opentelemetry-instrumentation-voyageai

What it is and what it does

This package is an OpenTelemetry instrumentation plugin that automatically intercepts and records Voyage AI API calls—both embeddings and reranking operations—without requiring code changes to your Voyage AI client usage. It captures structured telemetry following OpenTelemetry's GenAI semantic conventions, recording the operation type, model name, token counts, and embedding dimensions as spans that can be exported to any OpenTelemetry-compatible backend (Jaeger, Datadog, New Relic, etc.).

The instrumentation works by wrapping Voyage AI client methods at import time. Once activated with a single call to `VoyageAIInstrumentor().instrument()`, all subsequent Voyage AI operations are traced automatically. It depends on four OpenTelemetry packages (api, instrumentation, and two semantic convention libraries) and requires Python 3.10 or later. The package is actively maintained and carries no known security vulnerabilities.

Use it for:

• Monitor embedding generation latency and token usage across your RAG or semantic search pipeline
• Debug reranking performance by tracing query and document processing through OpenTelemetry
• Export Voyage AI operation traces to a centralized observability platform for cost and performance analysis
• Correlate Voyage AI calls with upstream application traces using OpenTelemetry context propagation
• Audit which models and operations are being called in production for compliance or billing purposes

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Automatically captures and traces Voyage AI API calls (embeddings and reranking) using OpenTelemetry, recording operation names, model names, token usage, and embedding dimensions as structured telemetry data.

Yes, if you are already using OpenTelemetry in your application and need visibility into Voyage AI API calls. The low install friction, active maintenance, permissive license, and zero known vulnerabilities make it a straightforward addition to any observability stack. Install only if you have an OpenTelemetry exporter configured; the instrumentation alone produces no output.

Install

opentelemetry-instrumentation-voyageai on PyPI

pip install opentelemetry-instrumentation-voyageai

uv add opentelemetry-instrumentation-voyageai

poetry add opentelemetry-instrumentation-voyageai

Installing opentelemetry-instrumentation-voyageai

Before you install

Low friction: pure Python wheel with four runtime dependencies (all part of the OpenTelemetry ecosystem). Actively maintained as of 2026-08-10 with recent releases.

License in practice

Apache-2.0 permissive license allows use in commercial and proprietary projects with minimal restrictions.

Quickstart

pip install opentelemetry-instrumentation-voyageai

from opentelemetry.instrumentation.voyageai import VoyageAIInstrumentor
VoyageAIInstrumentor().instrument()

import voyageai
client = voyageai.Client()
result = client.embed(texts=["Hello, world!"], model="voyage-3")

Requires Python 3.10 or later (package specifies >=3.10,<4); Voyage AI client library must be installed separately and available at runtime.

Verify before relying

• Whether the package works with Voyage AI client versions other than those tested during development
• Performance overhead of instrumentation on high-volume embedding or reranking workloads

Package facts

Evidence: opentelemetry_instrumentation_voyageai-0.62.3-py3-none-any.whl

Tags

More Monitoring packages