PerplexityEmbeddings 集成

使用 LangChain Python 集成 Perplexity’s 向量嵌入模型 。

本指南将帮助您开始使用 Perplexity 向量嵌入模型 using LangChain. For detailed documentation on PerplexityEmbeddings 功能和配置选项的详细文档，请参阅 API reference.

概述

集成详情

类	包	本地	Py support	包 downloads	包 latest
PerplexityEmbeddings	langchain-perplexity	❌	✅

设置

要访问 Perplexity embedding 模型，您需要创建一个 Perplexity 账户，获取 API 密钥，并安装 langchain-perplexity 集成包。

凭证

前往 https://www.perplexity.ai/account/api/keys 注册 the Perplexity API 并生成 API 密钥。 完成后，设置 PPLX_API_KEY (or PERPLEXITY_API_KEY) 环境变量：

import getpass
import os

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

要启用模型调用的自动追踪，请设置您的 LangSmith API key:

os.environ["LANGSMITH_TRACING"] = "true"
os.environ["LANGSMITH_API_KEY"] = getpass.getpass("请输入您的 LangSmith API 密钥: ")

安装

LangChain 的 Perplexity 集成位于 langchain-perplexity 包中：

pip install -qU langchain-perplexity

实例化

Now we can instantiate our embedding model object and generate embeddings:

from langchain_perplexity import PerplexityEmbeddings

embeddings = PerplexityEmbeddings(
    model="pplx-embed-v1-4b",
    # api_key="...",       # if you prefer to pass the key explicitly
    # request_timeout=60,
    # max_retries=6,
)

Available models include pplx-embed-v1-4b (default) and pplx-embed-v1-0.6b. 请参阅 Perplexity Embeddings API reference for the current list and dimensions.

索引与检索

向量嵌入模型常用于检索增强生成 (RAG) 流程中, 既用于索引数据，也用于后续检索数据。 更详细的说明请参阅我们的 RAG tutorials.

下面展示如何使用 embeddings 对象来索引和检索数据。 在此示例中，我们将在 InMemoryVectorStore.

# 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,
)

# 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

Under the hood, the vectorstore and retriever implementations are calling embeddings.embed_documents(...) and embeddings.embed_query(...) to create embeddings for the text(s) used in from_texts and retrieval invoke operations, respectively.

You can directly call these methods to get embeddings for your own use cases.

Embed single texts

You can embed single texts or documents with embed_query:

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

Embed multiple texts

You can embed multiple texts with 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

Async usage

PerplexityEmbeddings also exposes async methods:

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

Perplexity returns base64-encoded signed int8 embeddings. PerplexityEmbeddings decodes these into list[float] values in the range [-128, 127]. The magnitude is preserved from the API’s quantized output; cosine similarity is unaffected by the lack of unit-length normalization.

---

API 参考

For detailed documentation on PerplexityEmbeddings 功能和配置选项的详细文档，请参阅 API reference and the Perplexity Embeddings API documentation.

---

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

Edit this page on GitHub or file an issue.