> ## 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.
# Query Rewriter Agent • AI Agent SDK
> Query Rewriter Agent Module
# query\_rewriter\_agent
AI Agent
Query Rewriter Agent Module
This module provides the QueryRewriterAgent class for transforming user queries
to improve retrieval quality in RAG applications.
Supported Rewriting Strategies:
* **BASIC**: Simple rephrasing for clarity and keyword optimization
* **HYDE**: Hypothetical Document Embeddings - generates a hypothetical answer
* **STEP\_BACK**: Generates higher-level concept questions for complex queries
* **SUB\_QUERIES**: Decomposes multi-part questions into focused sub-queries
* **MULTI\_QUERY**: Generates multiple paraphrased versions for ensemble retrieval
* **CONTEXTUAL**: Uses conversation history to resolve references and context
Example:
from praisonaiagents import QueryRewriterAgent, RewriteStrategy
agent = QueryRewriterAgent()
# Basic rewriting
result = agent.rewrite("AI trends")
print(result.rewritten\_queries)
# HyDE for better semantic matching
result = agent.rewrite("What is quantum computing?", strategy=RewriteStrategy.HYDE)
print(result.hypothetical\_document)
# Contextual with chat history
chat\_history = \[
\{"role": "user", "content": "Tell me about Python"},
\{"role": "assistant", "content": "Python is a programming language..."}
]
result = agent.rewrite("What about its performance?", chat\_history=chat\_history)
# With search tools for context-aware rewriting
from praisonaiagents.tools import internet\_search
agent = QueryRewriterAgent(tools=\[internet\_search])
result = agent.rewrite("latest AI developments") # Searches first, then rewrites
## Import
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents.agent import query_rewriter_agent
```
## Classes
Enumeration of available query rewriting strategies.
Result of a query rewriting operation.
Agent for rewriting queries to improve retrieval quality in RAG applications.
***
## Related Documentation