>Voyage AI provides cutting-edge embedding/vectorizations models.

让我们加载 Voyage AI Embedding 类。(安装 LangChain 合作伙伴包，使用 pip install langchain-voyageai)

from langchain_voyageai import VoyageAIEmbeddings

Voyage AI 使用 API 密钥来监控使用情况和管理权限。要获取您的密钥，请在我们的 主页上创建一个账户。然后，使用您的 API 密钥创建一个 VoyageEmbeddings 模型。您可以使用以下任何模型：(source):

• - voyage-4-large
• - voyage-4
• - voyage-4-lite
• - voyage-context-3
• - voyage-3.5
• - voyage-3.5-lite
• - voyage-3-large
• - voyage-3
• - voyage-3-lite
• - voyage-large-2
• - voyage-code-2
• - voyage-2
• - voyage-law-2
• - voyage-large-2-instruct
• - voyage-finance-2
• - voyage-multilingual-2

embeddings = VoyageAIEmbeddings(
    voyage_api_key="[ Your Voyage API key ]", model="voyage-law-2"
)

准备文档并使用 embed_documents 来获取它们的嵌入向量。

documents = [
    "Caching embeddings enables the storage or temporary caching of embeddings, eliminating the necessity to recompute them each time.",
    "An LLMChain is a chain that composes basic LLM functionality. It consists of a PromptTemplate and a language model (either an LLM or chat model). It formats the prompt template using the input key values provided (and also memory key values, if available), passes the formatted string to LLM and returns the LLM output.",
    "A Runnable represents a generic unit of work that can be invoked, batched, streamed, and/or transformed.",
]

documents_embds = embeddings.embed_documents(documents)

documents_embds[0][:5]

[0.0562174916267395,
 0.018221192061901093,
 0.0025736060924828053,
 -0.009720131754875183,
 0.04108370840549469]

类似地，使用 embed_query 来嵌入查询。

query = "What's an LLMChain?"

query_embd = embeddings.embed_query(query)

query_embd[:5]

[-0.0052348352037370205,
 -0.040072452276945114,
 0.0033957737032324076,
 0.01763271726667881,
 -0.019235141575336456]

一个简约的检索系统

The main feature of the embeddings is that the cosine similarity between two embeddings captures the semantic relatedness of the corresponding original passages. This allows us to use the embeddings to do semantic retrieval / search.

我们可以根据余弦相似度在文档嵌入向量中找到几个最接近的嵌入向量，并使用 KNNRetriever LangChain 中的类来检索相应的文档。

from langchain_community.retrievers import KNNRetriever

retriever = KNNRetriever.from_texts(documents, embeddings)

# retrieve the most relevant documents
result = retriever.invoke(query)
top1_retrieved_doc = result[0].page_content  # return the top1 retrieved result

print(top1_retrieved_doc)

An LLMChain is a chain that composes basic LLM functionality. It consists of a PromptTemplate and a language model (either an LLM or chat model). It formats the prompt template using the input key values provided (and also memory key values, if available), passes the formatted string to LLM and returns the LLM output.