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_nebius import NebiusEmbeddings

# 初始化嵌入模型
embeddings = NebiusEmbeddings(
    # api_key="YOUR_API_KEY",  # 您可以直接传递 API 密钥
    model="Qwen/Qwen3-Embedding-8B"  # 默认嵌入模型
)

from langchain_community.vectorstores import FAISS
from langchain_core.documents import Document

# 准备文档
docs = [
    Document(
        page_content="Machine learning algorithms build mathematical models based on sample data"
    ),
    Document(page_content="Deep learning uses neural networks with many layers"),
    Document(page_content="Climate change is a major global environmental challenge"),
    Document(
        page_content="Neural networks are inspired by the human brain's structure"
    ),
]

# 创建向量存储
vector_store = FAISS.from_documents(docs, embeddings)

# 执行相似性搜索
query = "How does the brain influence AI?"
results = vector_store.similarity_search(query, k=2)

print("Search results for query:", query)
for i, doc in enumerate(results):
    print(f"Result {i + 1}: {doc.page_content}")

Search results for query: How does the brain influence AI?
Result 1: Neural networks are inspired by the human brain's structure
Result 2: Deep learning uses neural networks with many layers

from langchain_core.vectorstores import InMemoryVectorStore

# 创建示例文本
text = "LangChain is a framework for developing applications powered by language models"

# 创建向量存储
vectorstore = InMemoryVectorStore.from_texts(
    [text],
    embedding=embeddings,
)

# 用作检索器
retriever = vectorstore.as_retriever()

# 检索相似文档
docs = retriever.invoke("What is LangChain?")
print(f"Retrieved document: {docs[0].page_content}")

Retrieved document: LangChain is a framework for developing applications powered by language models

query = "What is machine learning?"
query_embedding = embeddings.embed_query(query)

# 检查嵌入维度
print(f"Embedding dimension: {len(query_embedding)}")
print(f"First few values: {query_embedding[:5]}")

Embedding dimension: 4096
First few values: [0.007419586181640625, 0.002246856689453125, 0.00193023681640625, -0.0066070556640625, -0.0179901123046875]

documents = [
    "Machine learning is a branch of artificial intelligence",
    "Deep learning is a subfield of machine learning",
    "Natural language processing deals with interactions between computers and human language",
]

document_embeddings = embeddings.embed_documents(documents)

# 检查结果
print(f"Number of document embeddings: {len(document_embeddings)}")
print(f"Each embedding has {len(document_embeddings[0])} dimensions")

Number of document embeddings: 3
Each embedding has 4096 dimensions

import asyncio


async def generate_embeddings_async():
    # 嵌入单个查询
    query_result = await embeddings.aembed_query("What is the capital of France?")
    print(f"Async query embedding dimension: {len(query_result)}")

    # 嵌入多个文档
    docs = [
        "Paris is the capital of France",
        "Berlin is the capital of Germany",
        "Rome is the capital of Italy",
    ]
    docs_result = await embeddings.aembed_documents(docs)
    print(f"Async document embeddings count: {len(docs_result)}")


await generate_embeddings_async()

Async query embedding dimension: 4096
Async document embeddings count: 3

import numpy as np
from scipy.spatial.distance import cosine

# 创建一些文档
documents = [
    "Machine learning algorithms build mathematical models based on sample data",
    "Deep learning uses neural networks with many layers",
    "Climate change is a major global environmental challenge",
    "Neural networks are inspired by the human brain's structure",
]

# 嵌入文档
embeddings_list = embeddings.embed_documents(documents)


# 计算相似性的函数
def calculate_similarity(embedding1, embedding2):
    return 1 - cosine(embedding1, embedding2)


# 打印相似性矩阵
print("Document Similarity Matrix:")
for i, emb_i in enumerate(embeddings_list):
    similarities = []
    for j, emb_j in enumerate(embeddings_list):
        similarity = calculate_similarity(emb_i, emb_j)
        similarities.append(f"{similarity:.4f}")
    print(f"Document {i + 1}: {similarities}")

Document Similarity Matrix:
Document 1: ['1.0000', '0.8282', '0.5811', '0.7985']
Document 2: ['0.8282', '1.0000', '0.5897', '0.8315']
Document 3: ['0.5811', '0.5897', '1.0000', '0.5918']
Document 4: ['0.7985', '0.8315', '0.5918', '1.0000']