>GreenNode 是一家全球 AI 解决方案提供商，也是 **NVIDIA 首选合作伙伴**，提供从基础设施到应用的完整 AI 能力，服务于美国、中东和北非以及亚太地区的企业。运营在 **世界级基础设施** （LEED 金级、TIA‑942、Uptime Tier III），GreenNode 为企业、初创公司和研究人员提供全面的 AI 服务套件

本指南提供入门指南，帮助您开始使用 GreenNodeEmbeddings。它使您能够通过生成高质量的文本向量表示，使用各种内置连接器或您自己的自定义数据源执行语义文档搜索。

概述

集成详情

设置

要访问 GreenNode 嵌入模型，您需要创建一个 GreenNode 账户，获取 API 密钥，并安装 langchain-greennode 集成包。

凭证

GreenNode 需要 API 密钥进行身份验证，可以通过以下方式提供： api_key 初始化时的参数或设置为环境变量 GREENNODE_API_KEY。您可以通过在以下网站注册账户来获取 API 密钥 GreenNode Serverless AI.

if not os.getenv("GREENNODE_API_KEY"):
    os.environ["GREENNODE_API_KEY"] = getpass.getpass("Enter your GreenNode API key: ")

如果您想获取模型调用的自动追踪，还可以设置您的 LangSmith API 密钥，取消下面的注释：

os.environ["LANGSMITH_TRACING"] = "true"
os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")

安装

LangChain GreenNode 集成位于 langchain-greennode package:

pip install -qU langchain-greennode

实例化

可以 GreenNodeEmbeddings 类可以使用可选参数进行实例化，包括 API 密钥和模型名称：

from langchain_greennode import GreenNodeEmbeddings

# Initialize the embeddings model
embeddings = GreenNodeEmbeddings(
    # api_key="YOUR_API_KEY",  # You can pass the API key directly
    model="BAAI/bge-m3"  # The default embedding model
)

索引和检索

嵌入模型在检索增强生成 (RAG) 工作流程中发挥关键作用，能够实现内容的索引和高效检索。 下面，了解如何使用 embeddings 对象进行数据索引和检索。在本例中，我们将对 InMemoryVectorStore.

# Create a vector store with a sample text
from langchain_core.vectorstores import InMemoryVectorStore

text = "LangChain is the framework for building context-aware reasoning applications"

vectorstore = InMemoryVectorStore.from_texts(
    [text],
    embedding=embeddings,
)

# Use the vectorstore as a retriever
retriever = vectorstore.as_retriever()

# Retrieve the most similar text
retrieved_documents = retriever.invoke("What is LangChain?")

# show the retrieved document's content
retrieved_documents[0].page_content

'LangChain is the framework for building context-aware reasoning applications'

直接使用

该 GreenNodeEmbeddings 类可以独立使用，无需向量存储即可生成文本嵌入。这对于相似度评分、聚类或自定义处理管道等任务非常有用。

嵌入单个文本

您可以使用 embed_query:

single_vector = embeddings.embed_query(text)
print(str(single_vector)[:100])  # Show the first 100 characters of the vector

[-0.01104736328125, -0.0281982421875, 0.0035858154296875, -0.0311279296875, -0.0106201171875, -0.039

嵌入多个文本

您可以使用 embed_documents:

text2 = (
    "LangGraph is a library for building stateful, multi-actor applications with LLMs"
)
two_vectors = embeddings.embed_documents([text, text2])
for vector in two_vectors:
    print(str(vector)[:100])  # Show the first 100 characters of the vector

[-0.01104736328125, -0.0281982421875, 0.0035858154296875, -0.0311279296875, -0.0106201171875, -0.039
[-0.07177734375, -0.00017452239990234375, -0.002044677734375, -0.0299072265625, -0.0184326171875, -0

异步支持

GreenNodeEmbeddings 支持异步操作：

async def generate_embeddings_async():
    # Embed a single query
    query_result = await embeddings.aembed_query("What is the capital of France?")
    print(f"Async query embedding dimension: {len(query_result)}")

    # Embed multiple documents
    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: 1024
Async document embeddings count: 3

文档相似度示例

from scipy.spatial.distance import cosine

# Create some documents
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",
]

# Embed the documents
embeddings_list = embeddings.embed_documents(documents)


# Function to calculate similarity
def calculate_similarity(embedding1, embedding2):
    return 1 - cosine(embedding1, embedding2)


# Print similarity matrix
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', '0.6005', '0.3542', '0.5788']
Document 2: ['0.6005', '1.0000', '0.4154', '0.6170']
Document 3: ['0.3542', '0.4154', '1.0000', '0.3528']
Document 4: ['0.5788', '0.6170', '0.3528', '1.0000']

API 参考

有关 GreenNode Serverless AI API 的更多详细信息，请访问 GreenNode Serverless AI 文档.