research
Method
This is a method of the DeepResearchAgent class in the deep_research_agent module.
Perform a deep research query.
Signature
def research(query: str, instructions: Optional[str], model: Optional[str], summary_mode: Optional[Literal['auto', 'detailed', 'concise']], web_search: Optional[bool], code_interpreter: Optional[bool], mcp_servers: Optional[List[Dict[str, Any]]], file_ids: Optional[List[str]], file_search: Optional[bool], file_search_stores: Optional[List[str]], stream: bool) -> DeepResearchResponse
Parameters
The research question or topic to investigate
Override the agent’s default instructions
Override the default model
Summary mode (“auto”, “detailed”, “concise”) - OpenAI only
Enable web search - OpenAI only
Enable code interpreter - OpenAI only
MCP server configurations - OpenAI only
File IDs for code interpreter - OpenAI only
Enable file search - Gemini only
File search store names - Gemini only
Enable streaming for real-time progress (default: True)
Returns
DeepResearchResponse containing the report, citations, and metadata
Usage
# Standard research
result = agent.research(
"What are the latest developments in quantum computing?",
summary_mode="detailed"
)
# Streaming research (Gemini) - shows real-time progress
result = agent.research(
"Research AI trends",
stream=True # Real-time thinking summaries
)
print(result.report)
