RAGatouille

RAGatouille makes it as simple as can be to use ColBERT! ColBERT is a fast and accurate retrieval model, enabling scalable BERT-based search over large text collections in tens of milliseconds.

See the ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction paper.

我们可以用多种方式使用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

我们还可以将RAGatouille开箱即用作重排序器。这将允许我们使用ColBERT对来自任何通用检索器的检索结果进行重新排序。这样做的好处是，我们可以在任何现有索引的基础上进行操作，而无需创建新的索引。我们可以通过使用LangChain中的文档压缩器抽象来实现这一点。

设置普通检索器

首先，让我们设置一个普通的检索器作为示例。

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])

API 参考：FAISS | OpenAIEmbeddings | RecursiveCharacterTextSplitter

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并不是非常相关。

使用ColBERT作为重排序器

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"
)

API 参考：ContextualCompressionRetriever

/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})

这个答案相关性更高！