Voyage AI 集成

from langchain_voyageai import VoyageAIEmbeddings

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

documents = [
    "缓存嵌入向量可以实现嵌入向量的存储或临时缓存，从而无需每次都重新计算它们。",
    "LLMChain 是一个组合了基本 LLM 功能的链。它由一个 PromptTemplate 和一个语言模型（LLM 或聊天模型）组成。它使用提供的输入键值（以及可用的记忆键值）格式化提示模板，将格式化后的字符串传递给 LLM 并返回 LLM 输出。",
    "Runnable 代表一个通用的工作单元，可以被调用、批处理、流式处理和/或转换。",
]

documents_embds = embeddings.embed_documents(documents)

documents_embds[0][:5]

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

query = "What's an LLMChain?"

query_embd = embeddings.embed_query(query)

query_embd[:5]

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

from langchain_community.retrievers import KNNRetriever

retriever = KNNRetriever.from_texts(documents, embeddings)

# 检索最相关的文档
result = retriever.invoke(query)
top1_retrieved_doc = result[0].page_content  # 返回检索到的第一条结果

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.