{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/9dc21b753bbe4f6fb3c1b44c06e39c20\" frameborder=\"0\" width=\"1108\" height=\"831\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":831,"width":1108,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":831,"thumbnail_width":1108,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/9dc21b753bbe4f6fb3c1b44c06e39c20-fb6622960c6b175e.gif","duration":221.739,"title":"Setting Up Splunk OTEL Traces in LightLM","description":"Hi Tim, quick demo on setting up Splunk Auto Traces in LightLM. From the LightLM side, configure the auto callback in YAML and add AutoEnvironmentAutoTracer variables, including the OTP endpoint, headers with your token, the OTP protocol, and an optional name. Once that is in place, restart your proxy and send a test request. In Splunk APM TraceAnalyzer, you should see the full trace with the Gen AI fields like model, finish reason, usage, costs, request metadata, and user ID. I also showed where to generate the ingest access token and copy the ingest URL."}