Skip to content

Latest commit

 

History

History
61 lines (50 loc) · 2.08 KB

oraclecloud.mdx

File metadata and controls

61 lines (50 loc) · 2.08 KB
title sidebarTitle
LLM Observability with Oracle Cloud Infrastructure Application Performance Monitoring(APM) service
OCI Application Performance Monitoring

Oracle Cloud Infrastructure Application Performance Monitoring(APM) service natively supports and can ingest OpenTelemetry (OTLP) spans and metrics. Traceloop's OpenLLMetry library enables instrumenting LLM frameworks and applications in Open Telemetry format and can be routed to OCI Application Performance Monitoring for observability and evaluation of LLM applications.

Initialize and export directly from application code

APM_BASE_URL=“<OCI APM dataUploadEndpoint>/20200101/opentelemetry/private"
APM_DATA_KEY="dataKey <OCI APM Private Data Key>"
APM_SERVICE_NAME=“My LLM Service”
 
Traceloop.init(
    disable_batch=True,
    app_name=APM_SERVICE_NAME,
    api_endpoint=APM_BASE_URL,
    headers={
      "Authorization": APM_DATA_KEY
      }
)

Initialize using environment variables

export TRACELOOP_BASE_URL=<OCI APM dataUploadEndpoint>/20200101/opentelemetry/private
export TRACELOOP_HEADERS="Authorization=dataKey <OCI APM Private Data Key>"

Using an OpenTelemetry Collector

If you are using an OpenTelemetry Collector, you can route metrics and traces to OCI APM by simply adding an OTLP exporter to your collector configuration.

receivers:
  otlp:
    protocols:
      http:
        endpoint: 0.0.0.0:4318
processors:
  batch:
exporters:
  otlphttp/apm:
    endpoint: "<OCI APM dataUploadEndpoint>/20200101/opentelemetry/private" 
    headers:
      "Authorization": "dataKey <OCI APM Private Data Key>"
service:
  pipelines:
    traces:
      receivers: [otlp]
      processors: [batch]
      exporters: [otlphttp/apm]

For more information check out the docs link.