WhereToolEvaluate, test, and ship LLM applications with a suite of observability tools to calibrate language model outputs across your dev and production lifecycle.
01 / 工具概览
Evaluate, test, and ship LLM applications with a suite of observability tools to calibrate language model outputs across your dev and production lifecycle.
02 / 使用流程
该分类的一般使用建议；实际功能请查看官网。
Start with a small use case and representative test data.
Evaluate the integration on quality, latency, and operating cost.
Add monitoring and appropriate access controls before wider use.
AI engineers, platform teams, and application builders.
完成类似任务的不同选择。
Access a collection of AI models through a hosted API for application development.
Infrastructure for building AI agents and connecting automated workflows to external services.
Open-source LLMOps platform for prompt management, LLM evaluation, and observability. Build, evaluate, and monitor production-grade LLM applications.
Open-source CLI security scanner for agentic workflows.
CLI that provides command completion, command translation using generative AI to translate intent to commands, and a full agentic chat interface with context…
APIs for transcribing speech and analyzing spoken audio.
