LlamaIndex - Failproof AI

Three steps to your first LlamaIndex trace. For workflow steps, retrieval, the reaper, and options, see the full guide.

Install

pip install 'failproofai-sdk[llamaindex]'

Instrument

LlamaIndex’s agent API is async. Every scope works under async with as well as with.

import asyncio

import failproofai_sdk

failproofai_sdk.configure(environment="production")
failproofai_sdk.instrument()

async def main():
    async with failproofai_sdk.session():
        await agent.run("...")

asyncio.run(main())

Without one extra argument on your LLM, every token count in your trace is null — llama-index-llms-openai does not request usage when it streams. See Token counts.

Check it arrived

Run it once, then open Observe → Sessions and select your environment. Your run appears as a reconstructed trace. If nothing arrives, confirm the machine is connected with failproofai config --status.

Full LlamaIndex guide

Token counts, what gets recorded, workflow steps, retrieval, options, and common problems.