Package com.tnsai.llm.providers

Class PerplexityClient

java.lang.Object

com.tnsai.llm.providers.AbstractLLMClient

com.tnsai.llm.providers.AbstractOpenAICompatibleClient

com.tnsai.llm.providers.PerplexityClient

All Implemented Interfaces:

com.tnsai.llm.LLMClient

public class PerplexityClient
extends AbstractOpenAICompatibleClient

Perplexity LLM client.

Perplexity hosts search-augmented LLMs (the Sonar family). Models fetch web results inline and ground their answers in real-time sources. The API is OpenAI-compatible at https://api.perplexity.ai — same chat-completions wire format as GroqClient / XAIGrokClient / YiClient.

Supported models (at time of writing):

• sonar — fast / cheap search-grounded answer
• sonar-pro — higher-quality search + synthesis tier
• sonar-reasoning — chain-of-thought reasoning over search results
• sonar-deep-research — multi-hop deep research mode

The catalog evolves; check the live list at docs.perplexity.ai.

About citations. Perplexity's responses include a citations[] array alongside the standard OpenAI choices[].message.content text. The shared

invalid reference

ChatResponse

SPI doesn't carry citation metadata, so v1 of this client preserves only the textual answer — citations are dropped on the floor. Most callers want grounded text without bookkeeping the source URLs themselves, so this is the right v1 default. Surfacing citations is a separate ChatResponse extension and a follow-up issue.

Configuration via environment variable:

• PERPLEXITY_API_KEY — Required.

See Also:

• Perplexity API Documentation

Constructor Summary

Constructors

Constructor	Description
PerplexityClient(String model)
PerplexityClient(String model, float temperature)
PerplexityClient(String model, float temperature, Float topP, Integer maxTokens)
PerplexityClient(String model, float temperature, Integer maxTokens)
PerplexityClient(String baseUrl, String model, float temperature, Float topP, Integer maxTokens, String apiKey)
PerplexityClient(String baseUrl, String model, float temperature, Integer maxTokens, String apiKey)

Method Summary

Methods inherited from class com.tnsai.llm.providers.AbstractOpenAICompatibleClient

chat, streamChat

Methods inherited from class com.tnsai.llm.providers.AbstractLLMClient

getBaseUrl, getCallTimeoutMs, getMaxTokens, getModel, getTemperature, getTopP

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface com.tnsai.llm.LLMClient

chat, chat, chat, chat, chat, getCapabilities, getProviderName, listModels, streamChat, streamChat, streamChatWithHandler, streamChatWithHandler, streamChatWithSpec, streamChatWithSpec

Constructor Details

PerplexityClient

public PerplexityClient(String model)

PerplexityClient

public PerplexityClient(String model,
 float temperature)

PerplexityClient

public PerplexityClient(String model,
 float temperature,
 Integer maxTokens)

PerplexityClient

public PerplexityClient(String model,
 float temperature,
 Float topP,
 Integer maxTokens)

PerplexityClient

public PerplexityClient(String baseUrl,
 String model,
 float temperature,
 Integer maxTokens,
 String apiKey)

PerplexityClient

public PerplexityClient(String baseUrl,
 String model,
 float temperature,
 Float topP,
 Integer maxTokens,
 String apiKey)