
pipeline 中的最常见位置	1. 在 RAG 管道中的 `PromptBuilder` 之前 2. 语义搜索管道中的最后一个组件 3. 在提取式 QA 管道中的 `ExtractiveReader` 之前
必需的初始化变量	"document_store": WeaviateDocumentStore 的一个实例
强制运行变量	“query”: 一个字符串
输出变量	"documents": 文档列表（与查询匹配）
API 参考	Weaviate
GitHub 链接	https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/weaviate

概述

WeaviateBM25Retriever 是一个基于关键字的 Retriever，用于从 WeaviateDocumentStore 中检索与查询匹配的文档。它基于 BM25 算法计算文档与查询之间的相似度，该算法通过计算两个字符串之间的加权词重叠来确定相似度。
两个字符串。

由于WeaviateBM25Retriever 基于词语重叠来匹配字符串，因此它常用于查找人名、产品名、ID 或明确定义的错误消息的精确匹配。BM25 算法非常轻量且简单。在处理域外数据时，很难用更复杂的基于嵌入的方法来超越它。

如果您希望查询和文档之间进行语义匹配，请使用 WeaviateEmbeddingRetriever，它使用嵌入模型创建的向量来检索相关信息。

参数

除了query，WeaviateBM25Retriever 接受其他可选参数，包括top_k（要检索的文档的最大数量）和filters（用于缩小搜索范围）。

用法

安装

要开始使用 Haystack 的 Weaviate，请使用以下命令安装该包：

pip install weaviate-haystack

单独使用

此 Retriever 需要一个 WeaviateDocumentStore 实例和已索引的文档才能运行。WeaviateDocumentStore 并已索引的文档才能运行。

from haystack_integrations.document_stores.weaviate.document_store import WeaviateDocumentStore
from haystack_integrations.components.retrievers.weaviate import WeaviateBM25Retriever

document_store = WeaviateDocumentStore(url="https://:8080")

retriever = WeaviateBM25Retriever(document_store=document_store)

retriever.run(query="How to make a pizza", top_k=3)

在 Pipeline 中

from haystack_integrations.document_stores.weaviate.document_store import (
    WeaviateDocumentStore,
)
from haystack_integrations.components.retrievers.weaviate import (
    WeaviateBM25Retriever,
)

from haystack import Document
from haystack import Pipeline
from haystack.components.builders.answer_builder import AnswerBuilder
from haystack.components.builders.prompt_builder import PromptBuilder
from haystack.components.generators import OpenAIGenerator
from haystack.document_stores.types import DuplicatePolicy

# Create a RAG query pipeline
prompt_template = """
    Given these documents, answer the question.\nDocuments:
    {% for doc in documents %}
        {{ doc.content }}
    {% endfor %}

    \nQuestion: {{question}}
    \nAnswer:
    """

document_store = WeaviateDocumentStore(url="https://:8080")

# Add Documents
documents = [
    Document(content="There are over 7,000 languages spoken around the world today."),
    Document(
        content="Elephants have been observed to behave in a way that indicates a high level of self-awareness, such as recognizing themselves in mirrors."
    ),
    Document(
        content="In certain parts of the world, like the Maldives, Puerto Rico, and San Diego, you can witness the phenomenon of bioluminescent waves."
    ),
]

# DuplicatePolicy.SKIP param is optional, but useful to run the script multiple times without throwing errors
document_store.write_documents(documents=documents, policy=DuplicatePolicy.SKIP)

rag_pipeline = Pipeline()
rag_pipeline.add_component(
    name="retriever", instance=WeaviateBM25Retriever(document_store=document_store)
)
rag_pipeline.add_component(
    instance=PromptBuilder(template=prompt_template), name="prompt_builder"
)
rag_pipeline.add_component(instance=OpenAIGenerator(), name="llm")
rag_pipeline.add_component(instance=AnswerBuilder(), name="answer_builder")
rag_pipeline.connect("retriever", "prompt_builder.documents")
rag_pipeline.connect("prompt_builder", "llm")
rag_pipeline.connect("llm.replies", "answer_builder.replies")
rag_pipeline.connect("llm.metadata", "answer_builder.metadata")
rag_pipeline.connect("retriever", "answer_builder.documents")

question = "How many languages are spoken around the world today?"
result = rag_pipeline.run(
    {
        "retriever": {"query": question},
        "prompt_builder": {"question": question},
        "answer_builder": {"query": question},
    }
)
print(result["answer_builder"]["answers"][0])