In the news
Introducing Pytest and Vitest integrations for LangSmith Evaluations
LangChain · Published · 3 min read
In 30 seconds
- What happened
- LangSmith now offers Pytest and Vitest integrations for running LLM application evaluations, available in beta with SDK v0.3.0.
- Why it matters
- Engineers testing LLM applications who already use Pytest or Vitest and want evaluation observability alongside familiar testing workflows.
- Watch out
- These integrations are in beta. They complement but differ from LangSmith's evaluate() function, which suits different evaluation patterns.
Listen to this summary
- eval
The patterns behind this
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.