> ## Documentation Index
> Fetch the complete documentation index at: https://aitutorial.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Evaluation & Quality Metrics

> How to evaluate the performance of a RAG system

export const QuizQuestion = ({question, options, answer, explanation}) => {
  const [selected, setSelected] = useState(null);
  const [revealed, setRevealed] = useState(false);
  const handleSelect = index => {
    if (revealed) return;
    setSelected(index);
    setRevealed(true);
  };
  const isCorrect = selected === answer;
  const getOptionClass = i => {
    const classes = ['quiz-option'];
    if (revealed) {
      classes.push('quiz-option-disabled');
      if (i === answer) classes.push('quiz-option-correct'); else if (i === selected && !isCorrect) classes.push('quiz-option-wrong');
    }
    return classes.join(' ');
  };
  return <div className="quiz-card">
      <p className="quiz-question">{question}</p>
      <div className="quiz-options">
        {options.map((option, i) => <button key={i} onClick={() => handleSelect(i)} className={getOptionClass(i)}>
            <span className="quiz-letter">{String.fromCharCode(65 + i)}</span>
            {option}
          </button>)}
      </div>
      {revealed && <div className={`quiz-feedback ${isCorrect ? 'quiz-feedback-correct' : 'quiz-feedback-wrong'}`}>
          <strong>{isCorrect ? 'Correct!' : 'Incorrect.'}</strong> {explanation}
        </div>}
    </div>;
};

export const Quiz = ({title = "Check Your Understanding", children}) => {
  return <div style={{
    marginTop: '24px'
  }}>
      <div className="quiz-title">{title}</div>
      {children}
    </div>;
};

export const CodeEditor = ({file = 'src/hello_world.ts', lines, title = 'Code Example', repo = 'ai-tutorial/typescript-examples', height = '650px', functionName, theme: userTheme}) => {
  const STORAGE_KEY = 'openai_api_key';
  const GEMINI_STORAGE_KEY = 'gemini_api_key';
  const ANTHROPIC_STORAGE_KEY = 'anthropic_api_key';
  const PROVIDER_STORAGE_KEY = 'llm_playground_provider';
  if (!functionName) {
    console.warn('CodeEditor: functionName parameter is required');
  }
  const hasCreatedEnvRef = useRef(false);
  const vmRef = useRef(null);
  const [isMaximized, setIsMaximized] = useState(false);
  const [isCollapsed, setIsCollapsed] = useState(false);
  const [isStuck, setIsStuck] = useState(false);
  const [iframeKey, setIframeKey] = useState(0);
  const [showApiKeyDialog, setShowApiKeyDialog] = useState(false);
  const [apiKey, setApiKey] = useState('');
  const [error, setError] = useState('');
  const [success, setSuccess] = useState(false);
  const [isSubmitting, setIsSubmitting] = useState(false);
  const [isValidating, setIsValidating] = useState(false);
  const [detectedTheme, setDetectedTheme] = useState('dark');
  useEffect(() => {
    if (typeof window === 'undefined') return;
    const checkTheme = () => {
      const isDark = document.documentElement.classList.contains('dark');
      setDetectedTheme(isDark ? 'dark' : 'light');
    };
    checkTheme();
    const observer = new MutationObserver(checkTheme);
    observer.observe(document.documentElement, {
      attributes: true,
      attributeFilter: ['class']
    });
    return () => observer.disconnect();
  }, []);
  const theme = userTheme || detectedTheme;
  const [selectedProvider, setSelectedProvider] = useState(() => {
    if (typeof window === 'undefined') return 'gemini';
    return localStorage.getItem(PROVIDER_STORAGE_KEY) || 'gemini';
  });
  const isApiKeyConfigured = () => {
    const openaiKey = localStorage.getItem(STORAGE_KEY);
    const geminiKey = localStorage.getItem(GEMINI_STORAGE_KEY);
    const anthropicKey = localStorage.getItem(ANTHROPIC_STORAGE_KEY);
    return openaiKey !== null && openaiKey.trim().length > 0 || geminiKey !== null && geminiKey.trim().length > 0 || anthropicKey !== null && anthropicKey.trim().length > 0;
  };
  const dispatchApiKeyChanged = () => {
    if (typeof window !== 'undefined' && window.dispatchEvent) {
      window.dispatchEvent(new CustomEvent('apiKeyChanged', {
        detail: {
          configured: isApiKeyConfigured()
        }
      }));
    }
  };
  const saveApiKey = apiKey => {
    if (apiKey && apiKey.trim()) {
      const trimmedKey = apiKey.trim();
      localStorage.setItem(STORAGE_KEY, trimmedKey);
      dispatchApiKeyChanged();
      return true;
    }
    return false;
  };
  const buildEnvContent = () => {
    const openaiKey = localStorage.getItem(STORAGE_KEY)?.trim();
    const geminiKey = localStorage.getItem(GEMINI_STORAGE_KEY)?.trim();
    const anthropicKey = localStorage.getItem(ANTHROPIC_STORAGE_KEY)?.trim();
    if (!openaiKey && !geminiKey && !anthropicKey) {
      return `OPENAI_MODEL=gpt-4.1-nano
OPENAI_API_KEY=sk-mock-key-1234567890abcdef
GEMINI_MODEL=gemini-2.5-flash-lite
GOOGLE_GENERATIVE_AI_API_KEY=
GOOGLE_API_KEY=
ANTHROPIC_API_KEY=
AI_PROVIDER=openai
# API key not found in browser storage
# To configure your API key:
# 1. For Gemini (free): Go to https://aistudio.google.com/apikey
# 2. For OpenAI: Go to https://platform.openai.com/api-keys
# 3. For Claude: Go to https://console.anthropic.com/settings/keys
# 4. Enter it in the configuration form above this editor
# 5. The .env file will be automatically updated with your key`;
    }
    const envLines = ['# Using the API key(s) you configured. This file will be created when the dialog is loaded.'];
    if (openaiKey) {
      envLines.push(`OPENAI_MODEL=gpt-4.1-nano`);
      envLines.push(`OPENAI_API_KEY=${openaiKey}`);
    }
    if (geminiKey) {
      envLines.push(`GEMINI_MODEL=gemini-2.5-flash-lite`);
      envLines.push(`# Vercel AI SDK uses GOOGLE_GENERATIVE_AI_API_KEY, LangChain uses GOOGLE_API_KEY`);
      envLines.push(`GOOGLE_GENERATIVE_AI_API_KEY=${geminiKey}`);
      envLines.push(`GOOGLE_API_KEY=${geminiKey}`);
    }
    if (anthropicKey) {
      envLines.push(`ANTHROPIC_API_KEY=${anthropicKey}`);
    }
    const provider = anthropicKey ? 'anthropic' : geminiKey ? 'gemini' : 'openai';
    envLines.push(`AI_PROVIDER=${provider}`);
    return envLines.join('\n');
  };
  const updateEnvFile = async vm => {
    if (!vm) return;
    try {
      await vm.applyFsDiff({
        create: {
          'env/.env': buildEnvContent(),
          'env/run.conf': `file=${file}`
        },
        destroy: []
      });
      hasCreatedEnvRef.current = true;
    } catch (error) {
      console.error('Failed to write env files:', error);
      hasCreatedEnvRef.current = false;
    }
  };
  useEffect(() => {
    if (!isApiKeyConfigured()) {
      setShowApiKeyDialog(true);
    }
    const handleApiKeyChanged = () => {
      if (isApiKeyConfigured()) {
        setShowApiKeyDialog(false);
      }
    };
    if (typeof window !== 'undefined') {
      window.addEventListener('apiKeyChanged', handleApiKeyChanged);
      return () => {
        window.removeEventListener('apiKeyChanged', handleApiKeyChanged);
      };
    }
  }, []);
  const validateApiKey = async (key, provider) => {
    try {
      const urls = {
        gemini: 'https://generativelanguage.googleapis.com/v1beta/models?key=' + encodeURIComponent(key.trim()),
        openai: 'https://api.openai.com/v1/models',
        anthropic: 'https://api.anthropic.com/v1/models'
      };
      const headerMap = {
        gemini: {
          'Content-Type': 'application/json'
        },
        openai: {
          'Authorization': `Bearer ${key.trim()}`,
          'Content-Type': 'application/json'
        },
        anthropic: {
          'x-api-key': key.trim(),
          'anthropic-version': '2023-06-01',
          'Content-Type': 'application/json'
        }
      };
      const url = urls[provider];
      const headers = headerMap[provider];
      const response = await fetch(url, {
        method: 'GET',
        headers
      });
      if (response.ok) {
        return {
          valid: true
        };
      } else if (response.status === 401 || response.status === 403) {
        return {
          valid: false,
          error: 'Invalid API key. Please check your key and try again.'
        };
      } else if (response.status === 429) {
        return {
          valid: false,
          error: 'Rate limit exceeded. Please try again later.'
        };
      } else {
        const errorData = await response.json().catch(() => ({}));
        return {
          valid: false,
          error: errorData.error?.message || `API request failed with status ${response.status}`
        };
      }
    } catch (err) {
      if (err.name === 'TypeError' && err.message.includes('fetch')) {
        return {
          valid: false,
          error: 'Network error. Please check your connection and try again.'
        };
      }
      return {
        valid: false,
        error: err.message || 'Failed to validate API key. Please try again.'
      };
    }
  };
  const handleSkipConfiguration = () => {
    const skipKey = 'sk-<configure-your-key>';
    saveApiKey(skipKey);
    setShowApiKeyDialog(false);
  };
  const handleApiKeySubmit = async e => {
    e.preventDefault();
    setError('');
    setSuccess(false);
    setIsSubmitting(true);
    const providerNames = {
      gemini: 'Gemini',
      openai: 'OpenAI',
      anthropic: 'Claude'
    };
    if (!apiKey || !apiKey.trim()) {
      setError(`Please enter your ${providerNames[selectedProvider]} API key`);
      setIsSubmitting(false);
      return;
    }
    const trimmedKey = apiKey.trim();
    if (selectedProvider === 'openai' && !trimmedKey.startsWith('sk-')) {
      setError('Invalid API key format. OpenAI API keys should start with "sk-"');
      setIsSubmitting(false);
      return;
    }
    if (selectedProvider === 'anthropic' && !trimmedKey.startsWith('sk-ant-')) {
      setError('Invalid API key format. Anthropic API keys should start with "sk-ant-"');
      setIsSubmitting(false);
      return;
    }
    setIsValidating(true);
    setError('');
    const validation = await validateApiKey(trimmedKey, selectedProvider);
    setIsValidating(false);
    if (!validation.valid) {
      setError(validation.error || 'Invalid API key. Please check your key and try again.');
      setIsSubmitting(false);
      return;
    }
    try {
      const storageKeys = {
        gemini: GEMINI_STORAGE_KEY,
        openai: STORAGE_KEY,
        anthropic: ANTHROPIC_STORAGE_KEY
      };
      localStorage.setItem(storageKeys[selectedProvider], trimmedKey);
      localStorage.setItem(PROVIDER_STORAGE_KEY, selectedProvider);
      dispatchApiKeyChanged();
      setSuccess(true);
      setApiKey('');
      setTimeout(() => {
        window.location.reload();
      }, 1000);
    } catch (err) {
      setError(err.message || 'Failed to save API key. Please try again.');
      setIsSubmitting(false);
    }
  };
  const baseFilePath = file || 'src/hello_world.ts';
  let filePath = baseFilePath;
  if (typeof lines === 'string' && lines.trim()) {
    const lineParts = lines.split('-');
    if (lineParts.length === 2) {
      filePath = `${filePath}:L${lineParts[0].trim()}-L${lineParts[1].trim()}`;
    } else {
      filePath = `${filePath}:L${lineParts[0].trim()}`;
    }
  } else if (typeof lines === 'object' && lines.start !== undefined) {
    filePath = lines.end !== undefined ? `${filePath}:L${lines.start}-L${lines.end}` : `${filePath}:L${lines.start}`;
  }
  const stackblitzUrl = `https://stackblitz.com/github/${repo}?file=${encodeURIComponent(filePath)}&embed=1&view=editor&theme=${theme}`;
  const loadSDK = () => {
    return new Promise((resolve, reject) => {
      if (window.StackBlitzSDK || window.stackblitzSDK) {
        resolve(window.StackBlitzSDK || window.stackblitzSDK);
        return;
      }
      if (document.querySelector('script[data-stackblitz-sdk]')) {
        const checkInterval = setInterval(() => {
          if (window.StackBlitzSDK || window.stackblitzSDK) {
            clearInterval(checkInterval);
            resolve(window.StackBlitzSDK || window.stackblitzSDK);
          }
        }, 100);
        setTimeout(() => {
          clearInterval(checkInterval);
          reject(new Error('SDK loading timeout'));
        }, 10000);
        return;
      }
      const script = document.createElement('script');
      script.src = 'https://unpkg.com/@stackblitz/sdk/bundles/sdk.umd.js';
      script.async = true;
      script.setAttribute('data-stackblitz-sdk', 'true');
      script.onload = () => {
        const sdk = window.StackBlitzSDK || window.stackblitzSDK;
        if (sdk) {
          resolve(sdk);
        } else {
          reject(new Error('SDK loaded but not available on window'));
        }
      };
      script.onerror = () => {
        reject(new Error('Failed to load StackBlitz SDK'));
      };
      document.head.appendChild(script);
    });
  };
  const LOAD_TIMEOUT_MS = 10000;
  const iframeElRef = useRef(null);
  const reloadCountRef = useRef(0);
  const handleRetry = () => {
    vmRef.current = null;
    hasCreatedEnvRef.current = false;
    reloadCountRef.current = 0;
    setIsStuck(false);
    setIframeKey(prev => prev + 1);
  };
  const iframeRef = iframe => {
    iframeElRef.current = iframe;
  };
  const connectToVM = async iframe => {
    const sdk = await loadSDK();
    return sdk.connect(iframe);
  };
  const handleIframeLoad = async () => {
    const iframe = iframeElRef.current;
    if (!iframe) return;
    if (reloadCountRef.current > 0) {
      try {
        const vm = await connectToVM(iframe);
        vmRef.current = vm;
        await updateEnvFile(vm);
      } catch (_) {}
      return;
    }
    try {
      if (vmRef.current) return;
      const vm = await Promise.race([connectToVM(iframe), new Promise((_, reject) => setTimeout(() => reject(new Error('connect timeout')), LOAD_TIMEOUT_MS))]);
      vmRef.current = vm;
      await updateEnvFile(vm);
    } catch (error) {
      console.error('Failed to connect to StackBlitz VM:', error);
      if (typeof window !== 'undefined' && window.gtag) {
        window.gtag('event', 'load_refresh_error', {
          event_category: 'stackblitz',
          event_label: file,
          error_message: error.message
        });
      }
      reloadCountRef.current = 1;
      setTimeout(() => {
        setIframeKey(prev => prev + 1);
      }, 2000);
    }
  };
  const isSafari = typeof navigator !== 'undefined' && (/^((?!chrome|android).)*safari/i).test(navigator.userAgent);
  if (isSafari) {
    return <div className="code-editor-dialog-container" style={{
      height: height
    }}>
        <div className="code-editor-dialog-box">
          <h2 className="code-editor-dialog-title">
            <svg width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="#f59e0b" strokeWidth="2">
              <path d="M10.29 3.86L1.82 18a2 2 0 0 0 1.71 3h16.94a2 2 0 0 0 1.71-3L13.71 3.86a2 2 0 0 0-3.42 0z"></path>
              <line x1="12" y1="9" x2="12" y2="13"></line>
              <line x1="12" y1="17" x2="12.01" y2="17"></line>
            </svg>
            Browser Not Supported
          </h2>
          <p className="code-editor-dialog-description">
            The interactive code editor is not supported on Safari. Please use <strong>Chrome</strong>, <strong>Edge</strong>, or <strong>Firefox</strong> to run the examples.
          </p>
        </div>
      </div>;
  }
  if (showApiKeyDialog) {
    return <div className="code-editor-dialog-container" style={{
      height: height
    }}>
        <div className="code-editor-dialog-box">
          <h2 className="code-editor-dialog-title">
            <svg width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="#f59e0b" strokeWidth="2">
              <path d="M10.29 3.86L1.82 18a2 2 0 0 0 1.71 3h16.94a2 2 0 0 0 1.71-3L13.71 3.86a2 2 0 0 0-3.42 0z"></path>
              <line x1="12" y1="9" x2="12" y2="13"></line>
              <line x1="12" y1="17" x2="12.01" y2="17"></line>
            </svg>
            Configure API Key
          </h2>

          <p className="code-editor-dialog-description">
            All interactive examples execute entirely within your browser environment, ensuring complete security and privacy.
            Your API key is stored locally in your browser's storage and is never transmitted to external servers.
          </p>

          <div className="llm-provider-tabs" style={{
      marginBottom: '16px'
    }}>
            <button type="button" onClick={() => {
      setSelectedProvider('gemini');
      setError('');
      setApiKey('');
    }} className={`llm-provider-tab ${selectedProvider === 'gemini' ? 'llm-provider-tab-active' : ''}`}>
              Gemini <span className="llm-provider-tab-badge">Free</span>
            </button>
            <button type="button" onClick={() => {
      setSelectedProvider('openai');
      setError('');
      setApiKey('');
    }} className={`llm-provider-tab ${selectedProvider === 'openai' ? 'llm-provider-tab-active' : ''}`}>
              OpenAI
            </button>
            <button type="button" onClick={() => {
      setSelectedProvider('anthropic');
      setError('');
      setApiKey('');
    }} className={`llm-provider-tab ${selectedProvider === 'anthropic' ? 'llm-provider-tab-active' : ''}`}>
              Claude
            </button>
          </div>

          {selectedProvider === 'gemini' && <div className="llm-gemini-recommendation" style={{
      marginBottom: '16px'
    }}>
              Gemini offers a generous free tier — great for learning! Get your free API key at{' '}
              <a href="https://aistudio.google.com/apikey" target="_blank" rel="noopener noreferrer" className="code-editor-link">
                aistudio.google.com/apikey
              </a>
            </div>}

          {selectedProvider === 'openai' && <div className="code-editor-info-box">
              <p className="code-editor-info-box-title">
                Don't have an API key?
              </p>
              <p className="code-editor-info-box-text">
                Get one at{' '}
                <a href="https://platform.openai.com/api-keys" target="_blank" rel="noopener noreferrer" className="code-editor-link">
                  platform.openai.com/api-keys
                </a>
              </p>
            </div>}

          {selectedProvider === 'anthropic' && <div className="code-editor-info-box">
              <p className="code-editor-info-box-title">
                Don't have an API key?
              </p>
              <p className="code-editor-info-box-text">
                Get one at{' '}
                <a href="https://console.anthropic.com/settings/keys" target="_blank" rel="noopener noreferrer" className="code-editor-link">
                  console.anthropic.com/settings/keys
                </a>
              </p>
            </div>}

          <form onSubmit={handleApiKeySubmit}>
            <div className="code-editor-form-group">
              <label htmlFor="api-key-input" className="code-editor-label">
                {selectedProvider === 'gemini' ? 'Gemini' : 'OpenAI'} API Key
              </label>
              <input id="api-key-input" type="password" value={apiKey} onChange={e => {
      setApiKey(e.target.value);
      setError('');
      setSuccess(false);
    }} placeholder={selectedProvider === 'openai' ? 'sk-...' : 'Gemini API Key'} disabled={isSubmitting} className={`code-editor-input ${error ? 'code-editor-input-error' : ''}`} />
            </div>

            {isValidating && <div className="code-editor-message code-editor-message-info">
                <span className="code-editor-message-icon">⏳</span>
                <span>Validating API key...</span>
              </div>}

            {error && !isValidating && <div className="code-editor-message code-editor-message-error">
                <span className="code-editor-message-icon">⚠️</span>
                <span>{error}</span>
              </div>}

            {success && <div className="code-editor-message code-editor-message-success">
                <span className="code-editor-message-icon">✓</span>
                <span>API key saved successfully! Loading editor...</span>
              </div>}

            <button type="submit" disabled={isSubmitting || isValidating || !apiKey.trim()} className="code-editor-button">
              {isValidating ? 'Validating...' : isSubmitting ? 'Saving...' : 'Save API Key'}
            </button>
          </form>

          <button type="button" onClick={handleSkipConfiguration} disabled={isSubmitting || isValidating} className="code-editor-button-secondary">
            Skip Configuration
          </button>

          <div className="code-editor-footer">
            <p className="code-editor-footer-text">
              Alternatively, you may checkout the source code from{' '}
              <a href="https://github.com/ai-tutorial/typescript-examples" target="_blank" rel="noopener noreferrer" className="code-editor-link code-editor-link-break">
                https://github.com/ai-tutorial/typescript-examples
              </a>
              {' '}and run the examples locally.
            </p>
          </div>
        </div>
      </div>;
  }
  const toggleMaximize = () => setIsMaximized(!isMaximized);
  const toggleCollapse = () => setIsCollapsed(!isCollapsed);
  return <div className={`code-editor-wrapper ${isMaximized ? 'maximized' : ''} ${isCollapsed ? 'collapsed' : ''}`} data-theme={theme}>
      <div className="code-editor-header">
        <div className="code-editor-title">
          <svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2" strokeLinecap="round" strokeLinejoin="round">
            <path d="M11 4H4a2 2 0 0 0-2 2v14a2 2 0 0 0 2 2h14a2 2 0 0 0 2-2v-7"></path>
            <path d="M18.5 2.5a2.121 2.121 0 0 1 3 3L12 15l-4 1 1-4 9.5-9.5z"></path>
          </svg>
          {title}
        </div>
        <div className="code-editor-controls">
          {!isMaximized && <button className="code-editor-collapse-button" onClick={toggleCollapse} title={isCollapsed ? "Expand" : "Collapse"} type="button">
              <svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2" strokeLinecap="round" strokeLinejoin="round">
                {isCollapsed ? <polyline points="6 9 12 15 18 9" /> : <polyline points="6 15 12 9 18 15" />}
              </svg>
            </button>}
          <button className="code-editor-maximize-button" onClick={toggleMaximize} title={isMaximized ? "Minimize" : "Maximize (Focus Mode)"} type="button">
            <svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2" strokeLinecap="round" strokeLinejoin="round">
              {isMaximized ? <><path d="M4 14h6v6" /><path d="M20 10h-6V4" /><path d="M14 10l7-7" /><path d="M3 21l7-7" /></> : <><path d="M15 3h6v6" /><path d="M9 21H3v-6" /><path d="M21 3l-7 7" /><path d="M3 21l7-7" /></>}
            </svg>
          </button>
        </div>
      </div>

      {!isCollapsed && <div style={{
    position: 'relative',
    height: isMaximized ? 'auto' : height,
    flex: isMaximized ? 1 : 'none'
  }}>
          <iframe key={iframeKey} ref={iframeRef} onLoad={handleIframeLoad} src={stackblitzUrl} className="code-editor-iframe" style={{
    height: '100%',
    flex: isMaximized ? 1 : 'none'
  }} title={title || 'Code Example'} allow="accelerometer; camera; encrypted-media; geolocation; gyroscope; hid; microphone; midi; payment; usb; xr-spatial-tracking" sandbox="allow-forms allow-modals allow-popups allow-presentation allow-same-origin allow-scripts" />

          {isStuck && <div className="code-editor-stuck-overlay">
              <div className="code-editor-stuck-box">
                <svg width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="#f59e0b" strokeWidth="2">
                  <path d="M10.29 3.86L1.82 18a2 2 0 0 0 1.71 3h16.94a2 2 0 0 0 1.71-3L13.71 3.86a2 2 0 0 0-3.42 0z"></path>
                  <line x1="12" y1="9" x2="12" y2="13"></line>
                  <line x1="12" y1="17" x2="12.01" y2="17"></line>
                </svg>
                <p>StackBlitz is taking too long to load. This can happen when the repository was recently updated.</p>
                <button type="button" className="code-editor-button" onClick={handleRetry} style={{
    marginTop: '8px'
  }}>
                  Retry
                </button>
              </div>
            </div>}
        </div>}
    </div>;
};

RAG systems fail silently — wrong answers look confident. This page covers retrieval metrics, LLM-as-Judge, golden datasets, and debugging failures.

## Why Evaluation is Non-Negotiable

You've built an incredible, multi-stage RAG pipeline. Now for the hard truth: it's failing. In production, RAG systems usually fail not because the LLM is bad, but because the context it receives is subtly wrong. A poor retrieval result, even if ranked fifth, can derail the answer. Without a clear evaluation framework, you're debugging blind, relying on "vibe checks" that fail in production.

**What Problem It Solves:** Systematic evaluation isolates failures. It answers: Did the system hallucinate because the relevant document wasn't found (Retrieval Failure), or because the LLM ignored the document that was found (Generation Failure)? This single distinction saves countless hours of wasted effort on prompt tuning when the real fix is adjusting your chunking strategy.

**Real-World Example:** Teams often spend weeks trying to fix LLM hallucination with better prompts, only to discover the root cause was a weak embedding model missing critical, domain-specific documents. We'll learn to diagnose the real issue upfront.

## The Two-Part Evaluation

The RAG pipeline has two core components that must be evaluated and debugged independently: Retrieval and Generation

1. **Retrieval Quality:** Did we find the right documents?
2. **Generation Quality:** Did the LLM use them correctly?

```
Query: "What's our refund policy?"
                  │
                  v
          +---------------+
          │   Retrieval   │ ← Evaluate: Are docs relevant?
          +---------------+
                  │
        Retrieved: Doc A, Doc B, Doc C
                  │
                  v
          +---------------+
          │  Generation   │ ← Evaluate: Is answer faithful?
          +---------------+
                  │
                  v
          Answer: "30-day returns..."
```

### The ARES Framework for Failure Attribution

We'll use a simplified version of the ARES framework (Answer Relevance, Evidence Support) to diagnose every failure based on three component checks:

| Check                   | Component  | Goal                                                    | Metric Type                 |
| :---------------------- | :--------- | :------------------------------------------------------ | :-------------------------- |
| **Context Relevance**   | Retrieval  | Did we retrieve the necessary ground-truth document(s)? | Recall\@k, NDCG\@k          |
| **Answer Faithfulness** | Generation | Is the answer grounded *only* in the retrieved context? | LLM-as-Judge (Faithfulness) |
| **Answer Relevance**    | Generation | Does the answer address the original query?             | LLM-as-Judge (Relevance)    |

If you get a wrong answer, you run this checklist: If Context Relevance is low, fix the retriever. If Context Relevance is high but Faithfulness or Relevance are low, fix the generator's prompt or the reranker.

## Part 1: Retrieval Metrics  (Did we find it?)

**Recall\@k: Are the relevant docs in the top-k?**

* **Definition:** What fraction of relevant documents did we retrieve?

* **When to use:** Measuring if all important docs are findable

* **Target:** Recall\@10 > 0.90 (catch 90%+ relevant docs in first 10)

**Precision\@k: Are the retrieved docs relevant?**

* **Definition:** What fraction of retrieved documents are actually relevant?

* **When to use:** Measuring retrieval noise/irrelevance

* **Target:** Precision\@5 > 0.80 (80%+ of top-5 are useful)

**NDCG\@k: Are relevant docs ranked higher?**

* **Definition:** Normalized Discounted Cumulative Gain - considers ranking order.

* **Why it matters:** Getting relevant doc at position 1 is better than position 10.

* **When to use:** Measuring overall retrieval quality (position matters)

* **Target:** NDCG\@10 > 0.80 (strong ranking)

**Mean Reciprocal Rank (MRR): How quickly do we find relevance?**

* **Definition:** Average of 1/rank for first relevant doc.

* **When to use:** User-focused metric (fast discovery matters)

* **Target:** MRR > 0.80 (relevant doc in top \~1-2 results)

### Setup and Metric Calculation

We'll use hit\_rate (a simple form of recall), MRR, Precision, and NDCG.

<CodeEditor file="src/rag/rag_evaluation.ts" lines="29-82" functionName="main" title="Setup & Retrieval Evaluation" />

## Part 2: Generation Quality

Now evaluate if the LLM used retrieved context correctly.

### Faithfulness: Is the answer grounded in context?

**Definition:** Does the answer only contain info from retrieved docs?

**Target:** Faithfulness > 0.90 (less than 10% hallucination)

### Relevance: Does the answer address the query?

**Definition:** Is the answer on-topic and helpful for the question?

**Target:** Relevance > 0.85 (answers actually helpful)

## LLM-as-Judge

Traditional evaluation metrics require labeled ground truth, but for generation quality—measuring faithfulness and relevance—we can leverage LLMs themselves as evaluators. The **LLM-as-Judge** approach uses a separate LLM to act as an impartial judge that scores whether a response is faithful to the retrieved context and relevant to the original query.

**Main advantage:** The primary benefit of LLM-as-Judge is that it can be used in **production environments where there is no ground truth**. Unlike retrieval metrics that require manually labeled relevant documents, or traditional answer evaluation that needs expected answers, LLM-as-Judge can evaluate any query-response pair in real-time by comparing the response against the retrieved context. This makes it ideal for continuous monitoring of production RAG systems.

**Why it works:** Modern LLMs are remarkably good at understanding semantic relationships and detecting inconsistencies. When given a query, a response, and the source context, a judge LLM can reliably determine if the answer is grounded in the provided documents (faithfulness) and if it actually addresses what was asked (relevance).

**Critical requirement:** Before deploying LLM-as-Judge in production, you must **evaluate and optimize the judge itself using ground truth data**. Create a validation set with human-annotated examples (e.g., 50-100 cases where you know the correct faithfulness/relevance scores), run the judge on these cases, and measure its accuracy against human labels. If the judge's scores don't align with ground truth (>85% agreement), adjust the judge model, prompts, or temperature settings. This calibration step ensures your judge is actually judging correctly before you rely on it for production monitoring.

**Trade-offs:** While faster and more scalable than human evaluation, LLM-as-Judge has costs (API calls to the judge model) and can occasionally disagree with human annotators on edge cases. Use it for continuous monitoring and initial evaluation, but validate critical failures with human review.

<CodeEditor file="src/rag/rag_evaluation.ts" lines="84-123" functionName="main" title="Generation Evaluation" />

## Building a Golden Dataset

**The most important step:** You need ground truth test cases.

### How to Create Golden Dataset

<CodeEditor file="src/rag/rag_monitoring.ts" lines="66-96" functionName="generateGoldenDataset" title="Golden Dataset Creation" />

**Golden dataset best practices:**

* **Size:** 50-100 queries minimum, 500+ ideal
* **Diversity:** Cover all query types (factual, conceptual, multi-hop)
* **Difficulty:** Include easy and hard cases
* **Updates:** Refresh quarterly as corpus changes
* **Multiple annotators:** Inter-annotator agreement > 0.80

## Debugging RAG Failures

When evaluation reveals problems, debug systematically.

<CodeEditor file="src/rag/rag_monitoring.ts" lines="152-195" functionName="debugRAGFailureWithScores" title="Debug RAG Failures" />

## Continuous Evaluation

<CodeEditor file="src/rag/rag_monitoring.ts" lines="197-242" functionName="ProductionRAGMonitor" title="Continuous Evaluation Monitor" />

**Monitoring frequency:**

* Log 100% of queries (for debugging)
* Evaluate 10% of queries (cost management)
* Full golden dataset evaluation weekly
* Alert on >10% metric drops

<Quiz>
  <QuizQuestion question="Your RAG system gives wrong answers. What should you check first?" options={["Whether the LLM prompt needs better instructions", "Whether retrieval found the right documents (context relevance) — most failures are retrieval failures", "Whether the model is too small"]} answer={1} explanation="70% of RAG failures come from retrieval, not generation. Always check if the right documents were found before tuning prompts." />

  <QuizQuestion question="What is the main advantage of LLM-as-Judge evaluation?" options={["It's free to run", "It can evaluate in production without ground truth labels by comparing responses against retrieved context", "It's more accurate than human evaluation"]} answer={1} explanation="LLM-as-Judge can run on any query-response pair in production without needing pre-labeled ground truth, making it ideal for continuous monitoring." />
</Quiz>