especially important when we make API calls that will update our variables. This is also a good example that your graph can hold much more information than just messages. In our example we use a very simple `UserInformation` class, but you can imagine holding much richer information in your state.\n",
"\n",
"Our graph looks like follows:\n",
"\n",
"\n",
"
![](\"./img/graph_diagram.png\")
\n",
"
\n",
"
![](\"./img/thread_diagram.png\")
\n",
"