> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Deep Research Agent • AI Agent SDK

> DeepResearchAgent: Agent for performing deep research using multiple provider APIs.

# DeepResearchAgent

> Defined in the [**Deep Research Agent**](https://praison.ai/docs/sdk/reference/praisonaiagents/modules/deep_research_agent.md) module.

AI Agent

Agent for performing deep research using multiple provider APIs.

Supports:

* **OpenAI Deep Research**: o3-deep-research, o4-mini-deep-research
* **Gemini Deep Research**: deep-research-pro-preview
* **LiteLLM**: Unified interface for OpenAI models

The provider is auto-detected based on the model name, or can be explicitly set.

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
%%{init: {'theme': 'base', 'themeVariables': { 'primaryColor': '#8B0000', 'primaryTextColor': '#fff', 'primaryBorderColor': '#710101', 'lineColor': '#189AB4', 'secondaryColor': '#189AB4', 'tertiaryColor': '#fff' }}}%%

graph LR
    input["Input Data"] --> agent["Agent: DeepResearchAgent"]
    agent --> output["Output Result"]
    style agent fill:#8B0000,color:#fff
    style input fill:#8B0000,color:#fff
    style output fill:#8B0000,color:#fff
```

## Constructor

**name** `Optional[str]`

No description available.

**instructions** `Optional[str]`

No description available.

**model** `str` (default: 'o3-deep-research')

No description available.

**provider** `Optional` (default: 'auto')

No description available.

**api\_key** `Optional[str]`

No description available.

**base\_url** `Optional[str]`

No description available.

**verbose** `bool` (default: True)

No description available.

**summary\_mode** `Literal` (default: 'auto')

No description available.

**enable\_web\_search** `bool` (default: True)

No description available.

**enable\_code\_interpreter** `bool` (default: False)

No description available.

**enable\_file\_search** `bool` (default: False)

No description available.

**mcp\_servers** `Optional`

No description available.

**file\_search\_stores** `Optional`

No description available.

**use\_litellm** `bool` (default: False)

No description available.

**poll\_interval** `int` (default: 10)

No description available.

**max\_wait\_time** `int` (default: 3600)

No description available.

## Methods

> [card] [openai\_client()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/DeepResearchAgent-openai_client.md)
>
> Get the synchronous OpenAI client (lazy initialization).

> [card] [async\_openai\_client()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/DeepResearchAgent-async_openai_client.md)
>
> Get the asynchronous OpenAI client (lazy initialization).

> [card] [gemini\_client()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/DeepResearchAgent-gemini_client.md)
>
> Get the Gemini client (lazy initialization).

> [card] [research()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/DeepResearchAgent-research.md)
>
> Perform a deep research query.

> [card] [aresearch()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/DeepResearchAgent-aresearch.md)
>
> Async version of research().

> [card] [follow\_up()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/DeepResearchAgent-follow_up.md)
>
> Ask a follow-up question based on a previous research interaction.

> [card] [clarify()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/DeepResearchAgent-clarify.md)
>
> Generate clarifying questions for a research query.

> [card] [rewrite\_query()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/DeepResearchAgent-rewrite_query.md)
>
> Rewrite a research query to be more specific and detailed.

## Usage

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# OpenAI (default)
    agent = DeepResearchAgent(
        model="o3-deep-research",
        instructions="You are a professional researcher."
    )
    
    # Gemini
    agent = DeepResearchAgent(
        model="deep-research-pro",
        instructions="You are a professional researcher."
    )
    
    # Using LiteLLM
    agent = DeepResearchAgent(
        model="o3-deep-research",
        use_litellm=True
    )
    
    result = agent.research("Research the economic impact of AI on healthcare.")
    print(result.report)
```

## Source

> [card] [View on GitHub](https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/agent/deep_research_agent.py#L151)
>
> `praisonaiagents/agent/deep_research_agent.py` at line 151

***

## Related Documentation

> [card] [Agents Concept](https://praison.ai/docs/docs/concepts/agents)

> [card] [Single Agent Guide](https://praison.ai/docs/docs/guides/single-agent)

> [card] [Multi-Agent Guide](https://praison.ai/docs/docs/guides/multi-agent)

> [card] [Agent Configuration](https://praison.ai/docs/docs/configuration/agent-config)

> [card] [Auto Agents](https://praison.ai/docs/docs/features/autoagents)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.