本文為英文版的機器翻譯版本，如內容有任何歧義或不一致之處，概以英文版為準。

# 為僅擷取 RAG 評估任務建立提示資料集
<a name="knowledge-base-evaluation-prompt-retrieve"></a>

僅擷取評估任務需要使用 JSON 行格式的提示資料集。您的資料集最多可有 1000 個提示。

## 為 Amazon Bedrock 調用您知識庫的僅擷取評估任務準備資料集
<a name="knowledge-base-evaluation-prompt-retrieve-invoke"></a>

若要建立 Amazon Bedrock 調用您知識庫的僅擷取評估任務，您的提示資料集必須包含下列鍵值對：
+ `referenceResponses` – 此父金鑰用於指定您預期端對端 RAG 系統傳回的基本事實回應。此參數不代表您預期從知識庫擷取的預期段落或區塊。在 `text` 索引鍵中指定基本事實。如果您在評估任務中選擇**內容涵蓋範圍**指標，則需要 `referenceResponses`。
+ `prompt` – 此父金鑰用於指定您想要讓 RAG 系統回應的提示 (使用者查詢)。

以下是包含 6 個輸入並使用 JSON 行格式的自訂資料集範例。

```
{"conversationTurns":[{"prompt":{"content":[{"text":"Provide the prompt you want to use during inference"}]},"referenceResponses":[{"content":[{"text":"Specify a ground-truth response"}]}]}]}
{"conversationTurns":[{"prompt":{"content":[{"text":"Provide the prompt you want to use during inference"}]},"referenceResponses":[{"content":[{"text":"Specify a ground-truth response"}]}]}]}
{"conversationTurns":[{"prompt":{"content":[{"text":"Provide the prompt you want to use during inference"}]},"referenceResponses":[{"content":[{"text":"Specify a ground-truth response"}]}]}]}
{"conversationTurns":[{"prompt":{"content":[{"text":"Provide the prompt you want to use during inference"}]},"referenceResponses":[{"content":[{"text":"Specify a ground-truth response"}]}]}]}
{"conversationTurns":[{"prompt":{"content":[{"text":"Provide the prompt you want to use during inference"}]},"referenceResponses":[{"content":[{"text":"Specify a ground-truth response"}]}]}]}
{"conversationTurns":[{"prompt":{"content":[{"text":"Provide the prompt you want to use during inference"}]},"referenceResponses":[{"content":[{"text":"Specify a ground-truth response"}]}]}]}
```

為了清楚起見，下列提示已展開。在實際提示資料集中，每行 (提示) 必須是有效的 JSON 物件。

```
{
    "conversationTurns": [
        {
            "prompt": {
                "content": [
                    {
                        "text": "What is the recommended service interval for your product?"
                    }
                ]
            },
            "referenceResponses": [
                {
                    "content": [
                        {
                            "text": "The recommended service interval for our product is two years."
                        }
                    ]
                }
            ]
        }
    ]
}
```

## 使用您自己的推論回應資料準備資料集以用於僅擷取評估任務
<a name="knowledge-base-evaluation-prompt-retrieve-byoir"></a>

若要在提供自己的推論回應資料的位置建立僅擷取評估任務，您的提示資料集必須包含下列項目：
+ `prompt` – 此父金鑰用於指定您用來產生推論回應資料的提示 (使用者查詢)。
+ `referenceResponses` – 此父金鑰用於指定您預期端對端 RAG 系統傳回的基本事實回應。此參數不代表您預期從知識庫擷取的預期段落或區塊。在 `text` 索引鍵中指定基本事實。如果您在評估任務中選擇**內容涵蓋範圍**指標，則需要 `referenceResponses`。
+ `referenceContexts` (選用) – 此選用父金鑰用於指定您預期從 RAG 來源擷取的基本事實段落。只有在您想要在自己的自訂評估指標中使用它時，才需要包含此金鑰。Amazon Bedrock 提供的內建指標不會使用此屬性。
+ `knowledgeBaseIdentifier` – 客戶定義的字串，識別用於產生擷取結果的 RAG 來源。
+ `retrievedResults` – 具有擷取結果清單的 JSON 物件。對於每個結果，您可以提供指定為鍵值對的選用 `name` 和選用 `metadata`。

以下是包含 6 個輸入並使用 JSON 行格式的自訂資料集範例。

```
{"conversationTurns":[{"prompt":{"content":[{"text":"The prompt you used to generate your response"}]},"referenceResponses":[{"content":[{"text":"A ground-truth response"}]}],"referenceContexts":[{"content":[{"text":"A ground truth for a received passage"}]}],"output":{"knowledgeBaseIdentifier":"A string identifying your RAG source","retrievedResults":{"retrievalResults":[{"name":"(Optional) a name for your reference context","content":{"text":"The output from your RAG inference"},"metadata":{"(Optional) a key for your metadata":"(Optional) a metadata value"}}]}}}]}
{"conversationTurns":[{"prompt":{"content":[{"text":"The prompt you used to generate your response"}]},"referenceResponses":[{"content":[{"text":"A ground-truth response"}]}],"referenceContexts":[{"content":[{"text":"A ground truth for a received passage"}]}],"output":{"knowledgeBaseIdentifier":"A string identifying your RAG source","retrievedResults":{"retrievalResults":[{"name":"(Optional) a name for your reference context","content":{"text":"The output from your RAG inference"},"metadata":{"(Optional) a key for your metadata":"(Optional) a metadata value"}}]}}}]}
{"conversationTurns":[{"prompt":{"content":[{"text":"The prompt you used to generate your response"}]},"referenceResponses":[{"content":[{"text":"A ground-truth response"}]}],"referenceContexts":[{"content":[{"text":"A ground truth for a received passage"}]}],"output":{"knowledgeBaseIdentifier":"A string identifying your RAG source","retrievedResults":{"retrievalResults":[{"name":"(Optional) a name for your reference context","content":{"text":"The output from your RAG inference"},"metadata":{"(Optional) a key for your metadata":"(Optional) a metadata value"}}]}}}]}
{"conversationTurns":[{"prompt":{"content":[{"text":"The prompt you used to generate your response"}]},"referenceResponses":[{"content":[{"text":"A ground-truth response"}]}],"referenceContexts":[{"content":[{"text":"A ground truth for a received passage"}]}],"output":{"knowledgeBaseIdentifier":"A string identifying your RAG source","retrievedResults":{"retrievalResults":[{"name":"(Optional) a name for your reference context","content":{"text":"The output from your RAG inference"},"metadata":{"(Optional) a key for your metadata":"(Optional) a metadata value"}}]}}}]}
{"conversationTurns":[{"prompt":{"content":[{"text":"The prompt you used to generate your response"}]},"referenceResponses":[{"content":[{"text":"A ground-truth response"}]}],"referenceContexts":[{"content":[{"text":"A ground truth for a received passage"}]}],"output":{"knowledgeBaseIdentifier":"A string identifying your RAG source","retrievedResults":{"retrievalResults":[{"name":"(Optional) a name for your reference context","content":{"text":"The output from your RAG inference"},"metadata":{"(Optional) a key for your metadata":"(Optional) a metadata value"}}]}}}]}
{"conversationTurns":[{"prompt":{"content":[{"text":"The prompt you used to generate your response"}]},"referenceResponses":[{"content":[{"text":"A ground-truth response"}]}],"referenceContexts":[{"content":[{"text":"A ground truth for a received passage"}]}],"output":{"knowledgeBaseIdentifier":"A string identifying your RAG source","retrievedResults":{"retrievalResults":[{"name":"(Optional) a name for your reference context","content":{"text":"The output from your RAG inference"},"metadata":{"(Optional) a key for your metadata":"(Optional) a metadata value"}}]}}}]}
```

為了清楚起見，下列提示已展開。在實際提示資料集中，每行 (提示) 必須是有效的 JSON 物件。

```
{
  "conversationTurns": [
    {
      "prompt": {
        "content": [
          {
            "text": "What is the recommended service interval for your product?"
          }
        ]
      },
      "referenceResponses": [
        {
          "content": [
            {
              "text": "The recommended service interval for our product is two years."
            }
          ]
        }
      ],
      "referenceContexts": [
        {
          "content": [
            {
              "text": "A ground truth for a received passage"
            }
          ]
        }
      ],
       "output": {
        "knowledgeBaseIdentifier": "RAG source 1",
        "retrievedResults": {
          "retrievalResults": [
            {
              "name": "(Optional) a name for your retrieval",
              "content": {
                "text": "The recommended service interval for our product is two years."
              },
              "metadata": {
                "(Optional) a key for your metadata": "(Optional) a value for your metadata"
              }
            }
          ]
        }
      }
    }
  ]
}
```