Skip to main content
Open In ColabOpen on GitHub

RAGatouille

RAGatouille 使使用 ColBERT 变得极其简单！ColBERT 是一个快速且准确的检索模型，能够在数十毫秒内对大型文本集合进行基于 BERT 的可扩展搜索。

请参阅 ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction 论文。

我们可以通过多种方式使用 RAGatouille。

设置​

集成位于 ragatouille 包中。

pip install -U ragatouille
from ragatouille import RAGPretrainedModel

RAG = RAGPretrainedModel.from_pretrained("colbert-ir/colbertv2.0")
[Jan 10, 10:53:28] Loading segmented_maxsim_cpp extension (set COLBERT_LOAD_TORCH_EXTENSION_VERBOSE=True for more info)...
``````output
/Users/harrisonchase/.pyenv/versions/3.10.1/envs/langchain/lib/python3.10/site-packages/torch/cuda/amp/grad_scaler.py:125: UserWarning: torch.cuda.amp.GradScaler is enabled, but CUDA is not available.  Disabling.
  warnings.warn(

检索器​

我们可以使用 RAGatouille 作为检索器。有关此内容的更多信息，请参阅 RAGatouille 检索器

文档压缩器​

我们也可以直接将 RAGatouille 用作重排器。这将允许我们使用 ColBERT 来重排任何通用检索器的检索结果。这样做的好处是我们可以将其应用于任何现有的索引之上，而无需创建新的索引。我们可以通过 LangChain 中的 文档压缩器 抽象来实现这一点。

设置 Vanilla Retriever​

首先，我们设置一个 vanilla retriever 作为示例。

import requests
from langchain_community.vectorstores import FAISS
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter


def get_wikipedia_page(title: str):
    """
    Retrieve the full text content of a Wikipedia page.

    :param title: str - Title of the Wikipedia page.
    :return: str - Full text content of the page as raw string.
    """
    # Wikipedia API endpoint
    URL = "https://en.wikipedia.org/w/api.php"

    # Parameters for the API request
    params = {
        "action": "query",
        "format": "json",
        "titles": title,
        "prop": "extracts",
        "explaintext": True,
    }

    # Custom User-Agent header to comply with Wikipedia's best practices
    headers = {"User-Agent": "RAGatouille_tutorial/0.0.1 (ben@clavie.eu)"}

    response = requests.get(URL, params=params, headers=headers)
    data = response.json()

    # Extracting page content
    page = next(iter(data["query"]["pages"].values()))
    return page["extract"] if "extract" in page else None


text = get_wikipedia_page("Hayao_Miyazaki")
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
texts = text_splitter.create_documents([text])
retriever = FAISS.from_documents(texts, OpenAIEmbeddings()).as_retriever(
    search_kwargs={"k": 10}
)
docs = retriever.invoke("What animation studio did Miyazaki found")
docs[0]
Document(page_content='collaborative projects. In April 1984, Miyazaki opened his own office in Suginami Ward, naming it Nibariki.')

我们可以看到，结果与所提出的问题关系不大

将 ColBERT 用作重排模型​

from langchain.retrievers import ContextualCompressionRetriever

compression_retriever = ContextualCompressionRetriever(
    base_compressor=RAG.as_langchain_document_compressor(), base_retriever=retriever
)

compressed_docs = compression_retriever.invoke(
    "What animation studio did Miyazaki found"
)
/Users/harrisonchase/.pyenv/versions/3.10.1/envs/langchain/lib/python3.10/site-packages/torch/amp/autocast_mode.py:250: UserWarning: User provided device_type of 'cuda', but CUDA is not available. Disabling
  warnings.warn(
compressed_docs[0]
Document(page_content='In June 1985, Miyazaki, Takahata, Tokuma and Suzuki founded the animation production company Studio Ghibli, with funding from Tokuma Shoten. Studio Ghibli\'s first film, Laputa: Castle in the Sky (1986), employed the same production crew of Nausicaä. Miyazaki\'s designs for the film\'s setting were inspired by Greek architecture and "European urbanistic templates". Some of the architecture in the film was also inspired by a Welsh mining town; Miyazaki witnessed the mining strike upon his first', metadata={'relevance_score': 26.5194149017334})

这个答案相关性更强！