知识图谱操作（四）Neo4j-基于节点和节点集构建知识地图（关键子图）

Chk_

已于 2024-06-24 09:47:15 修改

阅读量348

点赞数 5

文章标签： prompt python 开发语言

于 2024-05-31 14:30:43 首次发布

本文链接：https://blog.youkuaiyun.com/m0_63358814/article/details/139351858

版权

制作Prompt模板

def create_prompt_template(retrieved_docs, query):
    context = "\n".join([f"Document {i+1}:\n{doc}" for i, doc in enumerate(retrieved_docs)])
    prompt = f"Context:\n{context}\n\nQuery: {query}\n\nAnswer:"
    return prompt

# 创建Prompt Template
prompt_template = create_prompt_template(retrieved_docs, query)
print("Prompt Template:\n", prompt_template)

将知识嵌入模型Prompt中

检索到的文档内容：

Document 1: "Paris is the capital and most populous city of France."
Document 2: "France, officially the French Republic, is a country primarily located in Western Europe."
Document 3: "The capital city of France is Paris, which is known for its art, fashion, and culture."

模型Prompt模板：

You should answer the Query by these contexts

Context:通过用户输入在向量库中检索到的相关文档

Que