Skip to content

Update the doc page to add Vertex AI and LLM #1262

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 25, 2025
Merged

Update the doc page to add Vertex AI and LLM #1262

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions solutions/observability/applications/llm-observability.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,15 +24,15 @@ Elastic’s LLM integrations now support the most widely adopted models, includi

## APM tracing for LLM models (via instrumentation)

Elastic offers specialized OpenTelemetry Protocol (OTLP) tracing for applications leveraging LLM models hosted on OpenAI, Azure, and Amazon Bedrock, providing a detailed view of request flows. This tracing capability captures critical insights, including the specific models used, request duration, errors encountered, token consumption per request, and the interaction between prompts and responses. Ideal for troubleshooting, APM tracing allows you to find exactly where the issue is happening with precision and efficiency in your LLM-powered application.
Elastic offers specialized OpenTelemetry Protocol (OTLP) tracing for applications leveraging LLM models hosted on Amazon Bedrock, OpenAI, Azure OpenAI, and GCP Vertex AI, providing a detailed view of request flows. This tracing capability captures critical insights, including the specific models used, request duration, errors encountered, token consumption per request, and the interaction between prompts and responses. Ideal for troubleshooting, APM tracing allows you to find exactly where the issue is happening with precision and efficiency in your LLM-powered application.

You can instrument the application with one of the following Elastic Distributions of OpenTelemetry (EDOT):

- [Python](https://github.com/elastic/elastic-otel-python)
- [Node.js](https://github.com/elastic/elastic-otel-node)
- [Java](https://github.com/elastic/elastic-otel-java)

EDOT includes many types of instrumentation. This [table](https://elastic.github.io/opentelemetry/use-cases/llm/#supported-technologies) lists the supported technologies.
EDOT includes many types of LLM instrumentation. This [table](https://elastic.github.io/opentelemetry/use-cases/llm/#supported-technologies) lists the supported technologies.

### Getting started

Expand Down
Loading