LangGraph Prebuilt Agents

raw JSON →
1.0.8 verified Tue May 12 auth: no python install: stale quickstart: stale

LangGraph Prebuilt is a Python library offering high-level APIs for creating and executing LangGraph agents and tools. It simplifies building complex agentic workflows by providing pre-packaged components and architectures, reducing the need for low-level graph construction. Currently at version 1.0.8, this library is part of the broader LangGraph ecosystem, which undergoes frequent updates, with `langgraph-prebuilt` releases typically aligning with major feature additions to its high-level components. [2, 18]

pip install langgraph-prebuilt langchain-openai tavily-python

Common errors

error ModuleNotFoundError: No module named 'langgraph.prebuilt' ↓
cause This error most commonly occurs when a Python file in your project is named `langgraph.py`, which shadows the installed `langgraph` package, or when `langgraph-prebuilt` is not properly installed or detected in the environment.
fix
Rename any local file named langgraph.py to something else. Ensure langgraph and langgraph-prebuilt are installed in your active virtual environment using: pip install langgraph langgraph-prebuilt. If issues persist, try creating a fresh virtual environment.
error ImportError: cannot import name 'create_react_agent' from 'langgraph.prebuilt' ↓
cause This indicates that the `create_react_agent` function (or other specific components) cannot be found within `langgraph.prebuilt`, often due to a version mismatch between `langgraph` and `langgraph-prebuilt`, or an outdated installation.
fix
Ensure both langgraph and langgraph-prebuilt are updated to their latest compatible versions. It is recommended to install them together, or upgrade both: pip install --upgrade langgraph langgraph-prebuilt. If the problem persists, confirm the function's availability in the specific version's documentation.
error ImportError: cannot import name 'ServerInfo' from 'langgraph.runtime' ↓
cause `langgraph-prebuilt` imports components like `ServerInfo` from `langgraph.runtime`, and this error occurs when your installed `langgraph` version is older and does not export these required names, indicating an incompatibility.
fix
Upgrade your langgraph package to a version compatible with your langgraph-prebuilt installation, or update both packages simultaneously: pip install --upgrade langgraph langgraph-prebuilt. Pinning compatible versions together is also a solution (e.g., langgraph==1.1.x for langgraph-prebuilt==1.0.x).
error AttributeError: 'HuggingFaceEndpoint' object has no attribute 'bind_tools' ↓
cause This error arises when using `langgraph-prebuilt` agents (like `create_react_agent`) with LLM models that do not support the `bind_tools` method, which is a required interface for tool calling within LangGraph agents.
fix
Ensure the LLM model you are using supports tool calling and implements the bind_tools method. If your current LLM does not, consider switching to a compatible model (e.g., OpenAI's Chat models, Anthropic's Claude 3, or other models with explicit tool-calling support) or integrate it via a custom wrapper that exposes the bind_tools functionality.

Warnings

gotcha LangGraph is a low-level framework, while `langgraph-prebuilt` offers higher-level abstractions. Mixing low-level graph construction (e.g., `StateGraph`, `add_node`) with prebuilt agents (like `create_react_agent`) without understanding LangGraph's state management can lead to unexpected behavior or difficult-to-debug issues. Stick to one paradigm or thoroughly understand how state is managed across both. [3, 5, 6] ↓
fix For complex customizations, consider extending or modifying the prebuilt agent's internal graph if the documentation provides a clear path, or build a custom graph from scratch using `langgraph.graph.StateGraph` for full control. For simpler cases, leverage the provided prebuilt agent parameters and hooks. Consult the official LangGraph documentation for advanced patterns. [5, 8, 9]
gotcha Prebuilt agents often rely on external services (LLMs, search tools). Failing to set required API keys as environment variables (e.g., `OPENAI_API_KEY`, `TAVILY_API_KEY`) or passing incorrect values will cause agents to fail silently or with authentication errors. [1, 6, 13] ↓
fix Always verify that all necessary API keys are correctly set in your environment or explicitly passed to the respective LLM/tool constructors before running the agent. Test credentials independently if an agent is failing. Use a `.env` file and `python-dotenv` for local development. [1, 6]
deprecated The LangGraph ecosystem, including `langgraph-prebuilt`, is actively developed. Older patterns for agents or tool integration, while functional, might be superseded by more efficient, flexible, or recommended approaches in newer releases. [7] ↓
fix Regularly consult the official LangChain/LangGraph documentation and quickstarts for the latest recommended practices and agent architectures. Pay attention to release notes for potential API changes or new high-level abstractions. [1, 7, 10]
gotcha The `langchain_community` package, which provides various tools and utilities (e.g., `TavilySearchResults`), is a common dependency for agents utilizing external services. If it's not explicitly installed, importing modules from it will result in a `ModuleNotFoundError`. ↓
fix Ensure `langchain_community` is listed in your project's `requirements.txt` or explicitly installed via `pip install langchain-community` in your environment before running agents that rely on it. Verify your environment setup, especially in containerized or CI/CD contexts, to ensure all necessary dependencies are installed.
breaking A `ModuleNotFoundError` for packages like `langchain_community` indicates that required dependencies are not installed in the execution environment. Prebuilt agents and tools often rely on specific packages that must be explicitly added. ↓
fix Ensure all necessary Python packages are installed in the environment. This typically involves running `pip install <package_name>` for each required package, or using `pip install -r requirements.txt` if a `requirements.txt` file is present. Verify that the correct virtual environment is activated if applicable.

Install compatibility stale last tested: 2026-05-12

python os / libc status wheel install import disk
3.10 alpine (musl) wheel - - 89.9M
3.10 alpine (musl) - - - -
3.10 slim (glibc) wheel 10.6s - 98M
3.10 slim (glibc) - - - -
3.11 alpine (musl) wheel - - 96.9M
3.11 alpine (musl) - - - -
3.11 slim (glibc) wheel 9.4s - 105M
3.11 slim (glibc) - - - -
3.12 alpine (musl) wheel - - 87.5M
3.12 alpine (musl) - - - -
3.12 slim (glibc) wheel 7.7s - 95M
3.12 slim (glibc) - - - -
3.13 alpine (musl) wheel - - 87.2M
3.13 alpine (musl) - - - -
3.13 slim (glibc) wheel 7.6s - 95M
3.13 slim (glibc) - - - -
3.9 alpine (musl) wheel - - 86.2M
3.9 alpine (musl) - - - -
3.9 slim (glibc) wheel 11.9s - 94M
3.9 slim (glibc) - - - -

Imports

Quickstart stale last tested: 2026-04-24

This quickstart demonstrates how to set up and use `create_react_agent` from `langgraph-prebuilt`. It initializes an OpenAI LLM, a Tavily search tool, and then creates an agent capable of using these tools. The agent is then invoked with a query, showcasing its ability to use tools for information retrieval and simple calculations. Ensure `OPENAI_API_KEY` and `TAVILY_API_KEY` are set in your environment for the example to run. [8, 13]

import os
from langchain_openai import ChatOpenAI
from langchain_community.tools.tavily_search import TavilySearchResults
from langgraph.prebuilt import create_react_agent
from typing import Annotated, Sequence, TypedDict
from langchain_core.messages import BaseMessage

# Set API keys (replace with actual keys or set as environment variables)
os.environ["OPENAI_API_KEY"] = os.environ.get("OPENAI_API_KEY", "YOUR_OPENAI_API_KEY")
os.environ["TAVILY_API_KEY"] = os.environ.get("TAVILY_API_KEY", "YOUR_TAVILY_API_KEY")

# Define the agent state (LangGraph requires a defined state)
class AgentState(TypedDict):
    messages: Annotated[Sequence[BaseMessage], lambda x, y: x + y]

# Initialize LLM and tools
llm = ChatOpenAI(model="gpt-4o-mini") # or any other tool-calling capable LLM
search_tool = TavilySearchResults(max_results=3)
tools = [search_tool]

# Create the prebuilt ReAct agent
agent_executor = create_react_agent(llm, tools=tools)

# Example usage
# Ensure OPENAI_API_KEY and TAVILY_API_KEY are set
if os.environ["OPENAI_API_KEY"] == "YOUR_OPENAI_API_KEY" or os.environ["TAVILY_API_KEY"] == "YOUR_TAVILY_API_KEY":
    print("Please set OPENAI_API_KEY and TAVILY_API_KEY environment variables or replace placeholders.")
else:
    response = agent_executor.invoke(
        {"messages": [("human", "What is the weather in London and what is 123 + 456?")]}
    )
    print(response["messages"][-1].content)
last verified Tue May 12
next check Fri Jun 26