Launching today
LLMValidate.ai
Open evaluation framework for LLMs and RAG pipelines.
1 follower
Open evaluation framework for LLMs and RAG pipelines.
1 follower
LLMValidate.ai evaluates LLM and RAG applications before and after they go live. It uses a self-hosted vLLM judge, local small models such as toxic-bert for safety checks, and custom scoring modules, and it plugs into any RAG pipeline over HTTP. Built by testAIng.com (AiEnsured), an ISO/IEC 42001 certified AI assurance company.
