DocondaStart for free
+

Generate Word, Excel, PowerPoint and PDF
with LangGraph

Code

Python or TypeScript

Your graph decides. Doconda delivers the file.

Turn Doconda's tools into StructuredTool and your LangGraph agent delivers finished, editable, reviewed Word, Excel, PowerPoint and PDF files.

  1. 01Install the SDKpip install doconda or npm install @doconda/sdk, and your API key.
  2. 02Give your agent the toolsDoconda's tools, in LangGraph's format.
  3. 03Your agent delivers the fileYour agent gets the link to the reviewed file.
See the full guide
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)  # a compiled LangGraph graph
result = agent.invoke({"messages": [{"role": "user", "content": "Write a quarterly sales report in Word"}]})
print(result["messages"][-1].content)

FAQ

Common questions

01 / 04

How do I use Doconda in LangGraph?

doconda.tools() is JSON Schema, which StructuredTool accepts as args_schema. Pass those tools to create_agent or to a ToolNode in your own graph.

The document API for AI agents, ready for production.

Start for freeDocs