{"ok":true,"site":{"host":"deepeval.com","url":"https://deepeval.com/docs/metrics-llm-evals","type":"live","desc":"G-Eval is a framework that uses LLM-as-a-judge with chain-of-thoughts (CoT) to evaluate LLM outputs based on ANY custom criteria. The G-Eval metric is the most…","tools":[{"name":"search_deepeval_docs","kind":"answer","impl":"imperative","description":"Search the DeepEval documentation (the /docs section). Returns titles and URLs. Request any result URL with Accept: text/markdown (or append .mdx) for markdown. For guides, tutorials, integrations, changelog, and blog, read / with Accept: text/markdown for the full site index.","inputSchema":{"type":"object","properties":{"query":{"type":"string","description":"Search terms"}},"required":["query"]},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/docs/metrics-llm-evals","pages":["/docs/metrics-llm-evals","/integrations","/changelog","/blog","/enterprise","/docs/benchmarks-introduction"]},{"name":"get_page_markdown","kind":"answer","impl":"imperative","description":"Fetch a page on this site as markdown. Works for the homepage, docs, guides, tutorials, integrations, changelog, and blog.","inputSchema":{"type":"object","properties":{"path":{"type":"string","description":"Site-relative path, e.g. /docs/introduction or /blog. Defaults to the current page."}}},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/docs/metrics-llm-evals","pages":["/docs/metrics-llm-evals","/integrations","/changelog","/blog","/enterprise","/docs/benchmarks-introduction"]},{"name":"list_agent_resources","kind":"answer","impl":"imperative","description":"List DeepEval's machine-readable resources for agents: llms.txt, agent skills, and the Confident AI API catalog.","inputSchema":{"type":"object","properties":{}},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute","page":"/docs/metrics-llm-evals","pages":["/docs/metrics-llm-evals","/integrations","/changelog","/blog","/enterprise","/docs/benchmarks-introduction"]}],"category":"Developer Tools","favicon":"/favicons/deepeval.com.png","apiSurface":"spec","toolCount":3}}