困惑度¶

Perplexity的Sonar API提供了一种解决方案，将实时、基于网络的搜索与高级推理和深度研究能力相结合。

何时使用：

当您的应用需要直接从网络获取及时、相关的数据时，例如动态内容更新或当前事件追踪。
适用于需要支持复杂用户查询并集成推理和深度研究的产品，例如数字助手或高级搜索引擎。

在开始之前，请确保已安装 llama_index

In [ ]:

Copied!

%pip install llama-index-llms-perplexity
%pip install llama-index-llms-perplexity

In [ ]:

Copied!

!pip install llama-index
!pip install llama-index

初始设置¶

截至2025年4月12日，LLaMa Index中的Perplexity LLM类支持以下模型：

模型	上下文长度	模型类型
`sonar-deep-research`	128k	Chat Completion
`sonar-reasoning-pro`	128k	Chat Completion
`sonar-reasoning`	128k	Chat Completion
`sonar-pro`	200k	Chat Completion
`sonar`	128k	Chat Completion
`r1-1776`	128k	Chat Completion

sonar-pro 的最大输出令牌限制为8k。
推理模型输出思维链式响应。
r1-1776 是一个离线聊天模型，不使用 Perplexity 搜索子系统。

您可以在此处找到最新支持的模型 here
速率限制信息请查看 here
价格详情请参阅 here。

In [ ]:

Copied!





import getpass
import os

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

if "PPLX_API_KEY" not in os.environ:
    os.environ["PPLX_API_KEY"] = getpass.getpass(
        "输入您的Perplexity API密钥: "
    )

In [ ]:

Copied!

from llama_index.llms.perplexity import Perplexity

PPLX_API_KEY = __import__("os").environ.get("PPLX_API_KEY")

llm = Perplexity(api_key=PPLX_API_KEY, model="sonar-pro", temperature=0.2)
from llama_index.llms.perplexity import Perplexity

PPLX_API_KEY = __import__("os").environ.get("PPLX_API_KEY")

llm = Perplexity(api_key=PPLX_API_KEY, model="sonar-pro", temperature=0.2)

In [ ]:

Copied!





# Import the ChatMessage class from the llama_index library.
from llama_index.core.llms import ChatMessage

# Create a list of dictionaries where each dictionary represents a chat message.
# Each dictionary contains a 'role' key (e.g., system or user) and a 'content' key with the corresponding message.
messages_dict = [
    {"role": "system", "content": "Be precise and concise."},
    {
        "role": "user",
        "content": "Tell me the latest news about the US Stock Market.",
    },
]

# Convert each dictionary in the list to a ChatMessage object using unpacking (**msg) in a list comprehension.
messages = [ChatMessage(**msg) for msg in messages_dict]

# Print the list of ChatMessage objects to verify the conversion.
print(messages)
# 从llama_index库中导入ChatMessage类。
from llama_index.core.llms import ChatMessage

# 创建一个字典列表，每个字典代表一条聊天消息。
# 每个字典包含'role'键（例如system或user）和对应的'content'键消息内容。
messages_dict = [
    {"role": "system", "content": "保持精确简洁。"},
    {
        "role": "user",
        "content": "告诉我关于美国股市的最新消息。",
    },
]

# 使用列表推导式和字典解包(**msg)将列表中的每个字典转换为ChatMessage对象。
messages = [ChatMessage(**msg) for msg in messages_dict]

# 打印ChatMessage对象列表以验证转换结果。
print(messages)

[ChatMessage(role=<MessageRole.SYSTEM: 'system'>, additional_kwargs={}, blocks=[TextBlock(block_type='text', text='Be precise and concise.')]), ChatMessage(role=<MessageRole.USER: 'user'>, additional_kwargs={}, blocks=[TextBlock(block_type='text', text='Tell me the latest news about the US Stock Market.')])]

聊天¶

In [ ]:

Copied!

response = llm.chat(messages)
print(response)
response = llm.chat(messages)
print(response)

assistant: The latest update on the U.S. stock market indicates a strong performance recently. A significant 10% rally occurred on Wednesday, which contributed substantially to market gains. Additionally, the market closed strongly on Friday, with a 2% increase, ending near the intraday high. This reflects robust momentum, particularly in mega and large-cap growth stocks[1].

异步聊天¶

对于异步对话处理，使用achat方法发送消息并等待响应：

In [ ]:

Copied!

# Asynchronously send the list of chat messages to the LLM using the 'achat' method.
# This method returns a ChatResponse object containing the model's answer.
response = await llm.achat(messages)

print(response)
# 使用'achat'方法异步发送聊天消息列表给LLM。
# 该方法返回一个包含模型回答的ChatResponse对象。
response = await llm.achat(messages)

print(response)

assistant: The U.S. stock market has recently experienced significant gains. A major rally on Wednesday resulted in a 10% surge, contributing substantially to the market's overall upside. Additionally, the market closed strongly on Friday, with a 2% increase, ending near the intraday high. This performance highlights robust momentum, particularly in mega-cap and large-cap growth stocks[1].

流式聊天¶

如果您希望实时逐令牌接收响应，请使用stream_chat方法：

In [ ]:

Copied!





# Call the stream_chat method on the LLM instance, which returns a generator or iterable
# for streaming the chat response one delta (token or chunk) at a time.
response = llm.stream_chat(messages)

# Iterate over each streaming response chunk.
for r in response:
    # Print the delta (the new chunk of generated text) without adding a newline.
    print(r.delta, end="")
# 在LLM实例上调用stream_chat方法，该方法返回一个生成器或可迭代对象
# 用于逐个delta(令牌或块)流式传输聊天响应。
response = llm.stream_chat(messages)

# 遍历每个流式响应块。
for r in response:
    # 打印delta(新生成的文本块)而不换行。
    print(r.delta, end="")

The latest news about the U.S. stock market indicates a strong performance recently. The New York Stock Exchange (NYSE) experienced a significant rally, with a 10% surge on Wednesday, followed by a 2% gain on Friday. This upward momentum brought the market near its intraday high, driven by strength in mega-cap and large-cap growth stocks[1].

异步流式聊天¶

类似地，对于异步流式处理，astream_chat方法提供了异步处理响应增量的方式：

In [ ]:

Copied!





# Asynchronously call the astream_chat method on the LLM instance,
# which returns an asynchronous generator that yields response chunks.
resp = await llm.astream_chat(messages)

# Asynchronously iterate over each response chunk from the generator.
# For each chunk (delta), print the chunk's text content.
async for delta in resp:
    print(delta.delta, end="")
# 异步调用LLM实例上的astream_chat方法，
# 该方法返回一个异步生成器，用于生成响应块。
resp = await llm.astream_chat(messages)

# 异步遍历生成器中的每个响应块。
# 对于每个块(delta)，打印该块的文本内容。
async for delta in resp:
    print(delta.delta, end="")

The latest updates on the U.S. stock market indicate significant positive momentum. The New York Stock Exchange (NYSE) experienced a strong rally, with a notable 10% surge on Wednesday. This was followed by a 2% gain on Friday, closing near the intraday high. The market's performance has been driven by mega and large-cap growth stocks, contributing to the overall upside[1].

工具调用¶

Perplexity模型可以轻松封装成llamaindex工具，以便在数据处理或对话工作流中调用。该工具利用Perplexity提供的实时生成式搜索功能，默认配置使用最新模型("sonar-pro")并启用了enable_search_classifier参数。

以下是如何定义和注册该工具的示例：

In [ ]:

Copied!





from llama_index.core.tools import FunctionTool
from llama_index.llms.perplexity import Perplexity
from llama_index.core.llms import ChatMessage


def query_perplexity(query: str) -> str:
    """
    Queries the Perplexity API via the LlamaIndex integration.

    This function instantiates a Perplexity LLM with updated default settings
    (using model "sonar-pro" and enabling search classifier so that the API can
    intelligently decide if a search is needed), wraps the query into a ChatMessage,
    and returns the generated response content.
    """
    pplx_api_key = (
        "your-perplexity-api-key"  # Replace with your actual API key
    )

    llm = Perplexity(
        api_key=pplx_api_key,
        model="sonar-pro",
        temperature=0.7,
        enable_search_classifier=True,  # This will determine if the search component is necessary in this particular context
    )

    messages = [ChatMessage(role="user", content=query)]
    response = llm.chat(messages)
    return response.message.content


# Create the tool from the query_perplexity function
query_perplexity_tool = FunctionTool.from_defaults(fn=query_perplexity)
from llama_index.core.tools import FunctionTool
from llama_index.llms.perplexity import Perplexity
from llama_index.core.llms import ChatMessage


def query_perplexity(query: str) -> str:
    """
    通过LlamaIndex集成查询Perplexity API。

    此函数使用更新后的默认设置实例化一个Perplexity LLM（使用"sonar-pro"模型并启用搜索分类器，使API能智能判断是否需要搜索），将查询包装成ChatMessage，并返回生成的响应内容。
    """
    pplx_api_key = (
        "your-perplexity-api-key"  # 替换为你的实际API密钥
    )

    llm = Perplexity(
        api_key=pplx_api_key,
        model="sonar-pro",
        temperature=0.7,
        enable_search_classifier=True,  # 这将判断在当前特定上下文中是否需要搜索组件
    )

    messages = [ChatMessage(role="user", content=query)]
    response = llm.chat(messages)
    return response.message.content


# 从query_perplexity函数创建工具
query_perplexity_tool = FunctionTool.from_defaults(fn=query_perplexity)