agents.research.open_perplexity.config¶

Configuration for the open_perplexity research agent.

from typing import Any This module defines the configuration class and factory methods for creating research agent configurations. It includes settings for LLM engines, tools, vector stores, and research parameters.

Classes¶

ResearchAgentConfig

Configuration for open_perplexity research agent.

Module Contents¶

class agents.research.open_perplexity.config.ResearchAgentConfig¶

Bases: haive.core.engine.agent.agent.AgentConfig

Configuration for open_perplexity research agent.

Defines all configuration parameters for the research agent, including state schemas, engines, tools, and research parameters.

state_schema¶: Schema for the agent state

input_schema¶: Schema for input to the agent

output_schema¶: Schema for agent output

engines¶: Dictionary of AugLLM engines for different tasks

tools¶: Tools for research and analysis

vectorstore_config¶: Vector store configuration for document storage

react_agent_name¶: Name of the configured ReAct agent

rag_agent_name¶: Name of the configured RAG agent

report_format¶: Format for the final report

research_depth¶: Depth of research (1-5, higher means more thorough)

max_sources_per_query¶: Maximum number of sources to use per query

concurrent_searches¶: Number of concurrent searches to perform

default_report_sections¶: Default sections for the research report

classmethod from_scratch(name=None, llm_model='gpt-4o', **kwargs)¶

Create a research agent configuration from scratch.

Factory method to create a fully configured research agent with all necessary engines, tools, and settings.

Parameters:

name (str | None) – Optional name for the agent (defaults to timestamped name)
llm_model (str) – Model to use for the agent (default: “gpt-4o”)
**kwargs – Additional configuration parameters

Returns:

A fully configured research agent configuration

Return type:

ResearchAgentConfig