Skip to main content
Open In ColabOpen on GitHub

如何创建自定义检索器

概览​

许多大语言模型应用涉及使用 检索器 从外部数据源检索信息。

检索器负责为一个给定的用户query检索相关的文档列表。

检索到的文档通常会被格式化为提示词，并输入到大型语言模型（LLM）中，使 LLM 能够利用这些信息生成合适的响应（例如，基于知识库回答用户问题）。

接口​

要创建您自己的检索器，您需要扩展 BaseRetriever 类并实现以下方法：

方法描述必需/可选
_get_relevant_documentsGet documents relevant to a query.Required
_aget_relevant_documentsImplement to provide async native support.Optional

_get_relevant_documents内部的逻辑可以涉及使用 requests 对数据库或网络进行的任意调用。

提示

通过继承自 BaseRetriever，您的检索器会自动成为 LangChain 可运行对象（Runnable），并开箱即用获得标准的 Runnable 功能！

信息

您可以使用 RunnableLambda 或 RunnableGenerator 来实现一个检索器。

将检索器实现为 BaseRetriever 而不是 RunnableLambda（一个自定义的可运行函数）的主要好处是，BaseRetriever 是一个众所周知的 LangChain 实体，因此某些监控工具可能会为检索器实现专门的行为。另一个区别是，在某些 API 中，BaseRetriever 的行为会与 RunnableLambda 略有不同；例如，astream_events API 中的 start 事件将是 on_retriever_start 而不是 on_chain_start。

示例​

让我们实现一个玩具检索器，它返回所有文本包含用户查询文本的文档。

from typing import List

from langchain_core.callbacks import CallbackManagerForRetrieverRun
from langchain_core.documents import Document
from langchain_core.retrievers import BaseRetriever


class ToyRetriever(BaseRetriever):
    """A toy retriever that contains the top k documents that contain the user query.

    This retriever only implements the sync method _get_relevant_documents.

    If the retriever were to involve file access or network access, it could benefit
    from a native async implementation of `_aget_relevant_documents`.

    As usual, with Runnables, there's a default async implementation that's provided
    that delegates to the sync implementation running on another thread.
    """

    documents: List[Document]
    """List of documents to retrieve from."""
    k: int
    """Number of top results to return"""

    def _get_relevant_documents(
        self, query: str, *, run_manager: CallbackManagerForRetrieverRun
    ) -> List[Document]:
        """Sync implementations for retriever."""
        matching_documents = []
        for document in documents:
            if len(matching_documents) > self.k:
                return matching_documents

            if query.lower() in document.page_content.lower():
                matching_documents.append(document)
        return matching_documents

    # Optional: Provide a more efficient native implementation by overriding
    # _aget_relevant_documents
    # async def _aget_relevant_documents(
    #     self, query: str, *, run_manager: AsyncCallbackManagerForRetrieverRun
    # ) -> List[Document]:
    #     """Asynchronously get documents relevant to a query.

    #     Args:
    #         query: String to find relevant documents for
    #         run_manager: The callbacks handler to use

    #     Returns:
    #         List of relevant documents
    #     """

测试它 🧪​

documents = [
    Document(
        page_content="Dogs are great companions, known for their loyalty and friendliness.",
        metadata={"type": "dog", "trait": "loyalty"},
    ),
    Document(
        page_content="Cats are independent pets that often enjoy their own space.",
        metadata={"type": "cat", "trait": "independence"},
    ),
    Document(
        page_content="Goldfish are popular pets for beginners, requiring relatively simple care.",
        metadata={"type": "fish", "trait": "low maintenance"},
    ),
    Document(
        page_content="Parrots are intelligent birds capable of mimicking human speech.",
        metadata={"type": "bird", "trait": "intelligence"},
    ),
    Document(
        page_content="Rabbits are social animals that need plenty of space to hop around.",
        metadata={"type": "rabbit", "trait": "social"},
    ),
]
retriever = ToyRetriever(documents=documents, k=3)
retriever.invoke("that")
[Document(page_content='Cats are independent pets that often enjoy their own space.', metadata={'type': 'cat', 'trait': 'independence'}),
 Document(page_content='Rabbits are social animals that need plenty of space to hop around.', metadata={'type': 'rabbit', 'trait': 'social'})]

这是一个可运行的组件，因此它将受益于标准的 Runnable 接口！🤩

await retriever.ainvoke("that")
[Document(page_content='Cats are independent pets that often enjoy their own space.', metadata={'type': 'cat', 'trait': 'independence'}),
 Document(page_content='Rabbits are social animals that need plenty of space to hop around.', metadata={'type': 'rabbit', 'trait': 'social'})]
retriever.batch(["dog", "cat"])
[[Document(page_content='Dogs are great companions, known for their loyalty and friendliness.', metadata={'type': 'dog', 'trait': 'loyalty'})],
 [Document(page_content='Cats are independent pets that often enjoy their own space.', metadata={'type': 'cat', 'trait': 'independence'})]]
async for event in retriever.astream_events("bar", version="v1"):
    print(event)
{'event': 'on_retriever_start', 'run_id': 'f96f268d-8383-4921-b175-ca583924d9ff', 'name': 'ToyRetriever', 'tags': [], 'metadata': {}, 'data': {'input': 'bar'}}
{'event': 'on_retriever_stream', 'run_id': 'f96f268d-8383-4921-b175-ca583924d9ff', 'tags': [], 'metadata': {}, 'name': 'ToyRetriever', 'data': {'chunk': []}}
{'event': 'on_retriever_end', 'name': 'ToyRetriever', 'run_id': 'f96f268d-8383-4921-b175-ca583924d9ff', 'tags': [], 'metadata': {}, 'data': {'output': []}}

贡献​

我们感谢对有趣检索器的贡献！

以下清单可帮助您确保贡献被添加到 LangChain：

文档：

  • 该检索器包含所有初始化参数的文档字符串，因为这些信息将在 API 参考 中展示。
  • 模型的类文档字符串包含指向用于检索器的任何相关 API 的链接（例如，如果检索器是从维基百科进行检索，最好链接到维基百科 API！）

测试：

  • 添加单元测试或集成测试以验证invoke和ainvoke工作。

优化项：

如果检索器正在连接外部数据源（例如 API 或文件），那么它几乎肯定会受益于原生的异步优化！

  • 提供原生的异步实现_aget_relevant_documents（由ainvoke)