adapters

LLM adapter for conversation-summary generation and formatting.

This module provides the LLMAdapter class used by the flow manager to:

• Format a generated summary as a context message

• Generate a summary via out-of-band LLM inference

class pipecat.flows.adapters.LLMAdapter

Bases: object

Helpers for generating and formatting conversation summaries.

format_summary_message(summary: str) → dict

Format a summary as a developer message.

Summary messages use the LLMContextMessage format (OpenAI-style), as summarization triggers an LLMMessagesUpdateFrame.

Parameters:

summary – The generated summary text.

Returns:

A developer message containing the summary.

async generate_summary(llm: Any, summary_prompt: str, context: LLMContext) → str | None

Generate a summary by running a direct one-shot, out-of-band inference with the LLM.

Parameters:

• llm – LLM service instance containing client/credentials.

• summary_prompt – Prompt text to guide summary generation.

• context – Context object containing conversation history for the summary.

Returns:

Generated summary text, or None if generation fails.