haive.agents.research.perplexity_agent
======================================

.. py:module:: haive.agents.research.perplexity_agent

.. autoapi-nested-parse::

   Perplexity-style deep research agent.

   Multi-agent composition:
     QueryAnalyzer (SimpleAgent) → Researcher (ReactAgent + search + RAG) → Synthesizer (SimpleAgent)

   The Researcher has:
   - Tavily web search (or mock fallback)
   - Dynamic RAG: stores search results in vector store for retrieval

   Usage:
       from haive.agents.research.perplexity_agent import create_research_agent
       agent = create_research_agent()
       result = agent.run("What are the latest advances in quantum computing?")



Classes
-------

.. autoapisummary::

   haive.agents.research.perplexity_agent.ResearchAgent


Functions
---------

.. autoapisummary::

   haive.agents.research.perplexity_agent.create_research_agent
   haive.agents.research.perplexity_agent.web_search


Module Contents
---------------

.. py:class:: ResearchAgent

   Bases: :py:obj:`haive.agents.multi.agent.MultiAgent`


   Perplexity-style research agent using MultiAgent sequential composition.

   Pipeline: QueryAnalyzer → Researcher (search + RAG) → Synthesizer

   Example::
       agent = create_research_agent()
       result = agent.run("What is quantum computing?")


.. py:function:: create_research_agent(name = 'perplexity', tools = None, max_search_iterations = 8)

   Create a Perplexity-style research agent.

   :param name: Agent name
   :param tools: Custom search tools (defaults to Tavily if TAVILY_API_KEY set, else mock)
   :param max_search_iterations: Max reasoning loops for the researcher

   :returns: ResearchAgent ready for execution


.. py:function:: web_search(query)

   Search the web for information. Returns search results for the given query.