RAG Prompt Builder — Tạo yêu cầu Ollama /api/chat chỉ trả lời từ các nguồn có đánh số, có trích dẫn

3 nguồn, được đọc là một mảng JSON các đối tượng.

Gửi yêu cầu tới Ollama trên máy này (localhost:11434).

curl http://localhost:11434/api/chat -d '{
  "model": "qwen2.5:7b",
  "messages": [
    {
      "role": "system",
      "content": "Answer the question using only the numbered sources in the user message. Cite the number of each source you use. If the sources do not contain the answer, say that you do not know and cite nothing. Answer in the same language as the question. For each citation, give the source number and copy a short quote from that source exactly as it is written. Return JSON that matches this schema: {\"type\":\"object\",\"properties\":{\"answer\":{\"type\":\"string\"},\"citations\":{\"type\":\"array\",\"items\":{\"type\":\"object\",\"properties\":{\"source\":{\"type\":\"integer\"},\"quote\":{\"type\":\"string\"}},\"required\":[\"source\",\"quote\"]}}},\"required\":[\"answer\",\"citations\"]}"
    },
    {
      "role": "user",
      "content": "Sources:\n\n[1] (id: 12)\nWith HNSW, hnsw.ef_search is 40 by default, so a query returns at most 40 rows unless you raise it.\n\n[2] (id: 7)\nSET LOCAL inside a transaction changes hnsw.ef_search for a single query.\n\n[3] (id: 3)\npgvector supports PostgreSQL 13 and later.\n\nQuestion: Why does my HNSW search return only 40 rows with LIMIT 100?"
    }
  ],
  "stream": false,
  "format": {
    "type": "object",
    "properties": {
      "answer": {
        "type": "string"
      },
      "citations": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "source": {
              "type": "integer"
            },
            "quote": {
              "type": "string"
            }
          },
          "required": [
            "source",
            "quote"
          ]
        }
      }
    },
    "required": [
      "answer",
      "citations"
    ]
  },
  "options": {
    "temperature": 0
  },
  "truncate": false
}'

{
  "model": "qwen2.5:7b",
  "messages": [
    {
      "role": "system",
      "content": "Answer the question using only the numbered sources in the user message. Cite the number of each source you use. If the sources do not contain the answer, say that you do not know and cite nothing. Answer in the same language as the question. For each citation, give the source number and copy a short quote from that source exactly as it is written. Return JSON that matches this schema: {\"type\":\"object\",\"properties\":{\"answer\":{\"type\":\"string\"},\"citations\":{\"type\":\"array\",\"items\":{\"type\":\"object\",\"properties\":{\"source\":{\"type\":\"integer\"},\"quote\":{\"type\":\"string\"}},\"required\":[\"source\",\"quote\"]}}},\"required\":[\"answer\",\"citations\"]}"
    },
    {
      "role": "user",
      "content": "Sources:\n\n[1] (id: 12)\nWith HNSW, hnsw.ef_search is 40 by default, so a query returns at most 40 rows unless you raise it.\n\n[2] (id: 7)\nSET LOCAL inside a transaction changes hnsw.ef_search for a single query.\n\n[3] (id: 3)\npgvector supports PostgreSQL 13 and later.\n\nQuestion: Why does my HNSW search return only 40 rows with LIMIT 100?"
    }
  ],
  "stream": false,
  "format": {
    "type": "object",
    "properties": {
      "answer": {
        "type": "string"
      },
      "citations": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "source": {
              "type": "integer"
            },
            "quote": {
              "type": "string"
            }
          },
          "required": [
            "source",
            "quote"
          ]
        }
      }
    },
    "required": [
      "answer",
      "citations"
    ]
  },
  "options": {
    "temperature": 0
  },
  "truncate": false
}

Trong phản hồi, câu trả lời nằm ở message.content. Nếu prompt_eval_count thấp hơn nhiều so với bạn dự đoán, prompt có thể đã bị cắt.