n4nAI

Topic

OpenTelemetry Tracing for LLM Apps

13 posts on opentelemetry tracing for llm apps — part of developer tools on the n4n AI blog.

Developer toolsAnalysis

Why distributed tracing matters for multi-step LLM chains

Distributed tracing for LLM chains exposes latency, token cost, and failure paths across multi-step agents. Here's how to implement it with OpenTelemetry.

5 min read
Developer toolsTutorial

Tracing a RAG pipeline end to end with OpenTelemetry

Learn how to implement tracing RAG with OpenTelemetry in Python: instrument retrieval, augmentation, and generation steps with runnable code and spans.

2 min read
Developer toolsTutorial

Sending OpenTelemetry LLM traces to Grafana Tempo

Step-by-step tutorial to send OpenTelemetry LLM traces to Grafana Tempo: run Tempo with Docker, instrument a Python LLM client, query spans.

2 min read
Developer toolsComparison

OpenTelemetry vs proprietary LLM tracing SDKs

A pragmatic head-to-head comparison of OpenTelemetry vs proprietary tracing SDKs for LLM apps across cost, latency, ergonomics, and ecosystem.

5 min read
Developer toolsDefinition

OpenTelemetry semantic conventions for GenAI, explained

A precise explainer of OpenTelemetry GenAI semantic conventions: what they define, how spans model LLM calls, and why standardized tracing matters.

5 min read
Developer toolsHow-to

OpenTelemetry context propagation for async LLM calls

Learn how to implement OpenTelemetry context propagation async patterns for LLM apps, keeping traces intact across asyncio tasks and threads.

3 min read
Developer toolsGuide

OpenTelemetry collector configs for high-volume LLM traffic

Practical OpenTelemetry collector configurations for scaling LLM tracing and metrics, with pipeline patterns, batching, and sampling for high-volume inference.

4 min read
Developer toolsHow-to

Measuring token counts as OpenTelemetry span attributes

Learn how to emit token counts as OpenTelemetry span attributes for LLM apps, with runnable Python code for instrumentation and verification.

3 min read
Developer toolsHow-to

Instrumenting LLM calls with OpenTelemetry spans

Learn how to implement instrumenting LLM calls with OpenTelemetry spans step by step, capturing latency, token usage, and errors across your LLM stack.

3 min read
Developer toolsHow-to

Exporting LLM traces to Jaeger with OpenTelemetry

Learn how exporting LLM traces to Jaeger with OpenTelemetry works: stand up Jaeger, instrument Python LLM calls, and verify spans end to end.

3 min read
Developer toolsHow-to

Debugging slow LLM chains using OpenTelemetry waterfalls

Learn how to trace and debug LLM chains with OpenTelemetry waterfalls. Step-by-step instrumentation, span analysis, and latency fixes for Python apps.

4 min read
Developer toolsGuide

Cross-service LLM span correlation with OpenTelemetry

A practical guide to correlating LLM spans across microservices with OpenTelemetry: propagate trace context, instrument clients, and avoid common pitfalls.

3 min read
Developer toolsTutorial

Adding OpenTelemetry to a Python LLM app in 20 minutes

Learn to add OpenTelemetry to a Python LLM app in 20 minutes with this hands-on tutorial covering spans, attributes, and Jaeger output.

3 min read