PerplexityEmbeddings 集成

import getpass
import os

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

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

pip install -qU langchain-perplexity

from langchain_perplexity import PerplexityEmbeddings

embeddings = PerplexityEmbeddings(
    model="pplx-embed-v1-4b",
    # api_key="...",       # 如果您希望显式传递密钥
    # request_timeout=60,
    # max_retries=6,
)

# 使用示例文本创建向量存储
from langchain_core.vectorstores import InMemoryVectorStore

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

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

# 将向量存储用作检索器
retriever = vectorstore.as_retriever()

# 检索最相似的文本
retrieved_documents = retriever.invoke("What is LangChain?")

# 显示检索到的文档内容
retrieved_documents[0].page_content

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

single_vector = embeddings.embed_query(text)
print(str(single_vector)[:100])  # 显示向量的前100个字符

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])  # 显示向量的前100个字符

single_vector = await embeddings.aembed_query(text)
two_vectors = await embeddings.aembed_documents([text, text2])