WatsonxRerank

WatsonxRerank 是 IBM watsonx.ai 基礎模型的封裝器。

本筆記本展示了如何在檢索器中使用 watsonx 的 rerank 端點。 這是建立在 ContextualCompressionRetriever 中的想法之上。

概觀 (Overview)

整合細節 (Integration details)

類別 (Class)	套件 (Package)	JS 支援 (JS support)	套件下載 (Package downloads)	套件最新版 (Package latest)
WatsonxRerank	langchain-ibm	✅

設定 (Setup)

要存取 IBM watsonx.ai 模型，您需要建立 IBM watsonx.ai 帳戶、取得 API 金鑰，並安裝 langchain-ibm 整合套件。

憑證 (Credentials)

下面的儲存格定義了使用 watsonx 基礎模型推論所需的憑證。

操作： 提供 IBM Cloud 使用者 API 金鑰。 有關詳細信息，請參閱 管理使用者 API 金鑰。

import os
from getpass import getpass

watsonx_api_key = getpass()
os.environ["WATSONX_APIKEY"] = watsonx_api_key

此外，您可以將其他機密作為環境變數傳遞。

import os

os.environ["WATSONX_URL"] = "your service instance url"
os.environ["WATSONX_TOKEN"] = "your token for accessing the CPD cluster"
os.environ["WATSONX_PASSWORD"] = "your password for accessing the CPD cluster"
os.environ["WATSONX_USERNAME"] = "your username for accessing the CPD cluster"
os.environ["WATSONX_INSTANCE_ID"] = "your instance_id for accessing the CPD cluster"

安裝 (Installation)

LangChain IBM 整合位於 langchain-ibm 套件中

!pip install -qU langchain-ibm
!pip install -qU langchain-community
!pip install -qU langchain_text_splitters

為了實驗目的，請同時安裝 faiss 或 faiss-cpu 套件

!pip install --upgrade --quiet  faiss

# OR  (depending on Python version)

!pip install --upgrade --quiet  faiss-cpu

用於列印文件的輔助函數 (Helper function for printing docs)

def pretty_print_docs(docs):
    print(
        f"\n{'-' * 100}\n".join(
            [f"Document {i+1}:\n\n" + d.page_content for i, d in enumerate(docs)]
        )
    )

實例化 (Instantiation)

設定基礎向量儲存檢索器 (Set up the base vector store retriever)

讓我們從初始化一個簡單的向量儲存檢索器並儲存 2023 年國情咨文 (以區塊形式) 開始。 我们可以设置檢索器以檢索大量 (20) 文件。

初始化 WatsonxEmbeddings。 有關更多詳細信息，請參閱 WatsonxEmbeddings。

注意 (Note):

• 為了提供 API 呼叫的上下文，您必須添加 project_id 或 space_id。 有關更多資訊，請參閱文檔。
• 根據您佈建的服務實例的區域，使用 此處 描述的 URL 之一。

在本例中，我們將使用 project_id 和 Dallas URL。

您需要指定將用於嵌入的 model_id。 您可以在 文檔中找到所有可用的模型。

from langchain_ibm import WatsonxEmbeddings

wx_embeddings = WatsonxEmbeddings(
    model_id="ibm/slate-125m-english-rtrvr",
    url="https://us-south.ml.cloud.ibm.com",
    project_id="PASTE YOUR PROJECT_ID HERE",
)

API 參考：WatsonxEmbeddings

from langchain_community.document_loaders import TextLoader
from langchain_community.vectorstores import FAISS
from langchain_text_splitters import RecursiveCharacterTextSplitter

documents = TextLoader("../../how_to/state_of_the_union.txt").load()
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)
texts = text_splitter.split_documents(documents)
retriever = FAISS.from_documents(texts, wx_embeddings).as_retriever(
    search_kwargs={"k": 20}
)

query = "What did the president say about Ketanji Brown Jackson"
docs = retriever.invoke(query)
pretty_print_docs(docs[:5])  # Printing the first 5 documents

API 參考：TextLoader | FAISS | RecursiveCharacterTextSplitter

Document 1:

One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. 

And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.
----------------------------------------------------------------------------------------------------
Document 2:

I spoke with their families and told them that we are forever in debt for their sacrifice, and we will carry on their mission to restore the trust and safety every community deserves. 

I’ve worked on these issues a long time. 

I know what works: Investing in crime prevention and community police officers who’ll walk the beat, who’ll know the neighborhood, and who can restore trust and safety. 

So let’s not abandon our streets. Or choose between safety and equal justice.
----------------------------------------------------------------------------------------------------
Document 3:

He met the Ukrainian people. 

From President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world. 

Groups of citizens blocking tanks with their bodies. Everyone from students to retirees teachers turned soldiers defending their homeland. 

In this struggle as President Zelenskyy said in his speech to the European Parliament “Light will win over darkness.” The Ukrainian Ambassador to the United States is here tonight.
----------------------------------------------------------------------------------------------------
Document 4:

As I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential. 

While it often appears that we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice.
----------------------------------------------------------------------------------------------------
Document 5:

To all Americans, I will be honest with you, as I’ve always promised. A Russian dictator, invading a foreign country, has costs around the world. 

And I’m taking robust action to make sure the pain of our sanctions  is targeted at Russia’s economy. And I will use every tool at our disposal to protect American businesses and consumers. 

Tonight, I can announce that the United States has worked with 30 other countries to release 60 Million barrels of oil from reserves around the world.

用法 (Usage)

使用 WatsonxRerank 進行重新排序 (Doing reranking with WatsonxRerank)

現在讓我們用 ContextualCompressionRetriever 包裹我們的基礎檢索器。 我們將添加一個 WatsonxRerank，它使用 watsonx rerank 端點來重新排序返回的結果。 請注意，必須在 WatsonxRerank 中指定模型名稱！

from langchain_ibm import WatsonxRerank

wx_rerank = WatsonxRerank(
    model_id="ibm/slate-125m-english-rtrvr",
    url="https://us-south.ml.cloud.ibm.com",
    project_id="PASTE YOUR PROJECT_ID HERE",
)

API 參考：WatsonxRerank

from langchain.retrievers.contextual_compression import ContextualCompressionRetriever

compression_retriever = ContextualCompressionRetriever(
    base_compressor=wx_rerank, base_retriever=retriever
)

compressed_docs = compression_retriever.invoke(
    "What did the president say about Ketanji Jackson Brown"
)
pretty_print_docs(compressed_docs[:5])  # Printing the first 5 compressed documents

API 參考：ContextualCompressionRetriever

Document 1:

One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. 

And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.
----------------------------------------------------------------------------------------------------
Document 2:

As I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential. 

While it often appears that we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice.
----------------------------------------------------------------------------------------------------
Document 3:

To all Americans, I will be honest with you, as I’ve always promised. A Russian dictator, invading a foreign country, has costs around the world. 

And I’m taking robust action to make sure the pain of our sanctions  is targeted at Russia’s economy. And I will use every tool at our disposal to protect American businesses and consumers. 

Tonight, I can announce that the United States has worked with 30 other countries to release 60 Million barrels of oil from reserves around the world.
----------------------------------------------------------------------------------------------------
Document 4:

I spoke with their families and told them that we are forever in debt for their sacrifice, and we will carry on their mission to restore the trust and safety every community deserves. 

I’ve worked on these issues a long time. 

I know what works: Investing in crime prevention and community police officers who’ll walk the beat, who’ll know the neighborhood, and who can restore trust and safety. 

So let’s not abandon our streets. Or choose between safety and equal justice.
----------------------------------------------------------------------------------------------------
Document 5:

He met the Ukrainian people. 

From President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world. 

Groups of citizens blocking tanks with their bodies. Everyone from students to retirees teachers turned soldiers defending their homeland. 

In this struggle as President Zelenskyy said in his speech to the European Parliament “Light will win over darkness.” The Ukrainian Ambassador to the United States is here tonight.

在鏈中使用

您當然可以在 QA 流程中使用這個檢索器

初始化 ChatWatsonx。 更多詳細信息請參閱ChatWatsonx。

from langchain_ibm import ChatWatsonx

wx_chat = ChatWatsonx(
    model_id="meta-llama/llama-3-1-70b-instruct",
    url="https://us-south.ml.cloud.ibm.com",
    project_id="PASTE YOUR PROJECT_ID HERE",
)

API 參考：ChatWatsonx

from langchain.chains import RetrievalQA

chain = RetrievalQA.from_chain_type(llm=wx_chat, retriever=compression_retriever)

API 參考：RetrievalQA

chain.invoke(query)

{'query': 'What did the president say about Ketanji Brown Jackson',
 'result': 'The President said that he had nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to serve on the United States Supreme Court, and described her as "one of our nation\'s top legal minds" who will continue Justice Breyer\'s legacy of excellence.'}

API 參考

有關所有 WatsonxRerank 功能和配置的詳細文檔，請前往API 參考。

相關內容

• 檢索器概念指南
• 檢索器操作指南