Integrations
LlamaIndex
Guard a LlamaIndex FunctionTool with AxioRank before it runs.
guard_tool wraps a LlamaIndex FunctionTool so its arguments are checked by
AxioRank before it runs. The schema, name, and description are preserved, so the
wrapped tool is a drop-in replacement.
Install
pip install "axiorank[llamaindex]"Guard a tool
Provide client (sync), async_client (async), or both. LlamaIndex derives the
direction it needs from whichever you supply.
from axiorank import AxioRank
from axiorank.integrations.llamaindex import guard_tool
from llama_index.core.tools import FunctionTool
axio = AxioRank(api_key="axr_live_...")
tool = FunctionTool.from_defaults(fn=deploy_service)
safe_tool = guard_tool(tool, axio, on_deny="return")
# ...hand safe_tool to your agent as usual.Recover or fail
on_deny="return" returns a short, model-readable refusal the agent can re-plan
around. The default, on_deny="raise", raises AxioRankDeniedError instead.
Next steps
- Framework integrations: the shared model and
axio.trace(). - Python SDK: the underlying client.