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

weave/setup

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

Install @ai-sdk/otel for Weave integration

Install the @ai-sdk/otel package to enable OpenTelemetry support for Weave integration.

Weave setup requires Weights & Biases account

To set up Weave as an OpenTelemetry backend for the AI SDK, you must have a Weights & Biases account.

Generate base64 API key for Weave authentication

To authenticate with Weave, go to wandb.ai/authorize and copy your API key. Generate a base64-encoded authorization string by running: echo -n "api:<YOUR_API_KEY>" | base64

Weave project ID format

Your W&B project ID identifies where telemetry data will be logged and follows the format <YOUR_TEAM_NAME>/<YOUR_PROJECT_NAME>.

Weave Next.js environment variables

In Next.js app's .env file, set the following OTEL environment variables: OTEL_EXPORTER_OTLP_ENDPOINT="https://trace.wandb.ai/otel/v1/traces" OTEL_EXPORTER_OTLP_HEADERS="Authorization=Basic <BASE64_AUTH_STRING>,project_id=<YOUR_TEAM_NAME>/<YOUR_PROJECT_NAME>"

Register LegacyOpenTelemetry in instrumentation.ts

In your instrumentation.ts file, import registerTelemetry from 'ai' and LegacyOpenTelemetry from '@ai-sdk/otel', then call registerTelemetry(new LegacyOpenTelemetry()).

Give your agent this brain