PromptExpanderAgent Module

Expand short prompts into detailed, comprehensive prompts for better task execution

PromptExpanderAgent Module

The PromptExpanderAgent class expands short prompts into detailed, comprehensive prompts for better task execution.

Key Difference from QueryRewriterAgent

• QueryRewriterAgent: Optimizes queries for search/retrieval (RAG)
• PromptExpanderAgent: Expands prompts for detailed task execution

Supported Strategies

• BASIC: Simple expansion with clarity improvements
• DETAILED: Rich expansion with context, constraints, and examples
• STRUCTURED: Expansion with clear structure (task, format, requirements)
• CREATIVE: Expansion with creative flair and vivid language
• AUTO: Automatically selects the best strategy based on prompt analysis

Import

from praisonaiagents import PromptExpanderAgent, ExpandStrategy

Quick Example

from praisonaiagents import PromptExpanderAgent, ExpandStrategy

agent = PromptExpanderAgent()

# Basic expansion
result = agent.expand("write a movie script in 3 lines")
print(result.expanded_prompt)

# Detailed expansion
result = agent.expand("blog about AI", strategy=ExpandStrategy.DETAILED)
print(result.expanded_prompt)

Constructor

PromptExpanderAgent()

Creates a new PromptExpanderAgent instance.

Parameters:

Parameter	Type	Default	Description
name	str	"Prompt Expander"	Agent name
model	str	"gpt-4o-mini"	LLM model to use
verbose	bool	False	Enable verbose logging
temperature	float	0.7	Temperature for generation (higher = more creative)
tools	list	[]	Optional tools for context gathering

Methods

expand(prompt, strategy)

Expands a prompt using the specified strategy.

Parameters:

• prompt (str): The original short prompt
• strategy (ExpandStrategy): Expansion strategy to use (default: AUTO)

Returns: ExpandResult - Contains expanded prompt and metadata

ExpandStrategy Enum

class ExpandStrategy(Enum):
    BASIC = "basic"
    DETAILED = "detailed"
    STRUCTURED = "structured"
    CREATIVE = "creative"
    AUTO = "auto"

ExpandResult

@dataclass
class ExpandResult:
    original_prompt: str
    expanded_prompt: str
    strategy_used: ExpandStrategy
    metadata: Dict[str, Any]

Examples

Creative Expansion

from praisonaiagents import PromptExpanderAgent, ExpandStrategy

agent = PromptExpanderAgent(model="gpt-4o-mini", )
result = agent.expand("write a poem", strategy=ExpandStrategy.CREATIVE)
print(result.expanded_prompt)

With Tools for Context

from praisonaiagents import PromptExpanderAgent
from praisonaiagents import internet_search

agent = PromptExpanderAgent(tools=[internet_search], )
result = agent.expand("latest AI developments")
# Gathers context first, then expands

Structured Expansion

from praisonaiagents import PromptExpanderAgent, ExpandStrategy

agent = PromptExpanderAgent()
result = agent.expand(
    "create a REST API",
    strategy=ExpandStrategy.STRUCTURED
)
# Returns structured prompt with task, format, requirements

Related

• Agent Module - Base Agent class
• QueryRewriterAgent Module - Query optimization for RAG
• Task Module - Task definition