OpenLLMetry contains a telemetry feature that collects anonymous usage information.
Not to be confused with OpenTelemetry. Telemetry refers to anonymous product
usage statistics we collect. It is a completely different stream of data, and
is not related to OpenTelemetry, traces, or instrumentations.
We use this information to help us understand how OpenLLMetry is used, to help us prioritize work on new features and bug fixes,
and to help us improve OpenLLMetry’s performance and stability.
If you prefer to opt out of telemetry, you can do this by setting the TRACELOOP_TELEMETRY environment variable to FALSE,
or passing telemetry_enabled=False to the Traceloop.init() function in Python.
We will only track usage details that help us make product decisions, specifically:
OpenLLMetry version
Tracing endpoint type (e.g. Honeycomb, Datadog, Traceloop, etc.)
Types of instrumentations that were initialized
Usage of prompt rendering (without logging any details about the prompt, variables, or values)
We do not collect personally-identifiable or sensitive information, such as: API keys, prompts, completions, embeddings, or spans and traces.To view the list of events we track, you may reference the code.