new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

AI SDK · Providers · all subjects

mlflow/setup

5 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

MLflow setup - start tracking server

Start MLflow Tracking Server with: mlflow server --backend-store-uri sqlite:///mlruns.db --port 5000

MLflow setup - environment variables

Configure these environment variables in .env.local: OTEL_EXPORTER_OTLP_ENDPOINT (set to http://localhost:5000 for local testing), OTEL_EXPORTER_OTLP_TRACES_HEADERS=x-mlflow-experiment-id=<your-experiment-id>, OTEL_EXPORTER_OTLP_TRACES_PROTOCOL=http/protobuf

MLflow setup - NextJS packages to install

Install packages for NextJS integration: pnpm i @opentelemetry/api @vercel/otel @ai-sdk/otel

MLflow setup - NextJS instrumentation.ts

Create instrumentation.ts in project root with: import { registerTelemetry } from 'ai'; import { LegacyOpenTelemetry } from '@ai-sdk/otel'; import { registerOTel } from '@vercel/otel'; registerTelemetry(new LegacyOpenTelemetry()); export async function register() { registerOTel({ serviceName: 'next-app' }); }

MLflow setup - Node.js manual OpenTelemetry configuration

For non-NextJS Node.js applications, manually configure OpenTelemetry: Create NodeSDK with spanProcessors containing SimpleSpanProcessor with OTLPTraceExporter pointing to <your-mlflow-tracking-server-endpoint>/v1/traces with headers { 'x-mlflow-experiment-id': '<your-experiment-id>' }. Call sdk.start() before registerTelemetry(new LegacyOpenTelemetry()), and sdk.shutdown() after operations.

Give your agent this brain