StructuredTools, for the prebuilt agent or your own graph.
Capabilities
- Create a Word, PowerPoint, Excel or PDF file, or an artifact, from a request or from Markdown the agent wrote.
- Edit a file: only what is asked changes, and
get_reportlists every change. - Convert a file to another format with no AI, for example any file to Markdown so the agent can read it.
- Read what people saved in an artifact, such as poll votes.
Setup
This integration uses a Doconda API key inDOCONDA_API_KEY (from API keys). The model provider
reads its own key, for example OPENAI_API_KEY.
With the Python SDK
doconda.tools() is JSON Schema, which StructuredTool takes as args_schema:
create_agent is LangGraph’s prebuilt ReAct
agent (formerly create_react_agent in langgraph.prebuilt) and returns a compiled graph, so checkpointer,
streaming and interrupts work as on any other.
In your own graph
In your own graph
With MCP
Instead of the SDK, load the tools from the MCP server withlangchain-mcp-adapters, as in
LangChain.
Tools
The agent gets the eight Doconda tools; see the tools for what each one does.doconda.tools() returns them with name, description, input_schema (JSON Schema) and run. A failed call returns
{ "error": "<code>", "message": "…" } instead of raising, so the model can correct itself.
Troubleshooting
Doconda: pass api_key or set DOCONDA_API_KEY.— The SDK found no key: setDOCONDA_API_KEY, or passapi_keytoDoconda.- A tool result has
"error": "insufficient_balance"— The project’s balance can’t cover the document: top up in the dashboard, or ask forquality: "fast". - The download link stopped working — File links expire after 5 minutes; the agent calls
get_documentfor fresh ones.
Useful links
- Python SDK.
- LangChain: the tools over MCP, in Python and TypeScript.
- doconda-examples on GitHub: ready-to-run scripts.
- API reference.