Voyage AI
Voyage AI 提供前沿的嵌入/向量化模型。
让我们加载Voyage AI嵌入类。（使用pip install langchain-voyageai安装LangChain合作伙伴包）
from langchain_voyageai import VoyageAIEmbeddings
API Reference: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：(来源):
voyage-3voyage-3-litevoyage-large-2voyage-code-2voyage-2voyage-law-2voyage-large-2-instructvoyage-finance-2voyage-multilingual-2
embeddings = VoyageAIEmbeddings(
voyage_api_key="[ Your Voyage API key ]", model="voyage-law-2"
)
准备文档并使用embed_documents获取它们的嵌入。
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]
同样地，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]
一个极简的检索系统
嵌入的主要特征是，两个嵌入之间的余弦相似度捕捉了相应原始段落的语义相关性。这使我们能够使用嵌入进行语义检索/搜索。
我们可以根据余弦相似度在文档嵌入中找到几个最接近的嵌入，并使用LangChain中的KNNRetriever类检索相应的文档。
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)
API Reference:KNNRetriever
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.