LangGraph (4/4): personalización del estado y checkpoints

19 de mayo del 2025

En las partes anteriores construimos un agente con herramientas, memoria a corto y largo plazo y human-in-the-loop. Para cerrar la guía vemos cómo **personalizar el estado** del grafo con esquemas y reductores propios, y cómo trabajar con **checkpoints** para inspeccionar y recorrer el historial de estados.

⚠️ Este capítulo continúa el código de las partes anteriores (Parte 1 · Parte 2 · Parte 3).

📚 **Esta entrada es parte de la serie _Guía completa de LangGraph_**, dividida en cuatro capítulos que se leen en orden:

> * Parte 1: Chatbot básico y herramientas

* Parte 2: Memoria a corto plazo

* Parte 3: Memoria a largo plazo y human-in-the-loop

* 👉 **Parte 4: Personalización del estado y checkpoints**

Personalización del estado

Nota: Este apartado lo vamos a hacer usando Sonnet 3.7, ya que a día de la escritura del post, es el mejor modelo para uso con agentes, y es el único que entiende cuándo tiene que llamar a las tools y cuándo no

Hasta ahora, hemos confiado en un estado simple con una entrada, una lista de mensajes. Se puede llegar lejos con este estado simple, pero si se desea definir un comportamiento complejo sin depender de la lista de mensajes, se pueden agregar campos adicionales al estado.

Aquí vamos a ver un nuevo escenario, en el que el chatbot está utilizando la herramienta de búsqueda para encontrar información específica y reenviándola a un ser humano para su revisión. Vamos a hacer que el chatbot investigue el cumpleaños de una entidad. Agregaremos name y birthday como claves del estado.

Primero cargamos los valores de las API KEYs

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		import os
import dotenv
 
dotenv.load_dotenv()
 
TAVILY_API_KEY = os.getenv("TAVILY_LANGGRAPH_API_KEY")
ANTHROPIC_TOKEN = os.getenv("ANTHROPIC_LANGGRAPH_API_KEY")
	
	Copied

Creamos el nuevo estado

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		from typing import Annotated
 
from typing_extensions import TypedDict
 
from langgraph.graph.message import add_messages
 
class State(TypedDict):
    messages: Annotated[list, add_messages]
    name: str
    birthday: str
	
	Copied

Agregar esta información al estado hace que sea fácilmente accesible por otros nodos del grafo (por ejemplo, un nodo que almacena o procesa la información), así como la capa de persistencia del grafo.

Ahora creamos el grafo

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		from langgraph.graph import StateGraph, START, END
 
graph_builder = StateGraph(State)
	
	Copied

Definimos la tool de búsqueda

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		from langchain_community.utilities.tavily_search import TavilySearchAPIWrapper
from langchain_community.tools.tavily_search import TavilySearchResults
 
wrapper = TavilySearchAPIWrapper(tavily_api_key=TAVILY_API_KEY)
search_tool = TavilySearchResults(api_wrapper=wrapper, max_results=2)
	
	Copied

Ahora creamos la tool de asistencia humana. En esta tool rellenaremos las claves de estado dentro de nuestra herramienta human_assistance. Esto permite a un ser humano revisar la información antes de que se almacene en el estado. Volveremos a usar Command, esta vez para emitir una actualización de estado desde el interior de nuestra herramienta.

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		from langchain_core.messages import ToolMessage
from langchain_core.tools import InjectedToolCallId, tool
 
from langgraph.types import Command, interrupt
 
@tool
# Note that because we are generating a ToolMessage for a state update, we
# generally require the ID of the corresponding tool call. We can use
# LangChain's InjectedToolCallId to signal that this argument should not
# be revealed to the model in the tool's schema.
def human_assistance(
    name: str, birthday: str, tool_call_id: Annotated[str, InjectedToolCallId]
) -&gt; str:
    """
    Request assistance from a human expert. Use this tool ONLY ONCE per conversation.
    After receiving the expert's response, you should provide an elaborated response to the user based on the information received
    based on the information received, without calling this tool again.
 
    Args:
        query: The query to ask the human expert.
 
    Returns:
        The response from the human expert.
    """
    human_response = interrupt(
        {
            "question": "Is this correct?",
            "name": name,
            "birthday": birthday,
        },
    )
 
    # If the information is correct, update the state as-is.
    if human_response.get("correct", "").lower().startswith("y"):
        verified_name = name
        verified_birthday = birthday
        response = "Correct"
 
    # Otherwise, receive information from the human reviewer.
    else:
        verified_name = human_response.get("name", name)
        verified_birthday = human_response.get("birthday", birthday)
        response = f"Made a correction: {human_response}"
 
    # This time we explicitly update the state with a ToolMessage inside
    # the tool.
    state_update = {
        "name": verified_name,
        "birthday": verified_birthday,
        "messages": [ToolMessage(response, tool_call_id=tool_call_id)],
    }
    
    # We return a Command object in the tool to update our state.
    return Command(update=state_update)
	
	Copied

Hemos usado ToolMessage que se usa para pasar el resultado de ejecutar una tool de nuevo a un modelo y InjectedToolCallId

Creamos una lista de tools

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		tools_list = [search_tool, human_assistance]
	
	Copied

A continuación, el LLM con las bind_tools y lo añadimos al grafo

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace
from langchain_anthropic import ChatAnthropic
 
# Create the LLM
llm = ChatAnthropic(model="claude-3-7-sonnet-20250219", api_key=ANTHROPIC_TOKEN)
 
# Modification: tell the LLM which tools it can call
llm_with_tools = llm.bind_tools(tools_list)
 
# Define the chatbot function
def chatbot_function(state: State):
    message = llm_with_tools.invoke(state["messages"])
    # Because we will be interrupting during tool execution,
    # we disable parallel tool calling to avoid repeating any
    # tool invocations when we resume.
    assert len(message.tool_calls) &lt;= 1
    return {"messages": [message]}
 
# Add the chatbot node
graph_builder.add_node("chatbot_node", chatbot_function)
	
	Copied

>_ Output

			
				&lt;langgraph.graph.state.StateGraph at 0x120b4f380&gt;

Añadimos la tool al grafo

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		from langgraph.prebuilt import ToolNode, tools_condition
 
tool_node = ToolNode(tools=tools_list)
graph_builder.add_node("tools", tool_node)
graph_builder.add_conditional_edges("chatbot_node", tools_condition)
graph_builder.add_edge("tools", "chatbot_node")
	
	Copied

>_ Output

			
				&lt;langgraph.graph.state.StateGraph at 0x120b4f380&gt;

Añadimos el nodo de START al grafo

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		graph_builder.add_edge(START, "chatbot_node")
	
	Copied

>_ Output

			
				&lt;langgraph.graph.state.StateGraph at 0x120b4f380&gt;

Creamos un checkpointer MemorySaver.

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		from langgraph.checkpoint.memory import MemorySaver
 
memory = MemorySaver()
	
	Copied

Compilamos el grafo con el checkpointer

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		graph = graph_builder.compile(checkpointer=memory)
	
	Copied

Lo representamos gráficamente

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		from IPython.display import Image, display
 
try:
    display(Image(graph.get_graph().draw_mermaid_png()))
except Exception as e:
    print(f"Error al visualizar el grafo: {e}")
	
	Copied

>_ Output

			
				&lt;IPython.core.display.Image object&gt;

Vamos a pedir a nuestro chatbot que busque el "cumpleaños" de la biblioteca de LangGraph.

Dirigiremos al chatbot hasta la herramienta human_assistance una vez que tenga la información requerida. Los argumentos name y birthday son obligatorios para la herramienta human_assistance, así que obligan al chatbot a generar propuestas para estos campos.

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		user_input = (
    "Can you look up when LangGraph was released? "
    "When you have the answer, use the human_assistance tool for review."
)
config = {"configurable": {"thread_id": "1"}}
 
events = graph.stream(
    {"messages": [{"role": "user", "content": user_input}]},
    config,
    stream_mode="values",
)
for event in events:
    if "messages" in event:
        event["messages"][-1].pretty_print()
	
	Copied

>_ Output

			
				================================ Human Message =================================
Can you look up when LangGraph was released? When you have the answer, use the human_assistance tool for review.

>_ Output

			
				Failed to multipart ingest runs: langsmith.utils.LangSmithError: Failed to POST https://eu.api.smith.langchain.com/runs/multipart in LangSmith API. HTTPError('403 Client Error: Forbidden for url: https://eu.api.smith.langchain.com/runs/multipart', '{"error":"Forbidden"}
')

>_ Output

			
				================================== Ai Message ==================================
[{'text': "I'll help you look up when LangGraph was released, and then I'll use the human_assistance tool for review as requested.

First, let me search for information about LangGraph's release date:", 'type': 'text'}, {'id': 'toolu_011KHWFxYbFnUvGEF6MPt3dE', 'input': {'query': 'LangGraph release date when was LangGraph released'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
Tool Calls:
  tavily_search_results_json (toolu_011KHWFxYbFnUvGEF6MPt3dE)
Call ID: toolu_011KHWFxYbFnUvGEF6MPt3dE
  Args:
    query: LangGraph release date when was LangGraph released

>_ Output

			
				Failed to send compressed multipart ingest: langsmith.utils.LangSmithError: Failed to POST https://eu.api.smith.langchain.com/runs/multipart in LangSmith API. HTTPError('403 Client Error: Forbidden for url: https://eu.api.smith.langchain.com/runs/multipart', '{"error":"Forbidden"}
')

>_ Output

			
				================================= Tool Message =================================
Name: tavily_search_results_json
[{"title": "LangGraph Studio: The first agent IDE | by Bhavik Jikadara - Medium", "url": "https://bhavikjikadara.medium.com/langgraph-studio-the-first-agent-ide-468132628274", "content": "LangGraph, launched in January 2023, is a low-level orchestration framework designed for building controllable and complex agentic applications.", "score": 0.80405265}, {"title": "langgraph - PyPI", "url": "https://pypi.org/project/langgraph/", "content": "langgraph · PyPI
Skip to main content Switch to mobile version

Search PyPI  Search

Help
Sponsors
Log in
Register

Menu

Help
Sponsors
Log in
Register

Search PyPI  Search
langgraph 0.2.70
pip install langgraph Copy PIP instructions
Latest versionReleased: Feb 6, 2025
Building stateful, multi-actor applications with LLMs
Navigation

Project description
Release history
Download files [...] 0.2.20 Sep 13, 2024

0.2.19 Sep 6, 2024

0.2.18 Sep 6, 2024

0.2.17 Sep 5, 2024

0.2.16 Sep 1, 2024

0.2.15 Aug 30, 2024

0.2.14 Aug 24, 2024

0.2.13 Aug 23, 2024

0.2.12 Aug 22, 2024

0.2.11 Aug 22, 2024

0.2.10 Aug 21, 2024

0.2.9 Aug 21, 2024

0.2.8 Aug 21, 2024

0.2.7 Aug 21, 2024

0.2.7a0 pre-release Aug 21, 2024

0.2.6 Aug 21, 2024

0.2.5 Aug 21, 2024

0.2.5a0 pre-release Aug 20, 2024

0.2.4 Aug 15, 2024

0.2.3 Aug 8, 2024

0.2.2 Aug 7, 2024

0.2.1 Aug 7, 2024

0.2.0 Aug 7, 2024 [...] Download URL: langgraph-0.2.70.tar.gz
Upload date: Feb 6, 2025
Size: 129.7 kB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.12.8", "score": 0.75659186}]

>_ Output

			
				Failed to send compressed multipart ingest: langsmith.utils.LangSmithError: Failed to POST https://eu.api.smith.langchain.com/runs/multipart in LangSmith API. HTTPError('403 Client Error: Forbidden for url: https://eu.api.smith.langchain.com/runs/multipart', '{"error":"Forbidden"}
')

>_ Output

			
				================================== Ai Message ==================================
[{'text': 'Based on my search, I found that LangGraph was launched in January 2023. However, I noticed some inconsistencies in the information, as one source mentions it was launched in January 2023, while the PyPI page shows a version history starting from 2024.

Let me request human assistance to verify this information:', 'type': 'text'}, {'id': 'toolu_019EopKn8bLi3ksvUVY2Mt5p', 'input': {'name': 'LangGraph', 'birthday': 'January 2023'}, 'name': 'human_assistance', 'type': 'tool_use'}]
Tool Calls:
  human_assistance (toolu_019EopKn8bLi3ksvUVY2Mt5p)
Call ID: toolu_019EopKn8bLi3ksvUVY2Mt5p
  Args:
    name: LangGraph
    birthday: January 2023

>_ Output

			
				Failed to send compressed multipart ingest: langsmith.utils.LangSmithError: Failed to POST https://eu.api.smith.langchain.com/runs/multipart in LangSmith API. HTTPError('403 Client Error: Forbidden for url: https://eu.api.smith.langchain.com/runs/multipart', '{"error":"Forbidden"}
')
Failed to send compressed multipart ingest: langsmith.utils.LangSmithError: Failed to POST https://eu.api.smith.langchain.com/runs/multipart in LangSmith API. HTTPError('403 Client Error: Forbidden for url: https://eu.api.smith.langchain.com/runs/multipart', '{"error":"Forbidden"}
')
Failed to send compressed multipart ingest: langsmith.utils.LangSmithError: Failed to POST https://eu.api.smith.langchain.com/runs/multipart in LangSmith API. HTTPError('403 Client Error: Forbidden for url: https://eu.api.smith.langchain.com/runs/multipart', '{"error":"Forbidden"}
')
Failed to send compressed multipart ingest: langsmith.utils.LangSmithError: Failed to POST https://eu.api.smith.langchain.com/runs/multipart in LangSmith API. HTTPError('403 Client Error: Forbidden for url: https://eu.api.smith.langchain.com/runs/multipart', '{"error":"Forbidden"}
')

Se ha parado por el interrupt en la herramienta human_assistance. En este caso, el chatbot, con la herramienta de búsqueda, ha determinado que la fecha de LangGraph es enero de 2023, pero no es la fecha exacta, es el 17 de enero de 2024, por lo que podemos introducirla nosotros mismos.

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		human_command = Command(
    resume={
        "name": "LangGraph",
        "birthday": "Jan 17, 2024",
    },
)
 
events = graph.stream(human_command, config, stream_mode="values")
for event in events:
    if "messages" in event:
        event["messages"][-1].pretty_print()
	
	Copied

>_ Output

			
				================================== Ai Message ==================================
[{'text': 'Based on my search, I found that LangGraph was launched in January 2023. However, I noticed some inconsistencies in the information, as one source mentions it was launched in January 2023, while the PyPI page shows a version history starting from 2024.

Let me request human assistance to verify this information:', 'type': 'text'}, {'id': 'toolu_019EopKn8bLi3ksvUVY2Mt5p', 'input': {'name': 'LangGraph', 'birthday': 'January 2023'}, 'name': 'human_assistance', 'type': 'tool_use'}]
Tool Calls:
  human_assistance (toolu_019EopKn8bLi3ksvUVY2Mt5p)
Call ID: toolu_019EopKn8bLi3ksvUVY2Mt5p
  Args:
    name: LangGraph
    birthday: January 2023
================================= Tool Message =================================
Name: human_assistance
Made a correction: {'name': 'LangGraph', 'birthday': 'Jan 17, 2024'}
================================== Ai Message ==================================
Thank you for the expert review and correction! Based on the human expert's feedback, I can now provide you with the accurate information:
LangGraph was released on January 17, 2024, not January 2023 as one of the search results incorrectly stated.
This is an important correction, as it means LangGraph is a relatively recent framework in the LLM orchestration space, having been available for less than a year at this point. LangGraph is developed by LangChain and is designed for building stateful, multi-actor applications with LLMs.

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		snapshot = graph.get_state(config)
 
{k: v for k, v in snapshot.values.items() if k in ("name", "birthday")}
	
	Copied

>_ Output

			
				{'name': 'LangGraph', 'birthday': 'Jan 17, 2024'}

Ahora la fecha es la correcta gracias a la intervención humana para modificar los valores del estado

Vuelvo a escribir todo el código para que sea más fácil de entender

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		import os
import dotenv
 
from typing import Annotated
from typing_extensions import TypedDict
 
from langgraph.graph.message import add_messages
from langgraph.graph import StateGraph, START, END
from langgraph.types import Command, interrupt
from langgraph.prebuilt import ToolNode, tools_condition
from langgraph.checkpoint.memory import MemorySaver
 
from langchain_community.utilities.tavily_search import TavilySearchAPIWrapper
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_core.messages import ToolMessage
from langchain_core.tools import InjectedToolCallId, tool
from langchain_anthropic import ChatAnthropic
 
dotenv.load_dotenv()
TAVILY_API_KEY = os.getenv("TAVILY_LANGGRAPH_API_KEY")
ANTHROPIC_TOKEN = os.getenv("ANTHROPIC_LANGGRAPH_API_KEY")
 
# State
class State(TypedDict):
    messages: Annotated[list, add_messages]
    name: str
    birthday: str
 
# Tools
wrapper = TavilySearchAPIWrapper(tavily_api_key=TAVILY_API_KEY)
search_tool = TavilySearchResults(api_wrapper=wrapper, max_results=2)
 
@tool
# Note that because we are generating a ToolMessage for a state update, we
# generally require the ID of the corresponding tool call. We can use
# LangChain's InjectedToolCallId to signal that this argument should not
# be revealed to the model in the tool's schema.
def human_assistance(
    name: str, birthday: str, tool_call_id: Annotated[str, InjectedToolCallId]
) -&gt; str:
    """
    Request assistance from a human expert. Use this tool ONLY ONCE per conversation.
    After receiving the expert's response, you should provide an elaborated response to the user based on the information received
    based on the information received, without calling this tool again.
 
    Args:
        query: The query to ask the human expert.
 
    Returns:
        The response from the human expert.
    """
    human_response = interrupt(
        {
            "question": "Is this correct?",
            "name": name,
            "birthday": birthday,
        },
    )
 
    # If the information is correct, update the state as-is.
    if human_response.get("correct", "").lower().startswith("y"):
        verified_name = name
        verified_birthday = birthday
        response = "Correct"
 
    # Otherwise, receive information from the human reviewer.
    else:
        verified_name = human_response.get("name", name)
        verified_birthday = human_response.get("birthday", birthday)
        response = f"Made a correction: {human_response}"
 
    # This time we explicitly update the state with a ToolMessage inside
    # the tool.
    state_update = {
        "name": verified_name,
        "birthday": verified_birthday,
        "messages": [ToolMessage(response, tool_call_id=tool_call_id)],
    }
    
    # We return a Command object in the tool to update our state.
    return Command(update=state_update)
 
tools_list = [search_tool, human_assistance]
tool_node = ToolNode(tools=tools_list)
 
# Create the LLM
llm = ChatAnthropic(model="claude-3-7-sonnet-20250219", api_key=ANTHROPIC_TOKEN)
llm_with_tools = llm.bind_tools(tools_list)
 
# Define the chatbot function
def chatbot_function(state: State):
    message = llm_with_tools.invoke(state["messages"])
    # Because we will be interrupting during tool execution,
    # we disable parallel tool calling to avoid repeating any
    # tool invocations when we resume.
    assert len(message.tool_calls) &lt;= 1
    return {"messages": [message]}
 
# Graph
graph_builder = StateGraph(State)
 
# Nodes
graph_builder.add_node("tools", tool_node)
graph_builder.add_node("chatbot_node", chatbot_function)
 
# Edges
graph_builder.add_edge(START, "chatbot_node")
graph_builder.add_conditional_edges("chatbot_node", tools_condition)
graph_builder.add_edge("tools", "chatbot_node")
 
# Checkpointer
memory = MemorySaver()
 
# Compile
graph = graph_builder.compile(checkpointer=memory)
 
# Visualize
from IPython.display import Image, display
 
try:
    display(Image(graph.get_graph().draw_mermaid_png()))
except Exception as e:
    print(f"Error al visualizar el grafo: {e}")
	
	Copied

>_ Output

			
				Error al visualizar el grafo: Failed to reach https://mermaid.ink/ API while trying to render your graph after 1 retries. To resolve this issue:
1. Check your internet connection and try again
2. Try with higher retry settings: `draw_mermaid_png(..., max_retries=5, retry_delay=2.0)`
3. Use the Pyppeteer rendering method which will render your graph locally in a browser: `draw_mermaid_png(..., draw_method=MermaidDrawMethod.PYPPETEER)`

Vamos a pedir a nuestro chatbot que busque el "cumpleaños" de la biblioteca de LangGraph.

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		user_input = (
    "Can you look up when LangGraph was released? "
    "When you have the answer, use the human_assistance tool for review."
)
config = {"configurable": {"thread_id": "1"}}
 
events = graph.stream(
    {"messages": [{"role": "user", "content": user_input}]},
    config,
    stream_mode="values",
)
for event in events:
    if "messages" in event:
        event["messages"][-1].pretty_print()
	
	Copied

>_ Output

			
				================================ Human Message =================================
Can you look up when LangGraph was released? When you have the answer, use the human_assistance tool for review.

>_ Output

			
				Failed to multipart ingest runs: langsmith.utils.LangSmithError: Failed to POST https://eu.api.smith.langchain.com/runs/multipart in LangSmith API. HTTPError('403 Client Error: Forbidden for url: https://eu.api.smith.langchain.com/runs/multipart', '{"error":"Forbidden"}
')

>_ Output

			
				================================== Ai Message ==================================
[{'text': "I'll look up when LangGraph was released and then get human verification of the information.", 'type': 'text'}, {'id': 'toolu_017SLLSEnFQZVdBpj85BKHyy', 'input': {'query': 'when was LangGraph released launch date'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
Tool Calls:
  tavily_search_results_json (toolu_017SLLSEnFQZVdBpj85BKHyy)
Call ID: toolu_017SLLSEnFQZVdBpj85BKHyy
  Args:
    query: when was LangGraph released launch date

>_ Output

			
				Failed to send compressed multipart ingest: langsmith.utils.LangSmithError: Failed to POST https://eu.api.smith.langchain.com/runs/multipart in LangSmith API. HTTPError('403 Client Error: Forbidden for url: https://eu.api.smith.langchain.com/runs/multipart', '{"error":"Forbidden"}
')

>_ Output

			
				================================= Tool Message =================================
Name: tavily_search_results_json
[{"title": "LangChain Introduces LangGraph Studio: The First Agent IDE for ...", "url": "https://www.marktechpost.com/2024/08/03/langchain-introduces-langgraph-studio-the-first-agent-ide-for-visualizing-interacting-with-and-debugging-complex-agentic-applications/", "content": "LangGraph, launched in January 2023, is a highly controllable, low-level orchestration framework for building agentic applications. Since its inception, it has undergone significant improvements, leading to a stable 0.1 release in June. LangGraph features a persistence layer enabling human-in-the-loop interactions and excels at building complex applications requiring domain-specific cognitive architecture.", "score": 0.83742094}, {"title": "LangGraph Studio: The first agent IDE | by Bhavik Jikadara - Medium", "url": "https://bhavikjikadara.medium.com/langgraph-studio-the-first-agent-ide-468132628274", "content": "LangGraph, launched in January 2023, is a low-level orchestration framework designed for building controllable and complex agentic applications. It’s beneficial for creating applications requiring highly domain-specific cognitive architecture and human-in-the-loop interactions. LangGraph is open source, available in Python and JavaScript, and integrates seamlessly with LangSmith, whether or not you use LangChain.

LangGraph: A Comprehensive Guide for Beginners", "score": 0.79369855}]

>_ Output

			
				Failed to send compressed multipart ingest: langsmith.utils.LangSmithError: Failed to POST https://eu.api.smith.langchain.com/runs/multipart in LangSmith API. HTTPError('403 Client Error: Forbidden for url: https://eu.api.smith.langchain.com/runs/multipart', '{"error":"Forbidden"}
')

>_ Output

			
				================================== Ai Message ==================================
[{'text': "Based on my search, I found that LangGraph was launched in January 2023. It's described as a low-level orchestration framework for building agentic applications. Since its release, it has seen significant improvements, including a stable 0.1 release in June (presumably 2024).

Let me now get human verification of this information:", 'type': 'text'}, {'id': 'toolu_016h3391yFhtPDhQvwjNgs7W', 'input': {'name': 'Information Verification', 'birthday': 'January 2023'}, 'name': 'human_assistance', 'type': 'tool_use'}]
Tool Calls:
  human_assistance (toolu_016h3391yFhtPDhQvwjNgs7W)
Call ID: toolu_016h3391yFhtPDhQvwjNgs7W
  Args:
    name: Information Verification
    birthday: January 2023

>_ Output

			
				Failed to send compressed multipart ingest: langsmith.utils.LangSmithError: Failed to POST https://eu.api.smith.langchain.com/runs/multipart in LangSmith API. HTTPError('403 Client Error: Forbidden for url: https://eu.api.smith.langchain.com/runs/multipart', '{"error":"Forbidden"}
')
Failed to send compressed multipart ingest: langsmith.utils.LangSmithError: Failed to POST https://eu.api.smith.langchain.com/runs/multipart in LangSmith API. HTTPError('403 Client Error: Forbidden for url: https://eu.api.smith.langchain.com/runs/multipart', '{"error":"Forbidden"}
')
Failed to send compressed multipart ingest: langsmith.utils.LangSmithError: Failed to POST https://eu.api.smith.langchain.com/runs/multipart in LangSmith API. HTTPError('403 Client Error: Forbidden for url: https://eu.api.smith.langchain.com/runs/multipart', '{"error":"Forbidden"}
')

Se ha parado por el interrupt en la herramienta human_assistance. En este caso, el chatbot, con la herramienta de búsqueda, ha determinado que la fecha de LangGraph es en enero de 2023, pero no es la fecha exacta, es el 17 de enero de 2024, por lo que podemos introducirla nosotros mismos.

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		human_command = Command(
    resume={
        "name": "LangGraph",
        "birthday": "Jan 17, 2024",
    },
)
 
events = graph.stream(human_command, config, stream_mode="values")
for event in events:
    if "messages" in event:
        event["messages"][-1].pretty_print()
	
	Copied

>_ Output

			
				================================== Ai Message ==================================
[{'text': "Based on my search, I found that LangGraph was launched in January 2023. It's described as a low-level orchestration framework for building agentic applications. Since its release, it has seen significant improvements, including a stable 0.1 release in June (presumably 2024).

Let me now get human verification of this information:", 'type': 'text'}, {'id': 'toolu_016h3391yFhtPDhQvwjNgs7W', 'input': {'name': 'Information Verification', 'birthday': 'January 2023'}, 'name': 'human_assistance', 'type': 'tool_use'}]
Tool Calls:
  human_assistance (toolu_016h3391yFhtPDhQvwjNgs7W)
Call ID: toolu_016h3391yFhtPDhQvwjNgs7W
  Args:
    name: Information Verification
    birthday: January 2023
================================= Tool Message =================================
Name: human_assistance
Made a correction: {'name': 'LangGraph', 'birthday': 'Jan 17, 2024'}
================================== Ai Message ==================================
Thank you for the expert correction! I need to update my response with the accurate information.
LangGraph was actually released on January 17, 2024 - not January 2023 as I initially found in my search results. This is a significant correction, as it means LangGraph is a much more recent framework than the search results indicated.
The expert has provided the specific date (January 17, 2024) for LangGraph's release, making it a fairly new tool in the AI orchestration ecosystem. This timing aligns better with the mention of its stable 0.1 release in June 2024, as this would be about 5 months after its initial launch.

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		snapshot = graph.get_state(config)
 
{k: v for k, v in snapshot.values.items() if k in ("name", "birthday")}
	
	Copied

>_ Output

			
				{'name': 'LangGraph', 'birthday': 'Jan 17, 2024'}

Ahora la fecha es la correcta gracias a la intervención humana para modificar los valores del estado

Actualización manual del estado

LangGraph proporciona un alto grado de control sobre el estado de aplicación. Por ejemplo, en cualquier punto (incluso cuando se interrumpe), podemos sobrescribir manualmente una key del estado usando graph.update_state:

Vamos a actualizar el name del estado a LangGraph (library).

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		graph.update_state(config, {"name": "LangGraph (library)"})
	
	Copied

>_ Output

			
				{'configurable': {'thread_id': '1',
  'checkpoint_ns': '',
  'checkpoint_id': '1f010a5a-8a70-618e-8006-89107653db68'}}

Si ahora vemos el estado con graph.get_state(config) veremos que el name se ha actualizado.

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		snapshot = graph.get_state(config)
 
{k: v for k, v in snapshot.values.items() if k in ("name", "birthday")}
	
	Copied

>_ Output

			
				{'name': 'LangGraph (library)', 'birthday': 'Jan 17, 2024'}

Las actualizaciones de estado manuales generarán una traza en LangSmith. Se pueden usar para controlar flujos de trabajo de human in the loop, como se puede ver en esta guía.

Checkpoints

En un flujo de trabajo típico de un chatbot, el usuario interactúa con el chatbot una o más veces para realizar una tarea. En las secciones anteriores, vimos cómo agregar memoria y un human in the loop para poder verificar nuestro estado de grafo y controlar las respuestas futuras.

Pero, a lo mejor un usuario quiere comenzar desde una respuesta anterior y quiere ramificar para explorar un resultado separado. Esto es útil para aplicaciones de agentes, cuando un flujo falla pueden volver a un checkpoint anterior y probar otra estrategia.

LangGraph da esta posibilidad mediante los checkpoints

Primero cargamos los valores de las API KEYs

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		import os
import dotenv
 
dotenv.load_dotenv()
 
HUGGINGFACE_TOKEN = os.getenv("HUGGINGFACE_LANGGRAPH")
TAVILY_API_KEY = os.getenv("TAVILY_LANGGRAPH_API_KEY")
	
	Copied

Creamos el nuevo estado

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		from typing import Annotated
 
from typing_extensions import TypedDict
 
from langgraph.graph.message import add_messages
 
class State(TypedDict):
    messages: Annotated[list, add_messages]
	
	Copied

Ahora creamos el grafo

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		from langgraph.graph import StateGraph, START, END
 
graph_builder = StateGraph(State)
	
	Copied

Definimos la tool de búsqueda

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		from langchain_community.utilities.tavily_search import TavilySearchAPIWrapper
from langchain_community.tools.tavily_search import TavilySearchResults
 
wrapper = TavilySearchAPIWrapper(tavily_api_key=TAVILY_API_KEY)
search_tool = TavilySearchResults(api_wrapper=wrapper, max_results=2)
	
	Copied

Creamos una lista de tools

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		tools_list = [search_tool]
	
	Copied

A continuación, el LLM con las bind_tools y lo añadimos al grafo

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace
from huggingface_hub import login
os.environ["LANGCHAIN_TRACING_V2"] = "false" # Disable LangSmith tracing
 
# Create the LLM
login(token=HUGGINGFACE_TOKEN)
MODEL = "Qwen/Qwen2.5-72B-Instruct"
model = HuggingFaceEndpoint(
    repo_id=MODEL,
    task="text-generation",
    max_new_tokens=512,
    do_sample=False,
    repetition_penalty=1.03,
)
# Create the chat model
llm = ChatHuggingFace(llm=model)
 
# Modification: tell the LLM which tools it can call
llm_with_tools = llm.bind_tools(tools_list)
 
# Define the chatbot function
def chatbot_function(state: State):
    message = llm_with_tools.invoke(state["messages"])
    return {"messages": [message]}
 
# Add the chatbot node
graph_builder.add_node("chatbot_node", chatbot_function)
	
	Copied

>_ Output

			
				&lt;langgraph.graph.state.StateGraph at 0x10d8ce7b0&gt;

Añadimos la tool al grafo

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		from langgraph.prebuilt import ToolNode, tools_condition
 
tool_node = ToolNode(tools=tools_list)
graph_builder.add_node("tools", tool_node)
graph_builder.add_conditional_edges("chatbot_node", tools_condition)
graph_builder.add_edge("tools", "chatbot_node")
	
	Copied

>_ Output

			
				&lt;langgraph.graph.state.StateGraph at 0x10d8ce7b0&gt;

Añadimos el nodo de START al grafo

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		graph_builder.add_edge(START, "chatbot_node")
	
	Copied

>_ Output

			
				&lt;langgraph.graph.state.StateGraph at 0x10d8ce7b0&gt;

Creamos un checkpointer MemorySaver.

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		from langgraph.checkpoint.memory import MemorySaver
 
memory = MemorySaver()
	
	Copied

Compilamos el grafo con el checkpointer

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		graph = graph_builder.compile(checkpointer=memory)
	
	Copied

Lo representamos gráficamente

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		from IPython.display import Image, display
 
try:
    display(Image(graph.get_graph().draw_mermaid_png()))
except Exception as e:
    print(f"Error al visualizar el grafo: {e}")
	
	Copied

>_ Output

			
				&lt;IPython.core.display.Image object&gt;

Hagamos que nuestro grafo dé un par de pasos. Cada paso será guardado en el historial del estado.

Hacemos la primera llamada al modelo

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		config = {"configurable": {"thread_id": "1"}}
 
user_input = (
    "I'm learning LangGraph. "
    "Could you do some research on it for me?"
)
 
events = graph.stream(
    {"messages": [{"role": "user","content": user_input},],},
    config,
    stream_mode="values",
)
for event in events:
    if "messages" in event:
        event["messages"][-1].pretty_print()
	
	Copied

>_ Output

			
				================================ Human Message =================================
I'm learning LangGraph. Could you do some research on it for me?
================================== Ai Message ==================================
Tool Calls:
  tavily_search_results_json (0)
Call ID: 0
  Args:
    query: LangGraph
================================= Tool Message =================================
Name: tavily_search_results_json
[{"title": "LangGraph Quickstart - GitHub Pages", "url": "https://langchain-ai.github.io/langgraph/tutorials/introduction/", "content": "[](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-9-1)Assistant: LangGraph is a library designed to help build stateful multi-agent applications using language models. It provides tools for creating workflows and state machines to coordinate multiple AI agents or language model interactions. LangGraph is built on top of LangChain, leveraging its components while adding graph-based coordination capabilities. It's particularly useful for developing more complex, [...] [](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-21-6)   LangGraph is a library designed for building stateful, multi-actor applications with Large Language Models (LLMs). It's particularly useful for creating agent and multi-agent workflows.
[](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-21-7)
[](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-21-8)2. Developer: [...] [](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-48-19)LangGraph is likely a framework or library designed specifically for creating AI agents with advanced capabilities. Here are a few points to consider based on this recommendation:
[](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-48-20)", "score": 0.9328032}, {"title": "langchain-ai/langgraph: Build resilient language agents as graphs.", "url": "https://github.com/langchain-ai/langgraph", "content": "LangGraph — used by Replit, Uber, LinkedIn, GitLab and more — is a low-level orchestration framework for building controllable agents. While langchain provides integrations and composable components to streamline LLM application development, the LangGraph library enables agent orchestration — offering customizable architectures, long-term memory, and human-in-the-loop to reliably handle complex tasks.

```
pip install -U langgraph
```", "score": 0.8884594}]
================================== Ai Message ==================================
Tool Calls:
  tavily_search_results_json (0)
Call ID: 0
  Args:
    query: LangGraph
================================= Tool Message =================================
Name: tavily_search_results_json
[{"title": "LangGraph Quickstart - GitHub Pages", "url": "https://langchain-ai.github.io/langgraph/tutorials/introduction/", "content": "[](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-9-1)Assistant: LangGraph is a library designed to help build stateful multi-agent applications using language models. It provides tools for creating workflows and state machines to coordinate multiple AI agents or language model interactions. LangGraph is built on top of LangChain, leveraging its components while adding graph-based coordination capabilities. It's particularly useful for developing more complex, [...] [](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-21-6)   LangGraph is a library designed for building stateful, multi-actor applications with Large Language Models (LLMs). It's particularly useful for creating agent and multi-agent workflows.
[](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-21-7)
[](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-21-8)2. Developer: [...] [](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-48-19)LangGraph is likely a framework or library designed specifically for creating AI agents with advanced capabilities. Here are a few points to consider based on this recommendation:
[](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-48-20)", "score": 0.9328032}, {"title": "langchain-ai/langgraph: Build resilient language agents as graphs.", "url": "https://github.com/langchain-ai/langgraph", "content": "LangGraph — used by Replit, Uber, LinkedIn, GitLab and more — is a low-level orchestration framework for building controllable agents. While langchain provides integrations and composable components to streamline LLM application development, the LangGraph library enables agent orchestration — offering customizable architectures, long-term memory, and human-in-the-loop to reliably handle complex tasks.

```
pip install -U langgraph
```", "score": 0.8884594}]
...
### Tutorials and Resources
- **Official Documentation**: The official LangGraph documentation is a comprehensive resource for learning about its features and usage.
- **Tutorials**: Look for tutorials and guides specifically focused on building AI agents with LangGraph. You can find a tutorial video [here](https://www.youtube.com/watch?v=gqvFmK7LpDo).
### Companies Using LangGraph
- **Replit, Uber, LinkedIn, GitLab, and more**: These companies are using LangGraph to build resilient and controllable language agents.
### Next Steps
1. **Review the Documentation**: Start by going through the official LangGraph documentation to get a deeper understanding of its features and capabilities.
2. **Follow Tutorials**: Watch tutorials and follow step-by-step guides to build your first multi-agent application.
3. **Experiment with Examples**: Try out the examples provided in the documentation to get hands-on experience with LangGraph.
If you have any specific questions or need further assistance, feel free to ask!

Y ahora la segunda llamada

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		user_input = (
    "Ya that's helpful. Maybe I'll "
    "build an autonomous agent with it!"
)
 
events = graph.stream(
    {"messages": [{"role": "user","content": user_input},],},
    config,
    stream_mode="values",
)
for event in events:
    if "messages" in event:
        event["messages"][-1].pretty_print()
	
	Copied

>_ Output

			
				================================ Human Message =================================
Ya that's helpful. Maybe I'll build an autonomous agent with it!
================================== Ai Message ==================================
Tool Calls:
  tavily_search_results_json (0)
Call ID: 0
  Args:
    query: LangGraph tutorial build autonomous agent
================================= Tool Message =================================
Name: tavily_search_results_json
[{"title": "LangGraph Tutorial: Building LLM Agents with LangChain's ... - Zep", "url": "https://www.getzep.com/ai-agents/langgraph-tutorial", "content": "This article focuses on building agents with LangGraph rather than LangChain. It provides a tutorial for building LangGraph agents, beginning with a discussion of LangGraph and its components. These concepts are reinforced by building a LangGraph agent from scratch and managing conversation memory with LangGraph agents. Finally, we use Zep's long-term memory for egents to create an agent that remembers previous conversations and user facts.Â

â

Summary of key LangGraph tutorial concepts [...] human intervention, and the ability to handle complex workflows with
      cycles and branches.
Building a LangGraph agent | Creating a LangGraph agent is the best way to understand the core concepts
      of nodes, edges, and state. The LangGraph Python libraries are modular and
      provide the functionality to build a stateful graph by incrementally
      adding nodes and edges.Incorporating tools enables an agent to perform specific tasks and access", "score": 0.8338803}, {"title": "Build Autonomous AI Agents with ReAct and LangGraph Tools", "url": "https://www.youtube.com/watch?v=ZfjaIshGkmk", "content": "LangGraph Intro - Build Autonomous AI Agents with ReAct and LangGraph Tools
GrabDuck!
4110 subscribers
18 likes
535 views
21 Jan 2025
In this video, LangGraph Intro: Build Autonomous AI Agents with ReAct and LangGraph Tools, we dive into creating a powerful agentic system where the LLM decides when to trigger tools and when to finalize results. You’ll see how to build a generic agent architecture using the ReAct principle, applying it to real-world examples like analyzing Tesla stock data. [...] reasoning like what they're doing so uh it's this way you're using tool and this is another thing from longchain core library and here you define the function and then you have to Define name description there are other parameters like for example you can provide very specific description of all the parameters like why you need them which one are those Etc but it's a bit over complicated for this tutorial I'm skipping it and uh interesting thing this one return direct is false and this is uh [...] Whether you’re wondering how to create AI agents, looking for a LangGraph tutorial, or eager to explore the power of LangChain agents, this video is packed with valuable insights to help you get started.

Support the channel while you shop on Amazon! 
Use my affiliate link https://amzn.to/4hssSvT

Every purchase via this Amazon link helps keep our content free for you!

🌟 Related Courses &amp; Tutorials", "score": 0.8286204}]
================================== Ai Message ==================================
Tool Calls:
  tavily_search_results_json (0)
Call ID: 0
  Args:
    query: LangGraph tutorial build autonomous agent
================================= Tool Message =================================
Name: tavily_search_results_json
[{"title": "LangGraph Tutorial: Building LLM Agents with LangChain's ... - Zep", "url": "https://www.getzep.com/ai-agents/langgraph-tutorial", "content": "This article focuses on building agents with LangGraph rather than LangChain. It provides a tutorial for building LangGraph agents, beginning with a discussion of LangGraph and its components. These concepts are reinforced by building a LangGraph agent from scratch and managing conversation memory with LangGraph agents. Finally, we use Zep's long-term memory for egents to create an agent that remembers previous conversations and user facts.Â

â

Summary of key LangGraph tutorial concepts [...] human intervention, and the ability to handle complex workflows with
      cycles and branches.
Building a LangGraph agent | Creating a LangGraph agent is the best way to understand the core concepts
      of nodes, edges, and state. The LangGraph Python libraries are modular and
      provide the functionality to build a stateful graph by incrementally
      adding nodes and edges.Incorporating tools enables an agent to perform specific tasks and access", "score": 0.8338803}, {"title": "Build Autonomous AI Agents with ReAct and LangGraph Tools", "url": "https://www.youtube.com/watch?v=ZfjaIshGkmk", "content": "LangGraph Intro - Build Autonomous AI Agents with ReAct and LangGraph Tools
GrabDuck!
4110 subscribers
18 likes
535 views
21 Jan 2025
In this video, LangGraph Intro: Build Autonomous AI Agents with ReAct and LangGraph Tools, we dive into creating a powerful agentic system where the LLM decides when to trigger tools and when to finalize results. You’ll see how to build a generic agent architecture using the ReAct principle, applying it to real-world examples like analyzing Tesla stock data. [...] reasoning like what they're doing so uh it's this way you're using tool and this is another thing from longchain core library and here you define the function and then you have to Define name description there are other parameters like for example you can provide very specific description of all the parameters like why you need them which one are those Etc but it's a bit over complicated for this tutorial I'm skipping it and uh interesting thing this one return direct is false and this is uh [...] Whether you’re wondering how to create AI agents, looking for a LangGraph tutorial, or eager to explore the power of LangChain agents, this video is packed with valuable insights to help you get started.

Support the channel while you shop on Amazon! 
Use my affiliate link https://amzn.to/4hssSvT

Every purchase via this Amazon link helps keep our content free for you!

🌟 Related Courses &amp; Tutorials", "score": 0.8286204}]
...
Once you have the basic structure in place, you can enhance your agent with advanced features such as:
- **Long-term Memory**: Use external storage (e.g., Zep) to remember user conversations and preferences.
- **Conditional Edges**: Define conditions for transitions between nodes to handle different scenarios.
- **Human-in-the-Loop**: Allow human intervention for complex tasks or error handling.
### Additional Resources
- **Official Documentation**: [LangGraph Documentation](https://langchain-ai.github.io/langgraph/tutorials/introduction/)
- **Comprehensive Guide**: [LangGraph Tutorial for Beginners](https://blog.futuresmart.ai/langgraph-tutorial-for-beginners)
- **Example Project**: [Building AI Agents with LangGraph](https://medium.com/@lorevanoudenhove/how-to-build-ai-agents-with-langgraph-a-step-by-step-guide-5d84d9c7e832)
### Conclusion
By following these steps, you can build a robust and flexible AI agent using LangGraph. Start with simple examples and gradually add more complex features to create powerful, stateful, and multi-actor applications. Happy coding!

Ahora que hemos hecho dos llamadas al modelo, vamos a ver el historial del estado.

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		to_replay = None
for state in graph.get_state_history(config):
    print(f"Num Messages: {len(state.values["messages"])}, Next: {state.next}, checkpoint id = {state.config["configurable"]['checkpoint_id']}")
    print("-" * 80)
 
    # Get state when first iteracction us done
    if len(state.next) == 0:
        to_replay = state
	
	Copied

>_ Output

			
				Num Messages: 24, Next: (), checkpoint id = 1f027f2f-e5b4-6c84-8018-9fcb33b5f397
--------------------------------------------------------------------------------
Num Messages: 23, Next: ('chatbot_node',), checkpoint id = 1f027f2f-e414-6b0e-8017-3ad465b70767
--------------------------------------------------------------------------------
Num Messages: 22, Next: ('tools',), checkpoint id = 1f027f2f-d382-6692-8016-fcfaf9c9a9f7
--------------------------------------------------------------------------------
Num Messages: 21, Next: ('chatbot_node',), checkpoint id = 1f027f2f-d1cf-6930-8015-f64aa0e6f750
--------------------------------------------------------------------------------
Num Messages: 20, Next: ('tools',), checkpoint id = 1f027f2f-bca9-6164-8014-86452cb10d83
--------------------------------------------------------------------------------
Num Messages: 19, Next: ('chatbot_node',), checkpoint id = 1f027f2f-bac1-6d24-8013-b539f3e4cedb
--------------------------------------------------------------------------------
Num Messages: 18, Next: ('tools',), checkpoint id = 1f027f2f-aa0e-69fa-8012-4ca2d9109f4e
--------------------------------------------------------------------------------
Num Messages: 17, Next: ('chatbot_node',), checkpoint id = 1f027f2f-a861-62c4-8011-5707badab130
--------------------------------------------------------------------------------
Num Messages: 16, Next: ('tools',), checkpoint id = 1f027f2f-93cf-6112-8010-ee536e76cdf7
--------------------------------------------------------------------------------
Num Messages: 15, Next: ('chatbot_node',), checkpoint id = 1f027f2f-91f5-63fa-800f-6ff45b0ebf86
--------------------------------------------------------------------------------
...
Num Messages: 4, Next: ('tools',), checkpoint id = 1f027f2c-627b-6f6e-8003-22208fac7c89
--------------------------------------------------------------------------------
Num Messages: 3, Next: ('chatbot_node',), checkpoint id = 1f027f2c-6122-6190-8002-b745c42a724e
--------------------------------------------------------------------------------
Num Messages: 2, Next: ('tools',), checkpoint id = 1f027f2c-4c4c-6720-8001-8a1c73b894c1
--------------------------------------------------------------------------------
Num Messages: 1, Next: ('chatbot_node',), checkpoint id = 1f027f2c-4a91-6278-8000-56b65f6d77cd
--------------------------------------------------------------------------------
Num Messages: 0, Next: ('__start__',), checkpoint id = 1f027f2c-4a8d-6a1a-bfff-2f7cbde97290
--------------------------------------------------------------------------------

Hemos guardado en to_replay el estado del grafo cuando nos ha dado la primera respuesta, justo antes de introducir el segundo mensaje. Podemos volver a un estado pasado y continuar el flujo desde allí.

La configuración del checkpoint contiene el checkpoint_id, que es un timestamp del flujo. Podemos verlo para comprobar que estamos en el estado que queremos estar.

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		print(to_replay.config)
	
	Copied

>_ Output

			
				{'configurable': {'thread_id': '1', 'checkpoint_ns': '', 'checkpoint_id': '1f027f2c-8873-61d6-8007-8a1c60438002'}}

Si nos fijamos en la lista de estados de antes, vemos que el ID coincide con el momento de introducir el segundo mensaje

Dando este checkpoint_id a LangGraph carga el estado en ese momento del flujo. Así que creamos un nuevo mensaje y se lo pasamos al grafo

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		user_input = (
    "Thanks"
)
 
# The `checkpoint_id` in the `to_replay.config` corresponds to a state we've persisted to our checkpointer.
events = graph.stream({"messages": [{"role": "user","content": user_input},],},
    to_replay.config,
    stream_mode="values",
)
 
for event in events:
    if "messages" in event:
        event["messages"][-1].pretty_print()
	
	Copied

>_ Output

			
				================================ Human Message =================================
Thanks
================================== Ai Message ==================================
You're welcome! If you have any more questions about LangGraph or any other topics, feel free to ask. Happy learning! 🚀

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		for state in graph.get_state_history(config):
    print(f"Num Messages: {len(state.values["messages"])}, Next: {state.next}, checkpoint id = {state.config["configurable"]['checkpoint_id']}")
    print("-" * 80)
	
	Copied

>_ Output

			
				Num Messages: 10, Next: (), checkpoint id = 1f027f43-71ae-67e0-800a-d84a557441fc
--------------------------------------------------------------------------------
Num Messages: 9, Next: ('chatbot_node',), checkpoint id = 1f027f43-5b1f-6ad8-8009-34f409789bc4
--------------------------------------------------------------------------------
Num Messages: 8, Next: ('__start__',), checkpoint id = 1f027f43-5b1b-68a2-8008-fbbcbd1c175e
--------------------------------------------------------------------------------
Num Messages: 24, Next: (), checkpoint id = 1f027f2f-e5b4-6c84-8018-9fcb33b5f397
--------------------------------------------------------------------------------
Num Messages: 23, Next: ('chatbot_node',), checkpoint id = 1f027f2f-e414-6b0e-8017-3ad465b70767
--------------------------------------------------------------------------------
Num Messages: 22, Next: ('tools',), checkpoint id = 1f027f2f-d382-6692-8016-fcfaf9c9a9f7
--------------------------------------------------------------------------------
Num Messages: 21, Next: ('chatbot_node',), checkpoint id = 1f027f2f-d1cf-6930-8015-f64aa0e6f750
--------------------------------------------------------------------------------
Num Messages: 20, Next: ('tools',), checkpoint id = 1f027f2f-bca9-6164-8014-86452cb10d83
--------------------------------------------------------------------------------
Num Messages: 19, Next: ('chatbot_node',), checkpoint id = 1f027f2f-bac1-6d24-8013-b539f3e4cedb
--------------------------------------------------------------------------------
Num Messages: 18, Next: ('tools',), checkpoint id = 1f027f2f-aa0e-69fa-8012-4ca2d9109f4e
--------------------------------------------------------------------------------
...
Num Messages: 4, Next: ('tools',), checkpoint id = 1f027f2c-627b-6f6e-8003-22208fac7c89
--------------------------------------------------------------------------------
Num Messages: 3, Next: ('chatbot_node',), checkpoint id = 1f027f2c-6122-6190-8002-b745c42a724e
--------------------------------------------------------------------------------
Num Messages: 2, Next: ('tools',), checkpoint id = 1f027f2c-4c4c-6720-8001-8a1c73b894c1
--------------------------------------------------------------------------------
Num Messages: 1, Next: ('chatbot_node',), checkpoint id = 1f027f2c-4a91-6278-8000-56b65f6d77cd
--------------------------------------------------------------------------------
Num Messages: 0, Next: ('__start__',), checkpoint id = 1f027f2c-4a8d-6a1a-bfff-2f7cbde97290
--------------------------------------------------------------------------------

Podemos ver en el historial que el grafo ejecutó todo lo primero que hicimos, pero que luego pisó el historial y volvió a ejecutar desde un punto anterior

Vuelvo a escribir todo el grafo junto

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		import os
import dotenv
 
from typing import Annotated
from typing_extensions import TypedDict
from langgraph.graph.message import add_messages
from langgraph.graph import StateGraph, START, END
from langgraph.prebuilt import ToolNode, tools_condition
from langgraph.checkpoint.memory import MemorySaver
 
from langchain_community.utilities.tavily_search import TavilySearchAPIWrapper
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace
from huggingface_hub import login
os.environ["LANGCHAIN_TRACING_V2"] = "false" # Disable LangSmith tracing
 
from IPython.display import Image, display
 
class State(TypedDict):
    messages: Annotated[list, add_messages]
 
dotenv.load_dotenv()
HUGGINGFACE_TOKEN = os.getenv("HUGGINGFACE_LANGGRAPH")
TAVILY_API_KEY = os.getenv("TAVILY_LANGGRAPH_API_KEY")
 
# Tools
wrapper = TavilySearchAPIWrapper(tavily_api_key=TAVILY_API_KEY)
search_tool = TavilySearchResults(api_wrapper=wrapper, max_results=2)
tools_list = [search_tool]
tool_node = ToolNode(tools=tools_list)
 
# Create the LLM
login(token=HUGGINGFACE_TOKEN)
MODEL = "Qwen/Qwen2.5-72B-Instruct"
model = HuggingFaceEndpoint(
    repo_id=MODEL,
    task="text-generation",
    max_new_tokens=512,
    do_sample=False,
    repetition_penalty=1.03,
)
# Create the chat model
llm = ChatHuggingFace(llm=model)
# Modification: tell the LLM which tools it can call
llm_with_tools = llm.bind_tools(tools_list)
 
# Define the chatbot function
def chatbot_function(state: State):
    message = llm_with_tools.invoke(state["messages"])
    return {"messages": [message]}
 
# Create the graph
graph_builder = StateGraph(State)
 
# Add nodes
graph_builder.add_node("chatbot_node", chatbot_function)
graph_builder.add_node("tools", tool_node)
graph_builder.add_edge("tools", "chatbot_node")
 
# Add edges
graph_builder.add_edge(START, "chatbot_node")
graph_builder.add_conditional_edges("chatbot_node", tools_condition)
 
# Add checkpointer
memory = MemorySaver()
 
# Compile
graph = graph_builder.compile(checkpointer=memory)
 
# Visualize
try:
    display(Image(graph.get_graph().draw_mermaid_png()))
except Exception as e:
    print(f"Error al visualizar el grafo: {e}")
	
	Copied

>_ Output

			
				Error al visualizar el grafo: Failed to reach https://mermaid.ink/ API while trying to render your graph after 1 retries. To resolve this issue:
1. Check your internet connection and try again
2. Try with higher retry settings: `draw_mermaid_png(..., max_retries=5, retry_delay=2.0)`
3. Use the Pyppeteer rendering method which will render your graph locally in a browser: `draw_mermaid_png(..., draw_method=MermaidDrawMethod.PYPPETEER)`

Hacemos la primera llamada al modelo

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		config = {"configurable": {"thread_id": "1"}}
 
user_input = (
    "I'm learning LangGraph. "
    "Could you do some research on it for me?"
)
 
events = graph.stream(
    {"messages": [{"role": "user","content": user_input},],},
    config,
    stream_mode="values",
)
for event in events:
    if "messages" in event:
        event["messages"][-1].pretty_print()
	
	Copied

>_ Output

			
				================================ Human Message =================================
I'm learning LangGraph. Could you do some research on it for me?
================================== Ai Message ==================================
Tool Calls:
  tavily_search_results_json (0)
Call ID: 0
  Args:
    query: LangGraph
================================= Tool Message =================================
Name: tavily_search_results_json
[{"title": "What is LangGraph? - IBM", "url": "https://www.ibm.com/think/topics/langgraph", "content": "LangGraph, created by LangChain, is an open source AI agent framework designed to build, deploy and manage complex generative AI agent workflows. It provides a set of tools and libraries that enable users to create, run and optimize large language models (LLMs) in a scalable and efficient manner. At its core, LangGraph uses the power of graph-based architectures to model and manage the intricate relationships between various components of an AI agent workflow. [...] Agent systems: LangGraph provides a framework for building agent-based systems, which can be used in applications such as robotics, autonomous vehicles or video games.

LLM applications: By using LangGraph’s capabilities, developers can build more sophisticated AI models that learn and improve over time. Norwegian Cruise Line uses LangGraph to compile, construct and refine guest-facing AI solutions. This capability allows for improved and personalized guest experiences. [...] By using a graph-based architecture, LangGraph enables users to scale artificial intelligence workflows without slowing down or sacrificing efficiency. LangGraph uses enhanced decision-making by modeling complex relationships between nodes, which means it uses AI agents to analyze their past actions and feedback. In the world of LLMs, this process is referred to as reflection.", "score": 0.9353998}, {"title": "LangGraph Quickstart - GitHub Pages", "url": "https://langchain-ai.github.io/langgraph/tutorials/introduction/", "content": "[](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-9-1)Assistant: LangGraph is a library designed to help build stateful multi-agent applications using language models. It provides tools for creating workflows and state machines to coordinate multiple AI agents or language model interactions. LangGraph is built on top of LangChain, leveraging its components while adding graph-based coordination capabilities. It's particularly useful for developing more complex, [...] [](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-21-6)   LangGraph is a library designed for building stateful, multi-actor applications with Large Language Models (LLMs). It's particularly useful for creating agent and multi-agent workflows.
[](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-21-7)
[](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-21-8)2. Developer: [...] [](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-48-19)LangGraph is likely a framework or library designed specifically for creating AI agents with advanced capabilities. Here are a few points to consider based on this recommendation:
[](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-48-20)", "score": 0.9328032}]
================================== Ai Message ==================================
Tool Calls:
  tavily_search_results_json (0)
Call ID: 0
  Args:
    query: LangGraph
================================= Tool Message =================================
Name: tavily_search_results_json
[{"title": "What is LangGraph? - IBM", "url": "https://www.ibm.com/think/topics/langgraph", "content": "LangGraph, created by LangChain, is an open source AI agent framework designed to build, deploy and manage complex generative AI agent workflows. It provides a set of tools and libraries that enable users to create, run and optimize large language models (LLMs) in a scalable and efficient manner. At its core, LangGraph uses the power of graph-based architectures to model and manage the intricate relationships between various components of an AI agent workflow. [...] Agent systems: LangGraph provides a framework for building agent-based systems, which can be used in applications such as robotics, autonomous vehicles or video games.

LLM applications: By using LangGraph’s capabilities, developers can build more sophisticated AI models that learn and improve over time. Norwegian Cruise Line uses LangGraph to compile, construct and refine guest-facing AI solutions. This capability allows for improved and personalized guest experiences. [...] By using a graph-based architecture, LangGraph enables users to scale artificial intelligence workflows without slowing down or sacrificing efficiency. LangGraph uses enhanced decision-making by modeling complex relationships between nodes, which means it uses AI agents to analyze their past actions and feedback. In the world of LLMs, this process is referred to as reflection.", "score": 0.9353998}, {"title": "LangGraph Quickstart - GitHub Pages", "url": "https://langchain-ai.github.io/langgraph/tutorials/introduction/", "content": "[](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-9-1)Assistant: LangGraph is a library designed to help build stateful multi-agent applications using language models. It provides tools for creating workflows and state machines to coordinate multiple AI agents or language model interactions. LangGraph is built on top of LangChain, leveraging its components while adding graph-based coordination capabilities. It's particularly useful for developing more complex, [...] [](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-21-6)   LangGraph is a library designed for building stateful, multi-actor applications with Large Language Models (LLMs). It's particularly useful for creating agent and multi-agent workflows.
[](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-21-7)
[](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-21-8)2. Developer: [...] [](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-48-19)LangGraph is likely a framework or library designed specifically for creating AI agents with advanced capabilities. Here are a few points to consider based on this recommendation:
[](https://langchain-ai.github.io/langgraph/tutorials/introduction/#__codelineno-48-20)", "score": 0.9328032}]
================================== Ai Message ==================================
LangGraph is an open-source AI agent framework developed by LangChain, designed to build, deploy, and manage complex generative AI agent workflows. Here are some key points about LangGraph:
### Overview
- **Purpose**: LangGraph is aimed at creating, running, and optimizing large language models (LLMs) in a scalable and efficient manner.
- **Graph-Based Architecture**: It uses graph-based architectures to model and manage the intricate relationships between various components of an AI agent workflow.
### Features
- **Agent Systems**: LangGraph provides a framework for building agent-based systems, which can be used in applications such as robotics, autonomous vehicles, or video games.
- **LLM Applications**: Developers can build more sophisticated AI models that learn and improve over time. For example, Norwegian Cruise Line uses LangGraph to compile, construct, and refine guest-facing AI solutions, enhancing personalized guest experiences.
- **Scalability**: By using a graph-based architecture, LangGraph enables users to scale artificial intelligence workflows without sacrificing efficiency.
- **Enhanced Decision-Making**: LangGraph uses AI agents to analyze their past actions and feedback, a process referred to as "reflection" in the context of LLMs.
### Developer Resources
- **Quickstart Guide**: The LangGraph Quickstart guide on GitHub provides a detailed introduction to building stateful multi-agent applications using language models. It covers tools for creating workflows and state machines to coordinate multiple AI agents or language model interactions.
- **Built on LangChain**: LangGraph is built on top of LangChain, leveraging its components while adding graph-based coordination capabilities. This makes it particularly useful for developing more complex, stateful, multi-actor applications with LLMs.
### Further Reading
- **What is LangGraph? - IBM**: [Link](https://www.ibm.com/think/topics/langgraph)
- **LangGraph Quickstart - GitHub Pages**: [Link](https://langchain-ai.github.io/langgraph/tutorials/introduction/)
These resources should provide a solid foundation for understanding and getting started with LangGraph. If you have any specific questions or need further details, feel free to ask!

Y ahora la segunda llamada

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		user_input = (
    "Ya that's helpful. Maybe I'll "
    "build an autonomous agent with it!"
)
 
events = graph.stream(
    {"messages": [{"role": "user","content": user_input},],},
    config,
    stream_mode="values",
)
for event in events:
    if "messages" in event:
        event["messages"][-1].pretty_print()
	
	Copied

>_ Output

			
				================================ Human Message =================================
Ya that's helpful. Maybe I'll build an autonomous agent with it!
================================== Ai Message ==================================
That sounds like an exciting project! Building an autonomous agent using LangGraph can be a rewarding experience. Here are some steps and tips to help you get started:
### 1. **Understand the Basics of LangGraph**
- **Read the Documentation**: Start with the official LangGraph documentation and quickstart guide. This will give you a solid understanding of the framework's capabilities and how to use its tools.
  - **Quickstart Guide**: [LangGraph Quickstart - GitHub Pages](https://langchain-ai.github.io/langgraph/tutorials/introduction/)
### 2. **Set Up Your Development Environment**
- **Install LangChain and LangGraph**: Ensure you have the necessary dependencies installed. LangGraph is built on top of LangChain, so you'll need to set up both.
  ```bash
  pip install langchain langgraph
  ```
### 3. **Define Your Agent's Objectives**
- **Identify the Use Case**: What specific tasks do you want your autonomous agent to perform? This could be anything from navigating a virtual environment, responding to user queries, or managing a robotic system.
- **Define the State and Actions**: Determine the states your agent can be in and the actions it can take. This will help you design the state machine and workflows.
### 4. **Design the Graph-Based Workflow**
- **Create Nodes and Edges**: In LangGraph, you'll define nodes (agents or components) and edges (interactions or transitions). Each node can represent a different part of your agent's functionality.
- **Define State Transitions**: Use the graph-based architecture to define how the agent transitions between different states based on actions and events.
### 5. **Implement the Agent**
- **Write the Code**: Start coding your agent using the LangGraph library. You can use the provided tools to create and manage the agent's workflows.
...
- **Deploy the Agent**: Once you are satisfied with the performance, you can deploy your agent in the real world or a production environment.
- **Monitor and Maintain**: Continuously monitor the agent's performance and make adjustments as needed. Use feedback loops to improve the agent over time.
### 8. **Community and Support**
- **Join the Community**: Engage with the LangChain and LangGraph community. You can find support, share ideas, and get feedback from other developers.
  - **GitHub**: [LangGraph GitHub](https://github.com/langchain-ai/langgraph)
  - **Forums and Discussion Boards**: Check out forums and discussion boards related to LangGraph and LangChain.
### Additional Resources
- **Tutorials and Examples**: Look for tutorials and example projects to get more hands-on experience.
- **Research Papers and Articles**: Read research papers and articles to deepen your understanding of AI agent design and graph-based architectures.
Good luck with your project! If you have any specific questions or need further guidance, feel free to ask.

Vemos el historial del estado

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		to_replay = None
for state in graph.get_state_history(config):
    print(f"Num Messages: {len(state.values["messages"])}, Next: {state.next}, checkpoint id = {state.config["configurable"]['checkpoint_id']}")
    print("-" * 80)
 
    # Get state when first iteracction us done
    if len(state.next) == 0:
        to_replay = state
	
	Copied

>_ Output

			
				Num Messages: 8, Next: (), checkpoint id = 1f03263e-a96c-6446-8008-d2c11df0b6cb
--------------------------------------------------------------------------------
Num Messages: 7, Next: ('chatbot_node',), checkpoint id = 1f03263d-7a35-6660-8007-a37d4b584c88
--------------------------------------------------------------------------------
Num Messages: 6, Next: ('__start__',), checkpoint id = 1f03263d-7a32-624e-8006-6509bbf32ebe
--------------------------------------------------------------------------------
Num Messages: 6, Next: (), checkpoint id = 1f03263d-7a1a-6f36-8005-f10b5d83f22c
--------------------------------------------------------------------------------
Num Messages: 5, Next: ('chatbot_node',), checkpoint id = 1f03263c-c53f-6666-8004-c6d35868dd73
--------------------------------------------------------------------------------
Num Messages: 4, Next: ('tools',), checkpoint id = 1f03263c-b14b-68f8-8003-28558fa38dbc
--------------------------------------------------------------------------------
Num Messages: 3, Next: ('chatbot_node',), checkpoint id = 1f03263c-a66b-6276-8002-2dc89fca4d99
--------------------------------------------------------------------------------
Num Messages: 2, Next: ('tools',), checkpoint id = 1f03263c-8c7c-68ec-8001-fb8a9aa300b0
--------------------------------------------------------------------------------
Num Messages: 1, Next: ('chatbot_node',), checkpoint id = 1f03263c-6d06-68d2-8000-ced2e7b8538f
--------------------------------------------------------------------------------
Num Messages: 0, Next: ('__start__',), checkpoint id = 1f03263c-6cdb-63e4-bfff-c644b57cee28
--------------------------------------------------------------------------------

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		print(to_replay.config)
	
	Copied

>_ Output

			
				{'configurable': {'thread_id': '1', 'checkpoint_ns': '', 'checkpoint_id': '1f03263d-7a1a-6f36-8005-f10b5d83f22c'}}

Dando este checkpoint_id a LangGraph carga el estado en ese momento del flujo. Así que creamos un nuevo mensaje y se lo pasamos al grafo

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		user_input = (
    "Thanks"
)
 
# The `checkpoint_id` in the `to_replay.config` corresponds to a state we've persisted to our checkpointer.
events = graph.stream({"messages": [{"role": "user","content": user_input},],},
    to_replay.config,
    stream_mode="values",
)
 
for event in events:
    if "messages" in event:
        event["messages"][-1].pretty_print()
	
	Copied

>_ Output

			
				================================ Human Message =================================
Thanks
================================== Ai Message ==================================
You're welcome! If you have any more questions about LangGraph or any other topic, feel free to reach out. Happy learning! 😊

	
		
			< >
			Input
		
		
			Python
			
		
	
	
		for state in graph.get_state_history(config):
    print(f"Num Messages: {len(state.values["messages"])}, Next: {state.next}, checkpoint id = {state.config["configurable"]['checkpoint_id']}")
    print("-" * 80)
	
	Copied

>_ Output

			
				Num Messages: 8, Next: (), checkpoint id = 1f03263f-fcb9-63a0-8008-e8c4a3fb44f9
--------------------------------------------------------------------------------
Num Messages: 7, Next: ('chatbot_node',), checkpoint id = 1f03263f-eb3b-663c-8007-72da4d16bf64
--------------------------------------------------------------------------------
Num Messages: 6, Next: ('__start__',), checkpoint id = 1f03263f-eb36-6ac4-8006-a2333805d5d6
--------------------------------------------------------------------------------
Num Messages: 8, Next: (), checkpoint id = 1f03263e-a96c-6446-8008-d2c11df0b6cb
--------------------------------------------------------------------------------
Num Messages: 7, Next: ('chatbot_node',), checkpoint id = 1f03263d-7a35-6660-8007-a37d4b584c88
--------------------------------------------------------------------------------
Num Messages: 6, Next: ('__start__',), checkpoint id = 1f03263d-7a32-624e-8006-6509bbf32ebe
--------------------------------------------------------------------------------
Num Messages: 6, Next: (), checkpoint id = 1f03263d-7a1a-6f36-8005-f10b5d83f22c
--------------------------------------------------------------------------------
Num Messages: 5, Next: ('chatbot_node',), checkpoint id = 1f03263c-c53f-6666-8004-c6d35868dd73
--------------------------------------------------------------------------------
Num Messages: 4, Next: ('tools',), checkpoint id = 1f03263c-b14b-68f8-8003-28558fa38dbc
--------------------------------------------------------------------------------
Num Messages: 3, Next: ('chatbot_node',), checkpoint id = 1f03263c-a66b-6276-8002-2dc89fca4d99
--------------------------------------------------------------------------------
Num Messages: 2, Next: ('tools',), checkpoint id = 1f03263c-8c7c-68ec-8001-fb8a9aa300b0
--------------------------------------------------------------------------------
Num Messages: 1, Next: ('chatbot_node',), checkpoint id = 1f03263c-6d06-68d2-8000-ced2e7b8538f
--------------------------------------------------------------------------------
Num Messages: 0, Next: ('__start__',), checkpoint id = 1f03263c-6cdb-63e4-bfff-c644b57cee28
--------------------------------------------------------------------------------

---

🎉 **Has completado la _Guía completa de LangGraph_.** Repasa los capítulos: Parte 1 · Parte 2 · Parte 3.

Seguir leyendo

Deep Research con LangGraph (3/3): agente Writer e informe final

Tercera y última parte de la serie Deep Research con LangGraph. Implementa el agente Writer que redacta el informe final a partir de la investigación, integra todo el grafo del deep researcher y ejecuta el asistente completo de principio a fin.

Deep Research con LangGraph (2/3): Research Supervisor multiagente

Segunda parte de la serie Deep Research con LangGraph. Construye el Research Supervisor que coordina varios agentes Rese...

Deep Research con LangGraph (1/3): agentes Scope y Researcher

Primera parte de la serie para crear un asistente de investigación con LangGraph. Conoce la arquitectura del sistema y c...

Últimos posts -->

¿Has visto estos proyectos?

Gymnasia

Horeca chatbot

Naviground

Ver todos los proyectos -->

>_ Disponible para proyectos

¿Tienes un proyecto con IA?

Hablemos.

maximofn@gmail.com

Especialista en Machine Learning e Inteligencia Artificial. Desarrollo soluciones con IA generativa, agentes inteligentes y modelos personalizados.

Escríbeme LinkedIn

¿Quieres ver alguna charla?

Agentes del Mañana: Descifrando los Enigmas de Planificación, UX y Memoria

Los agentes IA, impulsados por LLMs, prometen transformar aplicaciones. Pero, ¿son hoy simples ejecutores o futuros colaboradores inteligentes? Para a...

Crea tu propio Apple intelligence

Aprende a crear un sistema de IA para ejecutar eficientemente en un dispositivo

Últimas charlas -->

¿Quieres mejorar con estos tips?

Buenas prácticas creando agentes con Claude Code

Charla técnica: skills, subagentes, slash commands y MCPs en Claude Code

o1 prompt engineering

Crear mejores prompts para o1 siguiendo un ejemplo

Memory profiler

Ver el uso de memoria de un script

Últimos tips -->

Usa esto en local

Los espacios de Hugging Face nos permite ejecutar modelos con demos muy sencillas, pero ¿qué pasa si la demo se rompe? O si el usuario la elimina? Por ello he creado contenedores docker con algunos espacios interesantes, para poder usarlos de manera local, pase lo que pase. De hecho, es posible que si pinchas en alún botón de ver proyecto te lleve a un espacio que no funciona.

Flow edit

FLUX.1-RealismLora

token_hmr

Ver todos los contenedores -->

>_ Disponible para proyectos

¿Tienes un proyecto con IA?

Hablemos.

maximofn@gmail.com

Especialista en Machine Learning e Inteligencia Artificial. Desarrollo soluciones con IA generativa, agentes inteligentes y modelos personalizados.

Escríbeme LinkedIn

¿Quieres entrenar tu modelo con estos datasets?

short-jokes-dataset

HuggingFace

Dataset de chistes en inglés

Uso: Fine-tuning de modelos de generación de texto humorístico

231K filas 2 columnas 45 MB

Ver en HuggingFace →

opus100

HuggingFace

Dataset con traducciones de inglés a español

Uso: Entrenamiento de modelos de traducción inglés-español

1M filas 2 columnas 210 MB

Ver en HuggingFace →

netflix_titles

HuggingFace

Dataset con películas y series de Netflix

Uso: Análisis de catálogo de Netflix y sistemas de recomendación

8.8K filas 12 columnas 3.5 MB

Ver en HuggingFace →

Ver más datasets -->