Weights and Biases

W&B Weave (LLM Observability)

LLM observability and evaluation platform providing tracing, output evaluation, cost estimation, prompt playground, guardrails, and a Python and TypeScript SDK. Traces and evaluations are persisted to the W&B backend and queryable via the Weave SDK.

W&B Weave (LLM Observability) is one of 7 APIs that Weights and Biases publishes on the APIs.io network.

Tagged areas include LLM, Observability, Tracing, Evaluation, and Guardrails. The published artifact set on APIs.io includes API documentation.

GitHub

Documentation

📖
Documentation
https://weave-docs.wandb.ai/

Other Resources

🔗
Repository
https://github.com/wandb/weave

API entry from apis.yml

apis.yml Raw ↑ 
aid: wandb:weave
name: W&B Weave (LLM Observability)
description: LLM observability and evaluation platform providing tracing, output evaluation, cost estimation,
  prompt playground, guardrails, and a Python and TypeScript SDK. Traces and evaluations are persisted
  to the W&B backend and queryable via the Weave SDK.
humanURL: https://weave-docs.wandb.ai/
baseURL: https://api.wandb.ai
tags:
- LLM
- Observability
- Tracing
- Evaluation
- Guardrails
properties:
- type: Documentation
  url: https://weave-docs.wandb.ai/
- type: Repository
  url: https://github.com/wandb/weave