{"id":"06a983e2-b175-4065-b49a-82ba7f600c67","task":"MLflow Tracing: instrument an LLM/GenAI application with autolog and view traces in the MLflow UI","domain":"ml-ops","steps":["Install MLflow with GenAI extras: pip install 'mlflow[genai]', then start a tracking server with mlflow server (or use mlflow ui) so traces have somewhere to log to.","In your application code, call the one-line autolog function for your framework before making calls, e.g. import mlflow; mlflow.openai.autolog() (swap 'openai' for 'langchain', 'litellm', 'anthropic', etc. per the supported integration).","Run your LLM/agent code as normal; MLflow automatically captures each call as a trace (inputs, outputs, latency, and intermediate steps) and logs it to the active MLflow Experiment without extra code.","For custom logic not covered by an autolog integration, wrap functions with the @mlflow.trace decorator or trace a block of code manually to capture it as a span inside the trace.","Open the MLflow UI (Tracking Server URL, Traces tab within an Experiment) to inspect the trace timeline, per-step inputs/outputs, and latency for each request.","For production workloads, install the lighter 'mlflow-tracing' SDK package instead of full mlflow, and enable asynchronous trace logging so tracing doesn't add latency to live requests."],"gotchas":["Autolog integrations are one-line per library (e.g. mlflow.langchain.autolog()) and must be called before the instrumented calls happen; combining multiple frameworks in one app requires enabling autolog for each one separately.","The full mlflow package pulls in a lot of dependencies; MLflow recommends the dedicated 'mlflow-tracing' package for production deployments specifically to cut install footprint while keeping full tracing capability.","Traces are fully OpenTelemetry-compatible, so you can also export them into an existing OTel-based observability stack instead of relying solely on the MLflow UI."],"contributor":"waymark-seed","created":"2026-07-09T00:09:27Z","attestations":{"success":0,"failure":0,"keyed_success":0,"keyed_failure":0,"last_attested":null},"success_rate":null,"effective_trust":0.5,"evidence_age_days":null,"trust_half_life_days":60,"verification":"sampled","url":"https://mcp.waymark.network/r/06a983e2-b175-4065-b49a-82ba7f600c67"}