WEBDIENSTE/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-09-08 02:37:52 +02:00
Code Issues Packages Projects Releases Wiki Activity

Add test and notebook for using pydantic base model as state object

Browse Source
This commit is contained in:
Nuno Campos
2024-04-01 17:40:55 -07:00
parent f88ef74002
commit 961ddd49ed
4 changed files with 603 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/state-model.ipynb
+446
View File
@@ -0,0 +1,446 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "51466c8d-8ce4-4b3d-be4e-18fdbeda5f53",
"metadata": {},
"source": [
"# Pydantic Base Model as State\n",
"\n",
"In this example we will build a chat executor which uses a pydantic base model as the state object. This means all nodes receive an instance of the model as their first arg, and validation is run before each node executes."
]
},
{
"cell_type": "markdown",
"id": "7cbd446a-808f-4394-be92-d45ab818953c",
"metadata": {},
"source": [
"## Setup\n",
"\n",
"First we need to install the packages required"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "af4ce0ba-7596-4e5f-8bf8-0b0bd6e62833",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.3.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.3.2\u001b[0m\n",
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n"
]
}
],
"source": [
"!pip install --quiet -U langchain langchain_openai tavily-python"
]
},
{
"cell_type": "markdown",
"id": "0abe11f4-62ed-4dc4-8875-3db21e260d1d",
"metadata": {},
"source": [
"Next, we need to set API keys for OpenAI (the LLM we will use) and Tavily (the search tool we will use)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "c903a1cf-2977-4e2d-ad7d-8b3946821d89",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"OpenAI API Key: ········\n",
"Tavily API Key: ········\n"
]
}
],
"source": [
"import os\n",
"import getpass\n",
"\n",
"os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
"os.environ[\"TAVILY_API_KEY\"] = getpass.getpass(\"Tavily API Key:\")"
]
},
{
"cell_type": "markdown",
"id": "f0ed46a8-effe-4596-b0e1-a6a29ee16f5c",
"metadata": {},
"source": [
"Optionally, we can set API key for [LangSmith tracing](https://smith.langchain.com/), which will give us best-in-class observability."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "95e25aec-7c9f-4a63-b143-225d0e9a79c3",
"metadata": {},
"outputs": [],
"source": [
"os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
"os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"LangSmith API Key:\")"
]
},
{
"cell_type": "markdown",
"id": "21ac643b-cb06-4724-a80c-2862ba4773f1",
"metadata": {},
"source": [
"## Set up the tools\n",
"\n",
"We will first define the tools we want to use.\n",
"For this simple example, we will use a built-in search tool via Tavily.\n",
"However, it is really easy to create your own tools - see documentation [here](https://python.langchain.com/docs/modules/agents/tools/custom_tools) on how to do that.\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "d7ef57dd-5d6e-4ad3-9377-a92201c1310e",
"metadata": {},
"outputs": [],
"source": [
"from langchain_community.tools.tavily_search import TavilySearchResults\n",
"\n",
"tools = [TavilySearchResults(max_results=1)]"
]
},
{
"cell_type": "markdown",
"id": "01885785-b71a-44d1-b1d6-7b5b14d53b58",
"metadata": {},
"source": [
"We can now wrap these tools in a simple ToolExecutor.\n",
"This is a real simple class that takes in a ToolInvocation and calls that tool, returning the output.\n",
"A ToolInvocation is any class with `tool` and `tool_input` attribute.\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "5cf3331e-ccb3-41c8-aeb9-a840a94d41e7",
"metadata": {},
"outputs": [],
"source": [
"from langgraph.prebuilt import ToolExecutor\n",
"\n",
"tool_executor = ToolExecutor(tools)"
]
},
{
"cell_type": "markdown",
"id": "5497ed70-fce3-47f1-9cad-46f912bad6a5",
"metadata": {},
"source": [
"## Set up the model\n",
"\n",
"Now we need to load the chat model we want to use.\n",
"Importantly, this should satisfy two criteria:\n",
"\n",
"1. It should work with messages. We will represent all agent state in the form of messages, so it needs to be able to work well with them.\n",
"2. It should work with OpenAI function calling. This means it should either be an OpenAI model or a model that exposes a similar interface.\n",
"\n",
"Note: these model requirements are not requirements for using LangGraph - they are just requirements for this one example.\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "892b54b9-75f0-4804-9ed0-88b5e5532989",
"metadata": {},
"outputs": [],
"source": [
"from langchain_openai import ChatOpenAI\n",
"\n",
"# We will set streaming=True so that we can stream tokens\n",
"# See the streaming section for more information on this.\n",
"model = ChatOpenAI(temperature=0, streaming=True)"
]
},
{
"cell_type": "markdown",
"id": "a77995c0-bae2-4cee-a036-8688a90f05b9",
"metadata": {},
"source": [
"\n",
"After we've done this, we should make sure the model knows that it has these tools available to call.\n",
"We can do this by converting the LangChain tools into the format for OpenAI function calling, and then bind them to the model class.\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "cd3cbae5-d92c-4559-a4aa-44721b80d107",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/nuno/dev/langgraph/.venv/lib/python3.11/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The function `format_tool_to_openai_function` was deprecated in LangChain 0.1.16 and will be removed in 0.2.0. Use langchain_core.utils.function_calling.convert_to_openai_function() instead.\n",
" warn_deprecated(\n"
]
}
],
"source": [
"from langchain.tools.render import format_tool_to_openai_function\n",
"\n",
"functions = [format_tool_to_openai_function(t) for t in tools]\n",
"model = model.bind_functions(functions)"
]
},
{
"cell_type": "markdown",
"id": "8e8b9211-93d0-4ad5-aa7a-9c09099c53ff",
"metadata": {},
"source": [
"## Define the agent state\n",
"\n",
"The main type of graph in `langgraph` is the `StateGraph`.\n",
"This graph is parameterized by a state object that it passes around to each node.\n",
"Each node then returns operations to update that state.\n",
"These operations can either SET specific attributes on the state (e.g. overwrite the existing values) or ADD to the existing attribute.\n",
"Whether to set or add is denoted by annotating the state object you construct the graph with.\n",
"\n",
"For this example, the state we will track will just be a list of messages.\n",
"We want each node to just add messages to that list.\n",
"Therefore, we will use a `pydantic.BaseModel` with one key (`messages`) and annotate it so that the `messages` attribute is always added to.\n"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "ea793afa-2eab-4901-910d-6eed90cd6564",
"metadata": {},
"outputs": [],
"source": [
"from typing import Annotated, Sequence\n",
"import operator\n",
"from langchain_core.messages import BaseMessage\n",
"from langchain_core.pydantic_v1 import BaseModel\n",
"\n",
"class AgentState(BaseModel):\n",
" messages: Annotated[Sequence[BaseMessage], operator.add]"
]
},
{
"cell_type": "markdown",
"id": "e03c5094-9297-4d19-a04e-3eedc75cefb4",
"metadata": {},
"source": [
"## Define the nodes\n",
"\n",
"We now need to define a few different nodes in our graph.\n",
"In `langgraph`, a node can be either a function or a [runnable](https://python.langchain.com/docs/expression_language/).\n",
"There are two main nodes we need for this:\n",
"\n",
"1. The agent: responsible for deciding what (if any) actions to take.\n",
"2. A function to invoke tools: if the agent decides to take an action, this node will then execute that action.\n",
"\n",
"We will also need to define some edges.\n",
"Some of these edges may be conditional.\n",
"The reason they are conditional is that based on the output of a node, one of several paths may be taken.\n",
"The path that is taken is not known until that node is run (the LLM decides).\n",
"\n",
"1. Conditional Edge: after the agent is called, we should either:\n",
" a. If the agent said to take an action, then the function to invoke tools should be called\n",
" b. If the agent said that it was finished, then it should finish\n",
"2. Normal Edge: after the tools are invoked, it should always go back to the agent to decide what to do next\n",
"\n",
"Let's define the nodes, as well as a function to decide how what conditional edge to take.\n",
"\n",
"**MODIFICATION**\n",
"\n",
"We define each node to receive the AgentState base model as its first argument."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "3b541bb9-900c-40d0-964d-7b5dfee30667",
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"\n",
"from langgraph.prebuilt import ToolInvocation\n",
"from langchain_core.messages import FunctionMessage\n",
"\n",
"\n",
"# Define the function that determines whether to continue or not\n",
"def should_continue(state):\n",
" messages = state.messages\n",
" last_message = messages[-1]\n",
" # If there is no function call, then we finish\n",
" if \"function_call\" not in last_message.additional_kwargs:\n",
" return \"end\"\n",
" # Otherwise if there is, we continue\n",
" else:\n",
" return \"continue\"\n",
"\n",
"\n",
"# Define the function that calls the model\n",
"def call_model(state):\n",
" messages = state.messages\n",
" response = model.invoke(messages)\n",
" # We return a list, because this will get added to the existing list\n",
" return {\"messages\": [response]}\n",
"\n",
"\n",
"# Define the function to execute tools\n",
"def call_tool(state):\n",
" messages = state.messages\n",
" # Based on the continue condition\n",
" # we know the last message involves a function call\n",
" last_message = messages[-1]\n",
" # We construct an ToolInvocation from the function_call\n",
" action = ToolInvocation(\n",
" tool=last_message.additional_kwargs[\"function_call\"][\"name\"],\n",
" tool_input=json.loads(\n",
" last_message.additional_kwargs[\"function_call\"][\"arguments\"]\n",
" ),\n",
" )\n",
" # We call the tool_executor and get back a response\n",
" response = tool_executor.invoke(action)\n",
" # We use the response to create a FunctionMessage\n",
" function_message = FunctionMessage(content=str(response), name=action.tool)\n",
" # We return a list, because this will get added to the existing list\n",
" return {\"messages\": [function_message]}"
]
},
{
"cell_type": "markdown",
"id": "ffd6e892-946c-4899-8cc0-7c9291c1f73b",
"metadata": {},
"source": [
"## Define the graph\n",
"\n",
"We can now put it all together and define the graph!"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "813ae66c-3b58-4283-a02a-36da72a2ab90",
"metadata": {},
"outputs": [],
"source": [
"from langgraph.graph import StateGraph, END\n",
"\n",
"# Define a new graph\n",
"workflow = StateGraph(AgentState)\n",
"\n",
"# Define the two nodes we will cycle between\n",
"workflow.add_node(\"agent\", call_model)\n",
"workflow.add_node(\"action\", call_tool)\n",
"\n",
"# Set the entrypoint as `agent`\n",
"# This means that this node is the first one called\n",
"workflow.set_entry_point(\"agent\")\n",
"\n",
"# We now add a conditional edge\n",
"workflow.add_conditional_edges(\n",
" # First, we define the start node. We use `agent`.\n",
" # This means these are the edges taken after the `agent` node is called.\n",
" \"agent\",\n",
" # Next, we pass in the function that will determine which node is called next.\n",
" should_continue,\n",
" # Finally we pass in a mapping.\n",
" # The keys are strings, and the values are other nodes.\n",
" # END is a special node marking that the graph should finish.\n",
" # What will happen is we will call `should_continue`, and then the output of that\n",
" # will be matched against the keys in this mapping.\n",
" # Based on which one it matches, that node will then be called.\n",
" {\n",
" # If `tools`, then we call the tool node.\n",
" \"continue\": \"action\",\n",
" # Otherwise we finish.\n",
" \"end\": END,\n",
" },\n",
")\n",
"\n",
"# We now add a normal edge from `tools` to `agent`.\n",
"# This means that after `tools` is called, `agent` node is called next.\n",
"workflow.add_edge(\"action\", \"agent\")\n",
"\n",
"# Finally, we compile it!\n",
"# This compiles it into a LangChain Runnable,\n",
"# meaning you can use it as you would any other runnable\n",
"app = workflow.compile()"
]
},
{
"cell_type": "markdown",
"id": "547c3931-3dae-4281-ad4e-4b51305594d4",
"metadata": {},
"source": [
"## Use it!\n",
"\n",
"We can now use it!\n",
"This now exposes the [same interface](https://python.langchain.com/docs/expression_language/) as all other LangChain runnables."
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "8edb04b9-40b6-46f1-a7a8-4b2d8aba7752",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'agent': {'messages': [AIMessage(content='', additional_kwargs={'function_call': {'arguments': '{\"query\":\"weather in San Francisco\"}', 'name': 'tavily_search_results_json'}})]}}\n",
"{'action': {'messages': [FunctionMessage(content=\"[{'url': 'https://forecast.weather.gov/zipcity.php?inputstring=San francisco,CA', 'content': 'NOAA National Weather Service National Weather Service. Toggle navigation. HOME; FORECAST . Local; Graphical; Aviation; Marine; Rivers and Lakes; Hurricanes; Severe Weather; Fire Weather; ... San Francisco CA 37.77°N 122.41°W (Elev. 131 ft) Last Update: 1:27 am PDT Apr 1, 2024. Forecast Valid: 8am PDT Apr 1, 2024-6pm PDT Apr 7, 2024 .'}]\", name='tavily_search_results_json')]}}\n",
"{'agent': {'messages': [AIMessage(content='You can check the weather in San Francisco by visiting the [NOAA National Weather Service website](https://forecast.weather.gov/zipcity.php?inputstring=San%20francisco,CA).')]}}\n"
]
}
],
"source": [
"from langchain_core.messages import HumanMessage\n",
"\n",
"inputs = {\"messages\": [HumanMessage(content=\"what is the weather in sf\")]}\n",
"for chunk in app.stream(inputs):\n",
" print(chunk)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "296c7456-da05-4326-95dc-47d6b312da9d",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.8"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
langgraph/graph/state.py
+5
View File
@@ -168,6 +168,11 @@ class CompiledStateGraph(CompiledGraph):
ChannelRead(
state_keys[0] if state_keys == ["__root__"] else state_keys,
fresh=True,
mapper=(
None
if state_keys == ["__root__"]
else partial(_coerce_state, self.graph.schema)
),
),
],
).pipe(node)
langgraph/pregel/read.py
+18 -3
View File
@@ -26,6 +26,8 @@ class ChannelRead(RunnableLambda):
fresh: bool = False
mapper: Optional[Callable[[Any], Any]] = None
@property
def config_specs(self) -> list[ConfigurableFieldSpec]:
return [
@@ -38,9 +40,16 @@ class ChannelRead(RunnableLambda):
),
]
def __init__(self, channel: Union[str, list[str]], fresh: bool = False) -> None:
def __init__(
self,
channel: Union[str, list[str]],
*,
fresh: bool = False,
mapper: Optional[Callable[[Any], Any]] = None,
) -> None:
super().__init__(func=self._read, afunc=self._aread)
self.fresh = fresh
self.mapper = mapper
self.channel = channel
self.name = f"ChannelRead<{channel}>"
@@ -52,7 +61,10 @@ class ChannelRead(RunnableLambda):
f"Runnable {self} is not configured with a read function"
"Make sure to call in the context of a Pregel process"
)
return read(self.channel, self.fresh)
if self.mapper:
return self.mapper(read(self.channel, self.fresh))
else:
return read(self.channel, self.fresh)
async def _aread(self, _: Any, config: RunnableConfig) -> Any:
try:
@@ -62,7 +74,10 @@ class ChannelRead(RunnableLambda):
f"Runnable {self} is not configured with a read function"
"Make sure to call in the context of a Pregel process"
)
return read(self.channel, self.fresh)
if self.mapper:
return self.mapper(read(self.channel, self.fresh))
else:
return read(self.channel, self.fresh)
default_bound: RunnablePassthrough = RunnablePassthrough()
tests/test_pregel.py
+134
View File
@@ -2964,6 +2964,140 @@ def test_in_one_fan_out_state_graph_waiting_edge_via_branch(
]
@pytest.mark.parametrize(
"checkpoint_at", [CheckpointAt.END_OF_RUN, CheckpointAt.END_OF_STEP]
)
def test_in_one_fan_out_state_graph_waiting_edge_custom_state_class(
checkpoint_at: CheckpointAt,
) -> None:
from langchain_core.pydantic_v1 import BaseModel
def sorted_add(
x: list[str], y: Union[list[str], list[tuple[str, str]]]
) -> list[str]:
if isinstance(y[0], tuple):
for rem, _ in y:
x.remove(rem)
y = [t[1] for t in y]
return sorted(operator.add(x, y))
class State(BaseModel):
query: str
answer: Optional[str] = None
docs: Annotated[list[str], sorted_add]
def rewrite_query(data: State) -> State:
return {"query": f"query: {data.query}"}
def analyzer_one(data: State) -> State:
return {"query": f"analyzed: {data.query}"}
def retriever_one(data: State) -> State:
return {"docs": ["doc1", "doc2"]}
def retriever_two(data: State) -> State:
return {"docs": ["doc3", "doc4"]}
def qa(data: State) -> State:
return {"answer": ",".join(data.docs)}
def decider(data: State) -> str:
assert isinstance(data, State)
return "retriever_two"
workflow = StateGraph(State)
workflow.add_node("rewrite_query", rewrite_query)
workflow.add_node("analyzer_one", analyzer_one)
workflow.add_node("retriever_one", retriever_one)
workflow.add_node("retriever_two", retriever_two)
workflow.add_node("qa", qa)
workflow.set_entry_point("rewrite_query")
workflow.add_edge("rewrite_query", "analyzer_one")
workflow.add_edge("analyzer_one", "retriever_one")
workflow.add_conditional_edges(
"rewrite_query", decider, {"retriever_two": "retriever_two"}
)
workflow.add_edge(["retriever_one", "retriever_two"], "qa")
workflow.set_finish_point("qa")
app = workflow.compile()
assert app.get_graph().draw_ascii() == (
""" +-----------+
| __start__ |
+-----------+
*
*
*
+---------------+
| rewrite_query |
+---------------+
** **
** **
** **
+--------------+ +-----------------------+
| analyzer_one | | rewrite_query_decider |
+--------------+ +-----------------------+
* *
* *
* *
+---------------+ +---------------+
| retriever_one | | retriever_two |
+---------------+ +---------------+
** **
** **
** **
+----+
| qa |
+----+
*
*
*
+---------+
| __end__ |
+---------+ """
)
assert app.invoke({"query": "what is weather in sf"}) == {
"query": "analyzed: query: what is weather in sf",
"docs": ["doc1", "doc2", "doc3", "doc4"],
"answer": "doc1,doc2,doc3,doc4",
}
assert [*app.stream({"query": "what is weather in sf"})] == [
{"rewrite_query": {"query": "query: what is weather in sf"}},
{
"analyzer_one": {"query": "analyzed: query: what is weather in sf"},
"retriever_two": {"docs": ["doc3", "doc4"]},
},
{"retriever_one": {"docs": ["doc1", "doc2"]}},
{"qa": {"answer": "doc1,doc2,doc3,doc4"}},
]
app_w_interrupt = workflow.compile(
checkpointer=MemorySaverAssertImmutable(at=checkpoint_at),
interrupt_after=["retriever_one"],
)
config = {"configurable": {"thread_id": "1"}}
assert [
c for c in app_w_interrupt.stream({"query": "what is weather in sf"}, config)
] == [
{"rewrite_query": {"query": "query: what is weather in sf"}},
{
"analyzer_one": {"query": "analyzed: query: what is weather in sf"},
"retriever_two": {"docs": ["doc3", "doc4"]},
},
{"retriever_one": {"docs": ["doc1", "doc2"]}},
]
assert [c for c in app_w_interrupt.stream(None, config)] == [
{"qa": {"answer": "doc1,doc2,doc3,doc4"}},
]
@pytest.mark.parametrize(
"checkpoint_at", [CheckpointAt.END_OF_RUN, CheckpointAt.END_OF_STEP]
)