LlamaIndex

How to use the python LlamaIndexInstrumentor to trace LlamaIndex

LlamaIndex is a data framework for your LLM application. It's a powerful framework by which you can build an application that leverages RAG (retrieval-augmented generation) to super-charge an LLM with your own data. RAG is an extremely powerful LLM application model because it lets you harness the power of LLMs such as OpenAI's GPT but tuned to your data and use-case.

For LlamaIndex, tracing instrumentation is added via an OpenTelemetry instrumentor aptly named the LlamaIndexInstrumentor . This callback is what is used to create spans and send them to the Phoenix collector.

Instrumentation (>=0.10.43)

Phoenix supports LlamaIndex's latest instrumentation paradigm.

To get started, pip install the following.

pip install "llama-index-core>=0.10.43" "openinference-instrumentation-llama-index>=2" "opentelemetry-proto>=1.12.0" opentelemetry-exporter-otlp opentelemetry-sdk

Use the following code snippet to activate the instrumentation.

Note that the endpoint variable below should the address of the Phoenix receiver.

from openinference.instrumentation.llama_index import LlamaIndexInstrumentor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk import trace as trace_sdk
from opentelemetry.sdk.trace.export import SimpleSpanProcessor

endpoint = "http://127.0.0.1:6006/v1/traces"  # Phoenix receiver address

tracer_provider = trace_sdk.TracerProvider()
tracer_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter(endpoint)))

LlamaIndexInstrumentor().instrument(tracer_provider=tracer_provider)

Note that the legacy One-Click system of spans can still be used instead by setting use_legacy_callback_handler=True as shown below.

LlamaIndexInstrumentor().instrument(
    tracer_provider=tracer_provider,
    use_legacy_callback_handler=True,
)

Legacy One-Click (<0.10.43)

Using phoenix as a callback requires an install of `llama-index-callbacks-arize-phoenix>0.1.3'

llama-index 0.10 introduced modular sub-packages. To use llama-index's one click, you must install the small integration first:

pip install 'llama-index-callbacks-arize-phoenix>0.1.3'

# Phoenix can display in real time the traces automatically
# collected from your LlamaIndex application.
import phoenix as px
# Look for a URL in the output to open the App in a browser.
px.launch_app()
# The App is initially empty, but as you proceed with the steps below,
# traces will appear automatically as your LlamaIndex application runs.

from llama_index.core import set_global_handler

set_global_handler("arize_phoenix")

# Run all of your LlamaIndex applications as usual and traces
# will be collected and displayed in Phoenix.

Legacy (<v0.10)

If you are using an older version of llamaIndex (pre-0.10), you can still use phoenix. You will have to be using arize-phoenix>3.0.0 and downgrade openinference-instrumentation-llama-index<1.0.0

# Phoenix can display in real time the traces automatically
# collected from your LlamaIndex application.
import phoenix as px
# Look for a URL in the output to open the App in a browser.
px.launch_app()
# The App is initially empty, but as you proceed with the steps below,
# traces will appear automatically as your LlamaIndex application runs.

import llama_index
llama_index.set_global_handler("arize_phoenix")

# Run all of your LlamaIndex applications as usual and traces
# will be collected and displayed in Phoenix.

By adding the callback to the callback manager of LlamaIndex, we've created a one-way data connection between your LLM application and Phoenix Server.

To view the traces in Phoenix, simply open the UI in your browser.

px.active_session().url

For a fully working example of tracing with LlamaIndex, checkout our colab notebook.

Google Colaboratory

Troubleshooting an LLM application using the OpenInferenceTraceCallback