OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Evaluation & Observability

Openllmetry

Openllmetry is an open-source Python library of OpenTelemetry extensions that instruments LLM applications and captures telemetry, including standard instrumentations for LLM providers and vector databases.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Openllmetry — OpenViST project profile in AI Evaluation & Observability.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Openllmetry when an LLM application needs OpenTelemetry-based tracing and the team wants to connect captured data to an existing or supported observability destination.

Who it is for

  • Developers adding telemetry instrumentation to Python-based LLM or generative AI applications.
  • Teams with an OpenTelemetry-based observability stack that want to add LLM-specific instrumentation.

Documented uses

  • Add tracing instrumentation to an LLM application.
  • Capture application telemetry from generative AI workloads.
  • Send standard OpenTelemetry data to a supported observability destination.
Before you choose

Requirements & limits

The project is open source under the Apache 2.0 license.

  • The repository documents a Traceloop SDK initialization path as well as individual instrumentations for applications already using OpenTelemetry.
  • The repository lists integrations for destinations including Datadog, Honeycomb, Grafana, Sentry, Google Cloud and the OpenTelemetry Collector.
  • Destination setup is separate from the basic SDK initialization and has destination-specific documentation.
  • The repository identifies OpenLLMetry-JS as a separate JavaScript/TypeScript version.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Instrument a Python OpenAI workflow with OpenLLMetry

Initialize the Traceloop SDK and annotate a Python function that calls the OpenAI API as a workflow.

Before you start

  • A Python project with the OpenAI client available.
  • An OPENAI_API_KEY environment variable for the API call shown in the example.

Steps

  1. Import os, OpenAI, Traceloop, and the workflow decorator from traceloop.sdk.decorators.

  2. Initialize tracing with Traceloop.init(app_name="joke_generation_service").

  3. Define a function decorated with @workflow(name="joke_creation").

  4. Inside the function, create an OpenAI client using os.environ["OPENAI_API_KEY"], make the documented chat completion call, and return the completion text.

Expected outcome

The example’s OpenAI call is placed inside a named workflow after Traceloop initialization, providing workflow annotation for tracing.

Guide limitations

  • The documented example uses the gpt-3.5-turbo model and a joke-generation prompt.
  • This example does not describe configuration of a trace-export destination.
Documentation 1 ↗Documentation 2 ↗
COMPARE OPTIONS

Compare options for Vector search

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
OpenllmetryAdd tracing instrumentation to an LLM application.Cloud, ServerThe project is open source under the Apache 2.0 license.
SmallevalsGenerate synthetic questions from chunks or documents for retrieval evaluation.Linux, macOS, Self-hosted, WindowsSmallevals is presented as a public Python repository and documents installation with pip. The repository information supplied does not identify a license.
MyScale Vector Database BenchmarkMeasure queries per second for vector search.CLI
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
7 October 2026
Original website title
traceloop/openllmetry · Official homepage title · retained in its source language
How we review sourcesSuggest a correction