text stringlengths 35 16k |
|---|
human: What are the key aspects of Actors?
bot: An **actor** is a [PregelNode](../../reference/pregel/#langgraph.pregel.PregelNode). It subscribes to channels, reads data from them, and writes data to them. It can be thought of as an **actor** in the Pregel algorithm. [PregelNodes](../../reference/pregel/#langgraph.p... |
human: What is Cookie consent?
bot: We use cookies to recognize your repeated visits and preferences, as well as to measure the effectiveness of our documentation and whether users find what they're searching for. **Clicking "Accept" makes our documentation better. Thank you!** * Google Analytics * GitHub Accept Reje... |
human: What are the key aspects of LangGraph Framework?
bot: * **[LangGraph Concepts](../../concepts)** : Learn the foundational concepts of LangGraph. * **[LangGraph How-to Guides](../../how-tos)** : Guides for common tasks with LangGraph. |
human: How does Cookie consent work?
bot: We use cookies to recognize your repeated visits and preferences, as well as to measure the effectiveness of our documentation and whether users find what they're searching for. **Clicking "Accept" makes our documentation better. Thank you!** * Google Analytics * GitHub Accep... |
human: Tell me about Cookie consent.
bot: We use cookies to recognize your repeated visits and preferences, as well as to measure the effectiveness of our documentation and whether users find what they're searching for. **Clicking "Accept" makes our documentation better. Thank you!** * Google Analytics * GitHub Accep... |
human: What is Cookie consent?
bot: We use cookies to recognize your repeated visits and preferences, as well as to measure the effectiveness of our documentation and whether users find what they're searching for. **Clicking "Accept" makes our documentation better. Thank you!** * Google Analytics * GitHub Accept Reje... |
human: Tell me about Cookie consent.
bot: We use cookies to recognize your repeated visits and preferences, as well as to measure the effectiveness of our documentation and whether users find what they're searching for. **Clicking "Accept" makes our documentation better. Thank you!** * Google Analytics * GitHub Accep... |
human: Tell me about How to interact with the deployment using RemoteGraph.
bot: Prerequisites * [LangGraph Platform](../../concepts/langgraph_platform/) * [LangGraph Server](../../concepts/langgraph_server/) `RemoteGraph` is an interface that allows you to interact with your LangGraph Platform deployment as if it we... |
human: What is Helm Chart?
bot: If you would like to deploy LangGraph Cloud on Kubernetes, you can use this . |
human: Can you explain Human-in-the-loop?
bot: [Human-in-the-loop](../concepts/human_in_the_loop/) functionality allows you to involve humans in the decision-making process of your graph. These how-to guides show how to implement human-in-the-loop workflows in your graph. Key workflows: * [How to wait for user input]... |
human: Can you explain How to use the pre-built ReAct agent?
bot: Prerequisites This guide assumes familiarity with the following: * * * In this how-to we'll create a simple agent app that can check the weather. The app consists of an agent (LLM) and tools. As we interact with the app, we will first call the agent (L... |
human: How does Comments work?
bot: Back to top [ Previous How to Deploy a Standalone Container ](../../cloud/deployment/standalone_container/) [ Next How to interact with the deployment using RemoteGraph ](../use-remote-graph/) Copyright (C) 2025 LangChain, Inc | Consent Preferences Made with |
human: Tell me about Design Patterns.
bot: There are typically three different **actions** that you can do with a human-in-the-loop workflow: 1. **Approve or Reject** : Pause the graph before a critical step, such as an API call, to review and approve the action. If the action is rejected, you can prevent the graph f... |
human: Can you explain Structured Output?
bot: Structured outputs with LLMs work by providing a specific format or schema that the LLM should follow in its response. This is similar to tool calling, but more general. While tool calling typically involves selecting and using predefined functions, structured outputs ca... |
human: What are the key aspects of Comments?
bot: Back to top [ Previous How to review tool calls (Functional API) ](../review-tool-calls-functional/) [ Next How to stream LLM tokens from your graph ](../streaming-tokens/) Copyright (C) 2025 LangChain, Inc | Consent Preferences Made with |
human: What are the key aspects of Comments?
bot: Back to top [ Previous How to build a multi-agent network ](../multi-agent-network/) [ Next How to build a multi-agent network (functional API) ](../multi-agent-network-functional/) Copyright (C) 2025 LangChain, Inc | Consent Preferences Made with |
human: How does Requirements work?
bot: * You’re using AWS already. * You use `langgraph-cli` and/or [LangGraph Studio](../langgraph_studio/) app to test graph locally. * You use `langgraph build` command to build image and then push it to your AWS ECR repository (`docker push`). |
human: Tell me about Default Reducer.
bot: These two examples show how to use the default reducer: **Example A:** from typing_extensions import TypedDict class State(TypedDict): foo: int bar: list[str] In this example, no reducer functions are specified for any key. Let's assume the input to the graph is `{"foo": 1, ... |
human: What is Accept a tool call?
bot: To accept a tool call, we just indicate in the data we provide in the `Command` that the tool call should pass through. config = {"configurable": {"thread_id": "1"}} user_message = {"role": "user", "content": "What's the weather in san francisco?"} print(user_message) for step ... |
human: How does Comments work?
bot: Back to top [ Previous How to stream LLM tokens from your graph ](../streaming-tokens/) [ Next How to stream data from within a tool ](../streaming-events-from-within-tools/) Copyright (C) 2025 LangChain, Inc | Consent Preferences Made with |
human: Tell me about Usage.
bot: Now we can run our graph to check that it worked as intended: answer = graph.invoke(input={"messages": [("human", "what's the weather in SF?")]})[ "final_response" ] answer WeatherResponse(temperature=75.0, wind_directon='SE', wind_speed=3.0) Again, the agent returned a `WeatherRespon... |
human: How does Test the API work?
bot: Python SDK (Async)Python SDK (Sync)Javascript SDKRest API **Install the LangGraph Python SDK** pip install langgraph-sdk **Send a message to the assistant (threadless run)** from langgraph_sdk import get_client client = get_client(url="http://localhost:2024") async for chunk in... |
human: What is Docker issues?
bot: LangGraph Studio (desktop) requires Docker Desktop version 4.24 or higher. Please make sure you have a version of Docker installed that satisfies that requirement and also make sure you have the Docker Desktop app up and running before trying to use LangGraph Studio. In addition, ma... |
human: What are the key aspects of Code?
bot: # First we initialize the model we want to use. from langchain_openai import ChatOpenAI model = ChatOpenAI(model="gpt-4o", temperature=0) # For this tutorial we will use custom tool that returns pre-defined values for weather in two cities (NYC & SF) from langchain_core.t... |
human: What is Part 6: Time Travel?
bot: In a typical chat bot workflow, the user interacts with the bot 1 or more times to accomplish a task. In the previous sections, we saw how to add memory and a human-in-the-loop to be able to checkpoint our graph state and control future responses. But what if you want to let y... |
human: What are the key aspects of How to add runtime configuration to your graph?
bot: Sometimes you want to be able to configure your agent when calling it. Examples of this include configuring which LLM to use. Below we walk through an example of doing so. Prerequisites This guide assumes familiarity with the foll... |
human: Can you explain Cookie consent?
bot: We use cookies to recognize your repeated visits and preferences, as well as to measure the effectiveness of our documentation and whether users find what they're searching for. **Clicking "Accept" makes our documentation better. Thank you!** * Google Analytics * GitHub Acc... |
human: What are the key aspects of Add a node function that invokes the subgraph?
bot: For more complex systems you might want to define subgraphs that have a completely different schema from the parent graph (no shared keys). For example, in a multi-agent RAG system, a search agent might only need to keep track of q... |
human: Can you explain Comments?
bot: Back to top [ Previous LangGraph Data Plane ](../langgraph_data_plane/) [ Next LangGraph Studio ](../langgraph_studio/) Copyright (C) 2025 LangChain, Inc | Consent Preferences Made with |
human: How does Self-Hosted Lite work?
bot: The Self-Hosted Lite version is a limited version of LangGraph Platform that you can run locally or in a self-hosted manner (up to 1 million nodes executed per year). When using the Self-Hosted Lite version, you authenticate with a API key. |
human: Tell me about Install Dependencies.
bot: In the root of your new LangGraph app, install the dependencies in `edit` mode so your local changes are used by the server: pip install -e . |
human: What are the key aspects of Set up the State?
bot: The main type of graph in `langgraph` is the . This graph is parameterized by a `State` object that it passes around to each node. Each node then returns operations the graph uses to `update` that state. These operations can either SET specific attributes on t... |
human: What is How are LangGraph and LangGraph Platform different??
bot: LangGraph is a stateful, orchestration framework that brings added control to agent workflows. LangGraph Platform is a service for deploying and scaling LangGraph applications, with an opinionated API for building agent UXs, plus an integrated d... |
human: Tell me about Authentication vs Authorization.
bot: While often used interchangeably, these terms represent distinct security concepts: * **Authentication** ("AuthN") verifies _who_ you are. This runs as middleware for every request. * **Authorization** ("AuthZ") determines _what you can do_. This validates th... |
human: What are the key aspects of Use it!?
bot: Let's now try running our agent. We'll need to provide user ID in the config so that our tool knows what information to look up: for chunk in agent.stream( {"messages": [("user", "hi, what should i do this weekend?")]}, # provide user ID in the config {"configurable": ... |
human: What are the key aspects of Setup?
bot: First, let's install the required packages and set our API keys %%capture --no-stderr %pip install -U langgraph langchain-openai import getpass import os def _set_env(var: str): if not os.environ.get(var): os.environ[var] = getpass.getpass(f"{var}: ") _set_env("OPENAI_AP... |
human: How does Cookie consent work?
bot: We use cookies to recognize your repeated visits and preferences, as well as to measure the effectiveness of our documentation and whether users find what they're searching for. **Clicking "Accept" makes our documentation better. Thank you!** * Google Analytics * GitHub Accep... |
human: How does Disable Indexing for Specific Memories work?
bot: Some memories shouldn't be searchable by content. You can disable indexing for these while still storing them using `put(..., index=False)`. Example: store = InMemoryStore(index={"embed": embeddings, "dims": 1536, "fields": ["memory"]}) # Store a norma... |
human: Can you explain Validating human input?
bot: If you need to validate the input provided by the human within the graph itself (rather than on the client side), you can achieve this by using multiple interrupt calls within a single node. from langgraph.types import interrupt def human_node(state: State): """Huma... |
human: What are the key aspects of Setup?
bot: %%capture --no-stderr %pip install --quiet -U langgraph langchain_openai import getpass import os def _set_env(var: str): if not os.environ.get(var): os.environ[var] = getpass.getpass(f"{var}: ") _set_env("OPENAI_API_KEY") OPENAI_API_KEY: Set up for LangGraph development... |
human: What is Standalone Container?
bot: The [Standalone Container](../langgraph_standalone_container/) deployment option is the least restrictive model for deployment. Deploy standalone instances of a LangGraph Server in your cloud. Build a Docker image using the [LangGraph CLI](../langgraph_cli/) and deploy your L... |
human: What are the key aspects of Human-in-the-loop?
bot: When designing complex graphs, relying entirely on the LLM for decision-making can be risky, particularly when it involves tools that interact with files, APIs, or databases. These interactions may lead to unintended data access or modifications, depending on... |
human: What are the key aspects of Routing?
bot: Routing classifies an input and directs it to a followup task. As noted in the Anthropic blog on `Building Effective Agents`: > Routing classifies an input and directs it to a specialized followup task. This workflow allows for separation of concerns, and building more... |
human: Can you explain Cookie consent?
bot: We use cookies to recognize your repeated visits and preferences, as well as to measure the effectiveness of our documentation and whether users find what they're searching for. **Clicking "Accept" makes our documentation better. Thank you!** * Google Analytics * GitHub Acc... |
human: Can you explain Serialization?
bot: In addition to keeping track of message IDs, the `add_messages` function will also try to deserialize messages into LangChain `Message` objects whenever a state update is received on the `messages` channel. See more information on LangChain serialization/deserialization . Th... |
human: Can you explain `entrypoint.final`?
bot: [entrypoint.final](../../reference/func/#langgraph.func.entrypoint.final) is a special primitive that can be returned from an entrypoint and allows **decoupling** the value that is **saved in the checkpoint** from the **return value of the entrypoint**. The first value ... |
human: Can you explain Handoffs as tools?
bot: One of the most common agent types is a ReAct-style tool-calling agents. For those types of agents, a common pattern is wrapping a handoff in a tool call, e.g.: def transfer_to_bob(state): """Transfer to bob.""" return Command( goto="bob", update={"my_state_key": "my_sta... |
human: What is Cookie consent?
bot: We use cookies to recognize your repeated visits and preferences, as well as to measure the effectiveness of our documentation and whether users find what they're searching for. **Clicking "Accept" makes our documentation better. Thank you!** * Google Analytics * GitHub Accept Reje... |
human: Tell me about Persistence.
bot: LangGraph has a built-in persistence layer, implemented through checkpointers. When you compile graph with a checkpointer, the checkpointer saves a `checkpoint` of the graph state at every super-step. Those checkpoints are saved to a `thread`, which can be accessed after graph e... |
human: How does Build the Docker Image work?
bot: Please read the [Application Structure](../../concepts/application_structure/) guide to understand how to structure your LangGraph application. If the application is structured correctly, you can build a docker image with the LangGraph Deploy server. To build the dock... |
human: What is Serializer?
bot: When checkpointers save the graph state, they need to serialize the channel values in the state. This is done using serializer objects. `langgraph_checkpoint` defines [protocol](../../reference/checkpoints/#langgraph.checkpoint.serde.base.SerializerProtocol) for implementing serializer... |
human: How does Cloud SaaS work?
bot: To deploy a [LangGraph Server](../langgraph_server/), follow the how-to guide for [how to deploy to Cloud SaaS](../../cloud/deployment/cloud/). |
human: Can you explain With a connection string?
bot: async with AsyncPostgresSaver.from_conn_string(DB_URI) as checkpointer: graph = create_react_agent(model, tools=tools, checkpointer=checkpointer) config = {"configurable": {"thread_id": "6"}} res = await graph.ainvoke( {"messages": [("human", "what's the weather i... |
human: What are the key aspects of Comments?
bot: Back to top [ Previous Deployment Options ](../deployment_options/) [ Next Template Applications ](../template_applications/) Copyright (C) 2025 LangChain, Inc | Consent Preferences Made with |
human: What is Setup?
bot: First, let's install the required packages and set our API keys %%capture --no-stderr %pip install -U langgraph langchain-openai import getpass import os def _set_env(var: str): if not os.environ.get(var): os.environ[var] = getpass.getpass(f"{var}: ") _set_env("OPENAI_API_KEY") Set up for L... |
human: How does Define model and tools for the graph work?
bot: from typing import Literal from langchain_core.tools import tool from langchain_openai import ChatOpenAI from langgraph.prebuilt import create_react_agent from langgraph.checkpoint.postgres import PostgresSaver from langgraph.checkpoint.postgres.aio impo... |
human: Tell me about Process state updates with reducers.
bot: Each key in the state can have its own independent [reducer](../../concepts/low_level/#reducers) function, which controls how updates from nodes are applied. If no reducer function is explicitly specified then it is assumed that all updates to the key sho... |
human: What is Comments?
bot: Back to top [ Previous How to run a graph asynchronously ](../async/) [ Next How to pass custom run ID or set tags and metadata for graph runs in LangSmith ](../run-id-langsmith/) Copyright (C) 2025 LangChain, Inc | Consent Preferences Made with |
human: How does Example work?
bot: from typing import TypedDict from langgraph.graph import START, StateGraph, MessagesState from langchain_openai import ChatOpenAI model = ChatOpenAI(model="gpt-4o-mini") class State(TypedDict): topic: str joke: str poem: str def write_joke(state: State): topic = state["topic"] joke_... |
human: What are the key aspects of Server scalability?
bot: As you add more instances to a service, they will share the HTTP load as long as an appropriate load balancer mechanism is placed in front of them. In most deployment modalities we configure a load balancer for the service automatically. In the “self-hosted ... |
human: Tell me about Add a node with the compiled subgraph.
bot: A common case is for the parent graph and subgraph to communicate over a shared state key (channel). For example, in systems, the agents often communicate over a shared key. If your subgraph shares state keys with the parent graph, you can follow these ... |
human: What are the key aspects of Using with a prebuilt ReAct agent?
bot: Let's now see how we can implement the same team of travel agents, but give each of the agents some tools to call. We'll be using prebuilt [`create_react_agent`](../../reference/prebuilt/#langgraph.prebuilt.chat_agent_executor.create_react_age... |
human: Tell me about Serialization.
bot: There are two key aspects to serialization in LangGraph: 1. `@entrypoint` inputs and outputs must be JSON-serializable. 2. `@task` outputs must be JSON-serializable. These requirements are necessary for enabling checkpointing and workflow resumption. Use python primitives like... |
human: What are the key aspects of Helm Chart?
bot: If you would like to deploy LangGraph Cloud on Kubernetes, you can use this . |
human: How does Add thread-level persistence work?
bot: Adding [thread-level persistence](../../concepts/persistence#threads) lets us support conversational experiences with our agent: subsequent invocations will append to the prior messages list, retaining the full conversational context. To add thread-level persist... |
human: Can you explain Define child?
bot: class ChildState(TypedDict): my_child_key: str def call_grandchild_graph(state: ChildState) -> ChildState: # NOTE: parent or grandchild keys won't be accessible here # we're transforming the state from the child state channels (`my_child_key`) # to the child state channels (`... |
human: Can you explain Setup?
bot: First, let's install the required packages %%capture --no-stderr %pip install -U langgraph langchain-anthropic import getpass import os def _set_env(var: str): if not os.environ.get(var): os.environ[var] = getpass.getpass(f"{var}: ") _set_env("ANTHROPIC_API_KEY") ANTHROPIC_API_KEY: ... |
human: How does Comments work?
bot: Back to top [ Previous How to create a sequence of steps ](../sequence/) [ Next How to create and control loops ](../recursion-limit/) Copyright (C) 2025 LangChain, Inc | Consent Preferences Made with |
human: Can you explain Postgres resilience?
bot: For deployment modalities where we manage the Postgres database we have periodic backups, continuously replicated standby replicas for automatic failover. Optionally, on request, we can also setup read replicas as well as other advanced failover capabilities. All commu... |
human: Can you explain Generate a custom ToolMessage?
bot: To Generate a custom `ToolMessage`, we supply the content of the message. In this case we will ask the model to reformat its tool call. config = {"configurable": {"thread_id": "3"}} user_message = {"role": "user", "content": "What's the weather in san francis... |
human: How does How to view and update state in subgraphs work?
bot: Prerequisites This guide assumes familiarity with the following: * * * Once you add [persistence](../subgraph-persistence), you can easily view and update the state of the subgraph at any point in time. This enables a lot of the human-in-the-loop in... |
human: Can you explain Time Travel?
bot: [Time travel](../concepts/time-travel/) allows you to replay past actions in your LangGraph application to explore alternative paths and debug issues. These how-to guides show how to use time travel in your graph. * [How to view and update past graph state](human_in_the_loop/t... |
human: What is Manually deleting messages?
bot: First, we will cover how to manually delete messages. Let's take a look at the current state of the thread: messages = app.get_state(config).values["messages"] messages [HumanMessage(content="hi! I'm bob", additional_kwargs={}, response_metadata={}, id='db576005-3a60-4b... |
human: What are the key aspects of Setup?
bot: First, let's install the required packages and set our API keys %%capture --no-stderr %pip install --quiet -U langgraph langchain_openai import getpass import os def _set_env(var: str): if not os.environ.get(var): os.environ[var] = getpass.getpass(f"{var}: ") _set_env("O... |
human: What are the key aspects of High Level?
bot: * [Why LangGraph Platform?](langgraph_platform/): The LangGraph platform is an opinionated way to deploy and manage LangGraph applications. This guide provides an overview of the key features and concepts behind LangGraph Platform. * [Platform Architecture](platform... |
human: Tell me about How to pass private state between nodes.
bot: Prerequisites This guide assumes familiarity with the following: * In some cases, you may want nodes to exchange information that is crucial for intermediate logic but doesn’t need to be part of the main schema of the graph. This private data is not r... |
human: Tell me about Versioning Assistants.
bot: Once you've created an assistant, you can save and version it to track changes to the configuration over time. You can think about this at three levels: 1) The graph lays out the general agent application logic 2) The agent configuration options represent parameters th... |
human: Tell me about Define graph.
bot: We will be using a single-node graph that calls a . Let's first define the model we'll be using: from langchain_anthropic import ChatAnthropic model = ChatAnthropic(model="claude-3-5-sonnet-20240620") API Reference: Now we can define our `StateGraph` and add our model-calling n... |
human: What are the key aspects of Cookie consent?
bot: We use cookies to recognize your repeated visits and preferences, as well as to measure the effectiveness of our documentation and whether users find what they're searching for. **Clicking "Accept" makes our documentation better. Thank you!** * Google Analytics ... |
human: How does Collection work?
bot: Alternatively, memories can be a collection of documents that are continuously updated and extended over time. Each individual memory can be more narrowly scoped and easier to generate, which means that you're less likely to **lose** information over time. It's easier for an LLM ... |
human: What are the key aspects of Cookie consent?
bot: We use cookies to recognize your repeated visits and preferences, as well as to measure the effectiveness of our documentation and whether users find what they're searching for. **Clicking "Accept" makes our documentation better. Thank you!** * Google Analytics ... |
human: What is Cookie consent?
bot: We use cookies to recognize your repeated visits and preferences, as well as to measure the effectiveness of our documentation and whether users find what they're searching for. **Clicking "Accept" makes our documentation better. Thank you!** * Google Analytics * GitHub Accept Reje... |
human: What is `values`?
bot: These are the values that will be used to update the state. Note that this update is treated exactly as any update from a node is treated. This means that these values will be passed to the [reducer](../low_level/#reducers) functions, if they are defined for some of the channels in the g... |
human: Can you explain Create a LangGraph App?
bot: Create a new app from the `react-agent` template. This template is a simple agent that can be flexibly extended to many tools. Python ServerNode Server langgraph new path/to/your/app --template react-agent-python langgraph new path/to/your/app --template react-agent... |
human: What is Comments?
bot: Back to top [ Previous LangGraph Server ](../langgraph_server/) [ Next LangGraph CLI ](../langgraph_cli/) Copyright (C) 2025 LangChain, Inc | Consent Preferences Made with |
human: What are the key aspects of How to add summary of the conversation history?
bot: One of the most common use cases for persistence is to use it to keep track of conversation history. This is great - it makes it easy to continue conversations. As conversations get longer and longer, however, this conversation hi... |
human: Can you explain Setup?
bot: First, let's set up the packages we're going to want to use %%capture --no-stderr %pip install --quiet -U langgraph langchain_anthropic Next, we need to set API keys for Anthropic (the LLM we will use) import getpass import os def _set_env(var: str): if not os.environ.get(var): os.e... |
human: What is Related?
bot: For more information, please see: * [LangGraph Platform plans](../plans/) * * [Deployment how-to guides](../../how-tos/#deployment) Was this page helpful? Thanks for your feedback! Thanks for your feedback! Please help us improve this page by adding to the discussion below. |
human: What are the key aspects of How to add cross-thread persistence to your graph?
bot: Prerequisites This guide assumes familiarity with the following: * * * In the you learned how to persist graph state across multiple interactions on a single [thread](). LangGraph also allows you to persist data across **multip... |
human: What is Comments?
bot: Back to top [ Previous How to call tools using ToolNode ](../tool-calling/) [ Next How to pass runtime values to tools ](../pass-run-time-values-to-tools/) Copyright (C) 2025 LangChain, Inc | Consent Preferences Made with |
human: Can you explain LangGraph Server API?
bot: The LangGraph Server API allows you to create and manage [assistants](../assistants/), threads, runs, cron jobs, and more. The [LangGraph Cloud API Reference](../../cloud/reference/api/api_ref.html) provides detailed information on the API endpoints and data models. |
human: What is Deployed Application?
bot: If you have deployed your LangGraph application on LangGraph Platform, you can access the studio as part of that deployment. To do so, navigate to the deployment in LangGraph Platform within the LangSmith UI and click the "LangGraph Studio" button. |
human: Tell me about Cookie consent.
bot: We use cookies to recognize your repeated visits and preferences, as well as to measure the effectiveness of our documentation and whether users find what they're searching for. **Clicking "Accept" makes our documentation better. Thank you!** * Google Analytics * GitHub Accep... |
human: What are the key aspects of Define tools?
bot: from langchain_core.messages import AIMessage from langchain_core.tools import tool from langgraph.prebuilt import ToolNode API Reference: As you can see, the AI message generated by the chat model already has `tool_calls` populated, so we can just pass it directl... |
human: How does Cookie consent work?
bot: We use cookies to recognize your repeated visits and preferences, as well as to measure the effectiveness of our documentation and whether users find what they're searching for. **Clicking "Accept" makes our documentation better. Thank you!** * Google Analytics * GitHub Accep... |
human: What is Replaying?
bot:  Replaying allows us to revisit and reproduce an agent's past actions, up to and including a specific step (checkpoint). To replay actions before a specific checkpoint, start by retrieving all checkpoints for the thread: all_checkpoints = [] for s... |
human: What is Execution?
bot: **Tasks** can only be called from within an **entrypoint** , another **task** , or a [state graph node](../low_level/#nodes). Tasks _cannot_ be called directly from the main application code. When you call a **task** , it returns _immediately_ with a future object. A future is a placeho... |
human: How does Setup work?
bot: First, let's install the required packages %%capture --no-stderr %pip install -U langgraph Set up for LangGraph development Sign up for LangSmith to quickly spot issues and improve the performance of your LangGraph projects. LangSmith lets you use trace data to debug, test, and monito... |
human: What is Cookie consent?
bot: We use cookies to recognize your repeated visits and preferences, as well as to measure the effectiveness of our documentation and whether users find what they're searching for. **Clicking "Accept" makes our documentation better. Thank you!** * Google Analytics * GitHub Accept Reje... |
human: Can you explain Cookie consent?
bot: We use cookies to recognize your repeated visits and preferences, as well as to measure the effectiveness of our documentation and whether users find what they're searching for. **Clicking "Accept" makes our documentation better. Thank you!** * Google Analytics * GitHub Acc... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.