Skip to main content

​
praisonaiagents.agent.deep_research_agent

Core SDK Deep Research Agent Module This module provides the DeepResearchAgent class for automating complex research workflows using Deep Research APIs from multiple providers:
  • OpenAI: o3-deep-research, o4-mini-deep-research (via Responses API)
  • Gemini: deep-research-pro (via Interactions API)
The agent automatically detects the provider based on the model name and uses the appropriate API. Example: from praisonaiagents import DeepResearchAgent

​
OpenAI Deep Research

agent = DeepResearchAgent( name=“Research Assistant”, model=“o3-deep-research”, instructions=“You are a professional researcher…” )

​
Gemini Deep Research

agent = DeepResearchAgent( name=“Research Assistant”, model=“deep-research-pro”, instructions=“You are a professional researcher…” ) result = agent.research(“What are the economic impacts of AI on healthcare?”) print(result.report) for citation in result.citations: print(f”- {citation.title}: {citation.url}“)

​
Overview

This module provides components for deep_research_agent.

​
Classes

Citation

Represents a citation in the research report.

ReasoningStep

Represents a reasoning step in the research process.

WebSearchCall

Represents a web search call made during research.

CodeExecutionStep

Represents a code execution step during research.

MCPCall

Represents an MCP tool call during research.

FileSearchCall

Represents a file search call (Gemini-specific).

DeepResearchResponse

Complete response from a Deep Research query.

Provider

Supported Deep Research providers.

DeepResearchAgent

Agent for performing deep research using multiple provider APIs.