llm

Perplexity LLM service implementation.

This module provides a service for interacting with Perplexity’s API using an OpenAI-compatible interface. It handles Perplexity’s unique token usage reporting patterns while maintaining compatibility with the Pipecat framework.

class pipecat.services.perplexity.llm.PerplexityLLMService(*, api_key: str, base_url: str = 'https://api.perplexity.ai', model: str = 'sonar', **kwargs)

Bases: OpenAILLMService

A service for interacting with Perplexity’s API.

This service extends OpenAILLMService to work with Perplexity’s API while maintaining compatibility with the OpenAI-style interface. It specifically handles the difference in token usage reporting between Perplexity (incremental) and OpenAI (final summary).

__init__(*, api_key: str, base_url: str = 'https://api.perplexity.ai', model: str = 'sonar', **kwargs)

Initialize the Perplexity LLM service.

Parameters:

• api_key – The API key for accessing Perplexity’s API.

• base_url – The base URL for Perplexity’s API. Defaults to “https://api.perplexity.ai”.

• model – The model identifier to use. Defaults to “sonar”.

• **kwargs – Additional keyword arguments passed to OpenAILLMService.

build_chat_completion_params(params_from_context: OpenAILLMInvocationParams) → dict

Build parameters for Perplexity chat completion request.

Perplexity uses a subset of OpenAI parameters and doesn’t support tools.

Parameters:

params_from_context – Parameters, derived from the LLM context, to use for the chat completion. Contains messages, tools, and tool choice.

Returns:

Dictionary of parameters for the chat completion request.

async start_llm_usage_metrics(tokens: LLMTokenUsage)

Accumulate token usage metrics during processing.

Perplexity reports token usage incrementally during streaming, unlike OpenAI which provides a final summary. We accumulate the counts and report the total at the end of processing.

Parameters:

tokens – Token usage information to accumulate.