AI tracing: LangChain · LlamaIndex
Agent frameworks traced with OpenInference; PowerTraces reads its attributes without any mapping.
1. Install the instrumentation for your framework
Pick the line for your framework. Others (CrewAI, DSPy, Haystack, OpenAI Agents) follow the same pattern.
pip install openinference-instrumentation-langchain
pip install openinference-instrumentation-llama-index2. Turn it on at start-up
Call it once, after your OpenTelemetry setup and before the framework runs.
from openinference.instrumentation.langchain import LangChainInstrumentor
LangChainInstrumentor().instrument()
from openinference.instrumentation.llama_index import LlamaIndexInstrumentor
LlamaIndexInstrumentor().instrument()OpenInference marks chains, agents, model calls and tools; PowerTraces counts tokens only on the model calls inside them, so totals aren't counted twice.
Prompts and answers
Most libraries send only counts and timings until you turn content on. When you do, PowerTraces keeps it, masks personal data, or drops it, as set in AI › Settings for each workspace.
Check it works
Make one model call, then open the AI page: the run appears within a minute. Open it to see each step in the Agent tab.