continuous-eval:基于 Python 的 LLM 应用数据驱动评估工具包项目

Star0

Star0

Data-Driven Evaluation for LLM-Powered Applications

项目介绍

Data-Driven Evaluation for LLM-Powered Applications

Apache-2.0 Python 108提交数evaluation-framework evaluation-metrics information-retrieval llm-evaluation llmops rag retrieval-augmented-generation

定制我的领域

551538访问 GitHub