docs: replace initialize_agent with create_react_agent

docs/docs/integrations/callbacks/argilla.ipynb

@@ -360,9 +360,10 @@
     }
    ],
    "source": [
-    "from langchain.agents import AgentType, initialize_agent, load_tools\n",
+    "from langchain.agents import load_tools\n",
     "from langchain_core.callbacks.stdout import StdOutCallbackHandler\n",
     "from langchain_openai import OpenAI\n",
+    "from langgraph.prebuilt import create_react_agent\n",
     "\n",
     "argilla_callback = ArgillaCallbackHandler(\n",
     "    dataset_name=\"langchain-dataset\",\n",
@@ -373,11 +374,9 @@
     "llm = OpenAI(temperature=0.9, callbacks=callbacks)\n",
     "\n",
     "tools = load_tools([\"serpapi\"], llm=llm, callbacks=callbacks)\n",
-    "agent = initialize_agent(\n",
-    "    tools,\n",
-    "    llm,\n",
-    "    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
-    "    callbacks=callbacks,\n",
+    "agent = create_react_agent(\n",
+    "    model=llm,\n",
+    "    tools=tools,\n",
     ")\n",
     "agent.run(\"Who was the first president of the United States of America?\")"
    ]

docs/docs/integrations/callbacks/comet_tracing.ipynb

@@ -41,7 +41,8 @@
     "# here we are configuring the comet project\n",
     "os.environ[\"COMET_PROJECT_NAME\"] = \"comet-example-langchain-tracing\"\n",
     "\n",
-    "from langchain.agents import AgentType, initialize_agent, load_tools"
+    "from langchain.agents import load_tools\n",
+    "from langgraph.prebuilt import create_react_agent"
    ]
   },
   {
@@ -76,8 +77,10 @@
    },
    "outputs": [],
    "source": [
-    "agent = initialize_agent(\n",
-    "    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
+    "agent = create_react_agent(\n",
+    "    model=llm,\n",
+    "    tools=tools,\n",
+    "    debug=True,\n",
     ")\n",
     "\n",
     "agent.run(\"What is 2 raised to .123243 power?\")  # this should be traced\n",
@@ -104,8 +107,10 @@
     "# Recreate the LLM, tools and agent and passing the callback to each of them\n",
     "llm = OpenAI(temperature=0)\n",
     "tools = load_tools([\"llm-math\"], llm=llm)\n",
-    "agent = initialize_agent(\n",
-    "    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
+    "agent = create_react_agent(\n",
+    "    model=llm,\n",
+    "    tools=tools,\n",
+    "    debug=True,\n",
     ")\n",
     "\n",
     "agent.run(\n",

docs/docs/integrations/callbacks/llmonitor.md

@@ -83,16 +83,25 @@ agent_executor.run("how many letters in the word educa?", callbacks=[handler])
 Another example:
 
 ```python
-from langchain.agents import load_tools, initialize_agent, AgentType
+from langchain.agents import load_tools
 from langchain_openai import OpenAI
 from langchain_community.callbacks.llmonitor_callback import LLMonitorCallbackHandler
+from langgraph.prebuilt import create_react_agent
 
 
 handler = LLMonitorCallbackHandler()
 
 llm = OpenAI(temperature=0)
 tools = load_tools(["serpapi", "llm-math"], llm=llm)
-agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, metadata={ "agent_name": "GirlfriendAgeFinder" })  # <- recommended, assign a custom name
+system_prompt = "You are a helpful assistant named GirlfriendAgeFinder."
+
+agent = create_react_agent(
+    model=llm,
+    tools=tools,
+    # Add a system prompt (or other advanced instructions).
+    state_modifier=system_prompt,  
+    debug=False,
+)
 
 agent.run(
     "Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?",

docs/docs/integrations/callbacks/sagemaker_tracking.ipynb

@@ -89,10 +89,11 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.agents import initialize_agent, load_tools\n",
+    "from langchain.agents import load_tools\n",
     "from langchain.chains import LLMChain, SimpleSequentialChain\n",
     "from langchain_core.prompts import PromptTemplate\n",
     "from langchain_openai import OpenAI\n",
+    "from langgraph.prebuilt import create_react_agent\n",
     "from sagemaker.analytics import ExperimentAnalytics\n",
     "from sagemaker.experiments.run import Run\n",
     "from sagemaker.session import Session"
@@ -294,8 +295,10 @@
     "    tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callbacks=[sagemaker_callback])\n",
     "\n",
     "    # Initialize agent with all the tools\n",
-    "    agent = initialize_agent(\n",
-    "        tools, llm, agent=\"zero-shot-react-description\", callbacks=[sagemaker_callback]\n",
+    "    agent = create_react_agent(\n",
+    "        model=llm,\n",
+    "        tools=tools,\n",
+    "        debug=True,\n",
     "    )\n",
     "\n",
     "    # Run agent\n",

docs/docs/integrations/llms/amazon_api_gateway.ipynb

@@ -130,7 +130,8 @@
     }
    ],
    "source": [
-    "from langchain.agents import AgentType, initialize_agent, load_tools\n",
+    "from langchain.agents import load_tools\n",
+    "from langgraph.prebuilt import create_react_agent\n",
     "\n",
     "parameters = {\n",
     "    \"max_new_tokens\": 50,\n",
@@ -147,11 +148,10 @@
     "tools = load_tools([\"python_repl\", \"llm-math\"], llm=llm)\n",
     "\n",
     "# Finally, let's initialize an agent with the tools, the language model, and the type of agent we want to use.\n",
-    "agent = initialize_agent(\n",
-    "    tools,\n",
-    "    llm,\n",
-    "    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
-    "    verbose=True,\n",
+    "agent = create_react_agent(\n",
+    "    model=llm,\n",
+    "    tools=tools,\n",
+    "    debug=True,\n",
     ")\n",
     "\n",
     "# Now let's test it out!\n",

docs/docs/integrations/memory/xata_chat_message_history.ipynb

@@ -219,9 +219,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.agents import AgentType, initialize_agent\n",
     "from langchain.agents.agent_toolkits import create_retriever_tool\n",
     "from langchain_openai import ChatOpenAI\n",
+    "from langgraph.prebuilt import create_react_agent\n",
     "\n",
     "tool = create_retriever_tool(\n",
     "    vector_store.as_retriever(),\n",
@@ -232,12 +232,11 @@
     "\n",
     "llm = ChatOpenAI(temperature=0)\n",
     "\n",
-    "agent = initialize_agent(\n",
-    "    tools,\n",
-    "    llm,\n",
-    "    agent=AgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION,\n",
-    "    verbose=True,\n",
-    "    memory=memory,\n",
+    "agent = create_react_agent(\n",
+    "    model=llm,\n",
+    "    tools=tools,\n",
+    "    state_modifier=memory,\n",
+    "    debug=True,\n",
     ")"
    ]
   },

docs/docs/integrations/memory/zep_memory.ipynb

@@ -47,13 +47,13 @@
    "source": [
     "from uuid import uuid4\n",
     "\n",
-    "from langchain.agents import AgentType, initialize_agent\n",
     "from langchain_community.memory.zep_memory import ZepMemory\n",
     "from langchain_community.retrievers import ZepRetriever\n",
     "from langchain_community.utilities import WikipediaAPIWrapper\n",
     "from langchain_core.messages import AIMessage, HumanMessage\n",
     "from langchain_core.tools import Tool\n",
     "from langchain_openai import OpenAI\n",
+    "from langgraph.prebuilt import create_react_agent\n",
     "\n",
     "# Set this to your Zep server URL\n",
     "ZEP_API_URL = \"http://localhost:8000\"\n",
@@ -134,12 +134,11 @@
     "\n",
     "# Initialize the agent\n",
     "llm = OpenAI(temperature=0, openai_api_key=openai_key)\n",
-    "agent_chain = initialize_agent(\n",
-    "    tools,\n",
-    "    llm,\n",
-    "    agent=AgentType.CONVERSATIONAL_REACT_DESCRIPTION,\n",
-    "    verbose=True,\n",
-    "    memory=memory,\n",
+    "agent_chain = create_react_agent(\n",
+    "    model=llm,\n",
+    "    tools=tools,\n",
+    "    state_modifier=memory,\n",
+    "    debug=True,\n",
     ")"
    ]
   },

docs/docs/integrations/memory/zep_memory_cloud.ipynb

@@ -69,13 +69,13 @@
    "source": [
     "from uuid import uuid4\n",
     "\n",
-    "from langchain.agents import AgentType, initialize_agent\n",
     "from langchain_community.memory.zep_cloud_memory import ZepCloudMemory\n",
     "from langchain_community.retrievers import ZepCloudRetriever\n",
     "from langchain_community.utilities import WikipediaAPIWrapper\n",
     "from langchain_core.messages import AIMessage, HumanMessage\n",
     "from langchain_core.tools import Tool\n",
     "from langchain_openai import OpenAI\n",
+    "from langgraph.prebuilt import create_react_agent\n",
     "\n",
     "session_id = str(uuid4())  # This is a unique identifier for the session"
    ]
@@ -138,12 +138,11 @@
     "\n",
     "# Initialize the agent\n",
     "llm = OpenAI(temperature=0, openai_api_key=openai_key)\n",
-    "agent_chain = initialize_agent(\n",
-    "    tools,\n",
-    "    llm,\n",
-    "    agent=AgentType.CONVERSATIONAL_REACT_DESCRIPTION,\n",
-    "    verbose=True,\n",
-    "    memory=memory,\n",
+    "agent_chain = create_react_agent(\n",
+    "    model=llm,\n",
+    "    tools=tools,\n",
+    "    state_modifier=memory,\n",
+    "    debug=True,\n",
     ")"
    ]
   },

docs/docs/integrations/providers/aim_tracking.ipynb

@@ -224,7 +224,8 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.agents import AgentType, initialize_agent, load_tools"
+    "from langchain.agents import load_tools\n",
+    "from langgraph.prebuilt import create_react_agent"
    ]
   },
   {
@@ -269,11 +270,10 @@
    "source": [
     "# scenario 3 - Agent with Tools\n",
     "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callbacks=callbacks)\n",
-    "agent = initialize_agent(\n",
-    "    tools,\n",
-    "    llm,\n",
-    "    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
-    "    callbacks=callbacks,\n",
+    "agent = create_react_agent(\n",
+    "    model=llm,\n",
+    "    tools=tools,\n",
+    "    debug=True,\n",
     ")\n",
     "agent.run(\n",
     "    \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\"\n",

docs/docs/integrations/providers/clearml_tracking.ipynb

@@ -542,15 +542,15 @@
     }
    ],
    "source": [
-    "from langchain.agents import AgentType, initialize_agent, load_tools\n",
+    "from langchain.agents import load_tools\n",
+    "from langgraph.prebuilt import create_react_agent\n",
     "\n",
     "# SCENARIO 2 - Agent with Tools\n",
     "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callbacks=callbacks)\n",
-    "agent = initialize_agent(\n",
-    "    tools,\n",
-    "    llm,\n",
-    "    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
-    "    callbacks=callbacks,\n",
+    "agent = create_react_agent(\n",
+    "    model=llm,\n",
+    "    tools=tools,\n",
+    "    debug=True,\n",
     ")\n",
     "agent.run(\"Who is the wife of the person who sang summer of 69?\")\n",
     "clearml_callback.flush_tracker(\n",

docs/docs/integrations/providers/comet_tracking.ipynb

@@ -192,10 +192,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.agents import initialize_agent, load_tools\n",
+    "from langchain.agents import load_tools\n",
     "from langchain_community.callbacks import CometCallbackHandler\n",
     "from langchain_core.callbacks import StdOutCallbackHandler\n",
     "from langchain_openai import OpenAI\n",
+    "from langgraph.prebuilt import create_react_agent\n",
     "\n",
     "comet_callback = CometCallbackHandler(\n",
     "    project_name=\"comet-example-langchain\",\n",
@@ -207,12 +208,10 @@
     "llm = OpenAI(temperature=0.9, callbacks=callbacks)\n",
     "\n",
     "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callbacks=callbacks)\n",
-    "agent = initialize_agent(\n",
-    "    tools,\n",
-    "    llm,\n",
-    "    agent=\"zero-shot-react-description\",\n",
-    "    callbacks=callbacks,\n",
-    "    verbose=True,\n",
+    "agent = create_react_agent(\n",
+    "    model=llm,\n",
+    "    tools=tools,\n",
+    "    debug=True,\n",
     ")\n",
     "agent.run(\n",
     "    \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\"\n",

docs/docs/integrations/providers/flyte.mdx

@@ -25,7 +25,8 @@ First, import the necessary dependencies to support your LangChain experiments.
 import os
 
 from flytekit import ImageSpec, task
-from langchain.agents import AgentType, initialize_agent, load_tools
+from langgraph.prebuilt import create_react_agent
+from langchain.agents import load_tools
 from langchain.callbacks import FlyteCallbackHandler
 from langchain.chains import LLMChain
 from langchain_openai import ChatOpenAI
@@ -124,12 +125,10 @@ def langchain_agent() -> str:
     tools = load_tools(
         ["serpapi", "llm-math"], llm=llm, callbacks=[FlyteCallbackHandler()]
     )
-    agent = initialize_agent(
-        tools,
-        llm,
-        agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
-        callbacks=[FlyteCallbackHandler()],
-        verbose=True,
+    agent = create_react_agent(
+        model=llm,
+        tools=tools,
+        debug=True,
     )
     return agent.run(
         "Who is Leonardo DiCaprio's girlfriend? Could you calculate her current age and raise it to the power of 0.43?"

docs/docs/integrations/providers/google_serper.mdx

@@ -23,8 +23,8 @@ You can use it as part of a Self Ask chain:
 ```python
 from langchain_community.utilities import GoogleSerperAPIWrapper
 from langchain_openai import OpenAI
-from langchain.agents import initialize_agent, Tool
-from langchain.agents import AgentType
+from langchain.agents import Tool
+from langgraph.prebuilt import create_react_agent
 
 import os
 
@@ -41,7 +41,11 @@ tools = [
     )
 ]
 
-self_ask_with_search = initialize_agent(tools, llm, agent=AgentType.SELF_ASK_WITH_SEARCH, verbose=True)
+self_ask_with_search = create_react_agent(
+    model=llm,
+    tools=tools,
+    debug=True,
+)
 self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?")
 ```
 

docs/docs/integrations/providers/mlflow_tracking.ipynb

@@ -358,13 +358,17 @@
    "outputs": [],
    "source": [
     "script_content = \"\"\"\n",
-    "from langchain.agents import AgentType, initialize_agent, load_tools\n",
+    "from langgraph.prebuilt import create_react_agent\n",
+    "from langchain.agents import load_tools\n",
     "from langchain_openai import ChatOpenAI\n",
     "import mlflow\n",
     "\n",
     "llm = ChatOpenAI(model_name=\"gpt-4o\", temperature=0)\n",
     "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)\n",
-    "agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION)\n",
+    "agent = create_react_agent(\n",
+    "    model=llm,\n",
+    "    tools=tools,\n",
+    ")\n",
     "\n",
     "# IMPORTANT: call set_model() to register the instance to be logged.\n",
     "mlflow.models.set_model(agent)\n",