Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Generate Word, PowerPoint, Excel and PDF files from a LangGraph agent.
pip install langgraph "langchain[openai]" doconda
doconda.tools() is JSON Schema, which StructuredTool takes as args_schema:
from doconda import Doconda
from langchain.agents import create_agent
from langchain_core.tools import StructuredTool
def as_langchain_tool(t):
return StructuredTool(name=t.name, description=t.description, args_schema=t.input_schema, func=lambda **args: t.run(args))
tools = [as_langchain_tool(t) for t in Doconda().tools()]
agent = create_agent("openai:gpt-5", tools)
agent.invoke({"messages": [{"role": "user", "content": "Write a quarterly sales report in Word"}]})
create_agent is LangGraph’s prebuilt ReAct agent (formerly create_react_agent in langgraph.prebuilt) and returns
a compiled graph: checkpointer, streaming and interrupts work as on any other. With the Python SDK.
In your own graph
from langchain.chat_models import init_chat_model
from langgraph.graph import START, MessagesState, StateGraph
from langgraph.prebuilt import ToolNode, tools_condition
model = init_chat_model("openai:gpt-5").bind_tools(tools)
def call_model(state: MessagesState):
return {"messages": [model.invoke(state["messages"])]}
graph = (
StateGraph(MessagesState)
.add_node("model", call_model)
.add_node("tools", ToolNode(tools))
.add_edge(START, "model")
.add_conditional_edges("model", tools_condition)
.add_edge("tools", "model")
.compile()
)
langchain-mcp-adapters as in LangChain.