Nebius 集成

pip install -U langchain-nebius

import getpass
import os

# 确保您已将 API 密钥设置为环境变量
if "NEBIUS_API_KEY" not in os.environ:
    os.environ["NEBIUS_API_KEY"] = getpass.getpass("Enter your Nebius API key: ")

from langchain_core.documents import Document
from langchain_nebius import NebiusEmbeddings, NebiusRetriever

# 创建示例文档
docs = [
    Document(
        page_content="Paris is the capital of France", metadata={"country": "France"}
    ),
    Document(
        page_content="Berlin is the capital of Germany", metadata={"country": "Germany"}
    ),
    Document(
        page_content="Rome is the capital of Italy", metadata={"country": "Italy"}
    ),
    Document(
        page_content="Madrid is the capital of Spain", metadata={"country": "Spain"}
    ),
    Document(
        page_content="London is the capital of the United Kingdom",
        metadata={"country": "UK"},
    ),
    Document(
        page_content="Moscow is the capital of Russia", metadata={"country": "Russia"}
    ),
    Document(
        page_content="Washington DC is the capital of the United States",
        metadata={"country": "USA"},
    ),
    Document(
        page_content="Tokyo is the capital of Japan", metadata={"country": "Japan"}
    ),
    Document(
        page_content="Beijing is the capital of China", metadata={"country": "China"}
    ),
    Document(
        page_content="Canberra is the capital of Australia",
        metadata={"country": "Australia"},
    ),
]

# 初始化嵌入模型
embeddings = NebiusEmbeddings()

# 创建检索器
retriever = NebiusRetriever(
    embeddings=embeddings,
    docs=docs,
    k=3,  # 返回的文档数量
)

# 查询欧洲首都
query = "What are some capitals in Europe?"
results = retriever.invoke(query)

print(f"Query: {query}")
print(f"Top {len(results)} results:")
for i, doc in enumerate(results):
    print(f"{i + 1}. {doc.page_content} (Country: {doc.metadata['country']})")

Query: What are some capitals in Europe?
Top 3 results:
1. Paris is the capital of France (Country: France)
2. Berlin is the capital of Germany (Country: Germany)
3. Rome is the capital of Italy (Country: Italy)

# 查询亚洲国家
query = "What are the capitals in Asia?"
results = retriever.get_relevant_documents(query)

print(f"Query: {query}")
print(f"Top {len(results)} results:")
for i, doc in enumerate(results):
    print(f"{i + 1}. {doc.page_content} (Country: {doc.metadata['country']})")

Query: What are the capitals in Asia?
Top 3 results:
1. Beijing is the capital of China (Country: China)
2. Tokyo is the capital of Japan (Country: Japan)
3. Canberra is the capital of Australia (Country: Australia)

# 查询特定国家，自定义 k 值
query = "Where is France?"
results = retriever.invoke(query, k=1)  # 覆盖默认的 k 值

print(f"Query: {query}")
print(f"Top {len(results)} result:")
for i, doc in enumerate(results):
    print(f"{i + 1}. {doc.page_content} (Country: {doc.metadata['country']})")

Query: Where is France?
Top 1 result:
1. Paris is the capital of France (Country: France)

import asyncio


async def retrieve_async():
    query = "What are some capital cities?"
    results = await retriever.ainvoke(query)

    print(f"Async query: {query}")
    print(f"Top {len(results)} results:")
    for i, doc in enumerate(results):
        print(f"{i + 1}. {doc.page_content} (Country: {doc.metadata['country']})")


await retrieve_async()

Async query: What are some capital cities?
Top 3 results:
1. Washington DC is the capital of the United States (Country: USA)
2. Canberra is the capital of Australia (Country: Australia)
3. Paris is the capital of France (Country: France)

# 创建一个包含空文档的检索器
empty_retriever = NebiusRetriever(
    embeddings=embeddings,
    docs=[],
    k=2,  # 空文档列表
)

# 使用空文档测试检索器
results = empty_retriever.invoke("What are the capitals of European countries?")
print(f"Number of results: {len(results)}")

Number of results: 0

from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_nebius import ChatNebius

# 初始化 LLM
llm = ChatNebius(model="meta-llama/Llama-3.3-70B-Instruct-fast")

# 创建提示模板
prompt = ChatPromptTemplate.from_template(
    """
Answer the question based only on the following context:

Context:
{context}

Question: {question}
"""
)


# 格式化文档函数
def format_docs(docs):
    return "\n\n".join(doc.page_content for doc in docs)


# 创建 RAG 链
rag_chain = (
    {"context": retriever | format_docs, "question": RunnablePassthrough()}
    | prompt
    | llm
    | StrOutputParser()
)

# 运行链
answer = rag_chain.invoke("What are three European capitals?")
print(answer)

Based on the context provided, three European capitals are:

1. Paris
2. Berlin
3. Rome

from langchain_nebius import NebiusRetrievalTool

# 创建检索工具
tool = NebiusRetrievalTool(
    retriever=retriever,
    name="capital_search",
    description="Search for information about capital cities around the world",
)

# 使用工具
result = tool.invoke({"query": "capitals in Europe", "k": 3})
print("Tool results:")
print(result)

Tool results:
Document 1:
Paris is the capital of France

Document 2:
Berlin is the capital of Germany

Document 3:
Rome is the capital of Italy