問答資料集 Template

interface QAExample {
  question: string;
  context: string;        // Source passage for context-grounded QA
  answer: string;         // The expected answer
  answer_start?: number;  // Character offset for extractive QA
  is_answerable: boolean; // Whether the context contains the answer
  metadata: {
    source_document: string;
    domain: string;
    difficulty: "easy" | "medium" | "hard";
    question_type: "factoid" | "reasoning" | "comparison" | "procedural";
  };
}

[
  {
    "question": "What is the maximum file size supported for GGUF model uploads?",
    "context": "Ertas Studio supports GGUF model files up to 50GB in size. For models exceeding this limit, the sharded upload feature allows splitting the model into multiple files, each up to 50GB. The platform automatically reassembles sharded models during deployment. Upload speeds depend on your network connection, with typical enterprise connections achieving 500MB-1GB per minute. All uploads are encrypted in transit using TLS 1.3.",
    "answer": "The maximum file size for GGUF model uploads is 50GB. For larger models, the sharded upload feature can split files into multiple 50GB chunks that are automatically reassembled during deployment.",
    "answer_start": 30,
    "is_answerable": true,
    "metadata": {
      "source_document": "ertas-studio-docs/uploads.md",
      "domain": "product-documentation",
      "difficulty": "easy",
      "question_type": "factoid"
    }
  },
  {
    "question": "How does the PII redaction engine handle names that are also common words?",
    "context": "The PII redaction engine uses a combination of named entity recognition (NER), pattern matching, and contextual analysis to identify personal information. For names that are also common words (e.g., 'Grace', 'Rose', 'Mark'), the engine evaluates surrounding context to determine whether the word is being used as a proper name or a common noun. Contextual signals include capitalization, position in the sentence, surrounding words (Mr., Ms., Dr.), and semantic role. The engine defaults to redaction when the confidence score exceeds 0.7, with a configurable threshold that organizations can adjust based on their risk tolerance.",
    "answer": "The PII redaction engine uses contextual analysis alongside NER and pattern matching to distinguish names from common words. It evaluates capitalization, sentence position, surrounding words (like Mr., Ms., Dr.), and semantic role. When the confidence score exceeds 0.7 (a configurable threshold), it defaults to redaction.",
    "answer_start": 0,
    "is_answerable": true,
    "metadata": {
      "source_document": "ertas-data-suite-docs/pii-redaction.md",
      "domain": "product-documentation",
      "difficulty": "medium",
      "question_type": "reasoning"
    }
  },
  {
    "question": "Can I export models in TensorRT format from Ertas Studio?",
    "context": "Ertas Studio supports model export in three formats: GGUF for local CPU/GPU inference, SafeTensors for GPU-based deployment with frameworks like vLLM and TGI, and ONNX for cross-platform deployment with ONNX Runtime. Export configurations include quantization level selection, metadata embedding, and tokenizer bundling.",
    "answer": "No, TensorRT format is not currently supported. Ertas Studio supports export in three formats: GGUF, SafeTensors, and ONNX.",
    "answer_start": -1,
    "is_answerable": true,
    "metadata": {
      "source_document": "ertas-studio-docs/export.md",
      "domain": "product-documentation",
      "difficulty": "easy",
      "question_type": "factoid"
    }
  }
]