是谁~还不会优雅的构建fewshot!

class SemanticSimilarityExampleSelector(BaseExampleSelector, BaseModel):
    ...
    def select_examples(self, input_variables: Dict[str, str]) -> List[dict]:
        """Select which examples to use based on semantic similarity."""
        # Get the docs with the highest similarity.
        if self.input_keys:
            input_variables = {key: input_variables[key] for key in self.input_keys}
        vectorstore_kwargs = self.vectorstore_kwargs or {}
        query = " ".join(sorted_values(input_variables))
        example_docs = self.vectorstore.similarity_search(
            query, k=self.k, **vectorstore_kwargs
        )
        # Get the examples from the metadata.
        # This assumes that examples are stored in metadata.
        examples = [dict(e.metadata) for e in example_docs]
        # If example keys are provided, filter examples to those keys.
        if self.example_keys:
            examples = [{k: eg[k] for k in self.example_keys} for eg in examples]
        return examples

[
  {
    "input": "人工智能的快速发展为解决复杂问题、改善生活质量和推动科学研究提供了新的机遇。",
    "output": "The rapid development of artificial intelligence provides new opportunities for solving complex problems, improving the quality of life, and advancing scientific research.."
  },
  {
    "input": "人工智能伦理和隐私问题引起了广泛关注，社会需要建立适当的法规和政策来保障公众权益。。",
    "output": "Ethical and privacy concerns related to artificial intelligence have garnered widespread attention, and there is a societal need to establish appropriate regulations and policies to safeguard public interests."
  },
  {
    "input": "聊天机器人的普及使得在网站和应用中提供实时客户支持变得更加便捷和高效。",
    "output": "The prevalence of chatbots makes it more convenient and efficient to provide real-time customer support on websites and applications."
  },
  {
    "input": "医学研究表明，定期锻炼和健康饮食对于预防慢性疾病至关重要。",
    "output": "Medical research indicates that regular exercise and a healthy diet are crucial for preventing chronic diseases.."
  },
  {
    "input": "全球范围内的医疗团队正在共同努力，以应对新型冠状病毒的传播，并寻找有效的治疗方法。",
    "output": "Medical teams worldwide are collaborating to combat the spread of the novel coronavirus and explore effective treatment methods.."
  },
  {
    "input": "在医疗保健系统中，科技创新已经推动了患者护理的改善，使得诊断和治疗更加精准和高效。",
    "output": "In the healthcare system, technological innovation has driven improvements in patient care, making diagnostics and treatments more precise and efficient."
  },
  ...
]

example_selector = SemanticSimilarityExampleSelector.from_examples(
        input_keys=["input"],
        examples=examples,
        embeddings=MyEmbeddings(),
        vectorstore_cls=Chroma,
        k=1,
        )

class MyEmbeddings(Embeddings, BaseModel):
    """Interface for embedding models."""    
    def embed_documents(self, texts: List[str]) -> List[List[float]]:
        """Embed search docs."""
        embeddings = []
        for text in texts:
            embedding = self.embed_query(text)
            embeddings.append(embedding)
        return embeddings
             
    def embed_query(self, text: str) -> List[float]:
        """自定义embedding接口"""
        return your_response

few_shot_prompt = FewShotChatMessagePromptTemplate(
                input_variables=["input"],
                example_selector=example_selector,
                example_prompt=(
                    HumanMessagePromptTemplate.from_template("中文：{input}")
                    + AIMessagePromptTemplate.from_template("英文：{output}")
                ),
            )
final_prompt = (
                SystemMessagePromptTemplate.from_template(
                    "你是一个专业的英文翻译。请根据以下格式回答用户问题："
                )
                + few_shot_prompt
                + HumanMessagePromptTemplate.from_template("中文：{input}")
            )
result = final_prompt.format_messages(input=query)
return result

def get_vectorstore(examples_path="examples.json", input_keys=["input"]):
    """_summary_

    Args:
        examples_path (str, optional): 示例文件，Defaults to "examples.json".
        input_keys (list, optional): 需要过滤的key. Defaults to ["input"].

    Returns:
        _type_: 向量数据库
    """
    with open(examples_path, 'r', encoding='utf-8') as json_file:
        examples = json.load(json_file)
    to_vectorize=[]
    if input_keys:
        to_vectorize = [
                " ".join(sorted_values({k: eg[k] for k in input_keys}))
                for eg in examples
            ]
    else:
        to_vectorize = [
            " ".join(example.values())
            for example in examples
            ]
    embeddings = MyEmbeddings()
    vectorstore = Chroma.from_texts(
        to_vectorize, embeddings, metadatas=examples
        )
    return vectorstore
vectorstore = get_vectorstore(examples_path)

def test_smei_fewshot_prompt_v2(examples_path, query):
    """ 根据相似度获取fewshot
    """
    # vectorstore单例生产一次就行
    example_selector = SemanticSimilarityExampleSelector(
        input_keys=["input"],
        vectorstore=vectorstore,
        k=1,
        )
        ...