Skip to main content

​
Overview

ParallelDocQA processes large documents in parallel by splitting them into chunks, analyzing each chunk concurrently, and then synthesizing results using RAG retrieval.

​
Class Signature

from qwen_agent.agents import ParallelDocQA

class ParallelDocQA(Assistant):
    def __init__(
        self,
        function_list: Optional[List[Union[str, Dict, BaseTool]]] = None,
        llm: Optional[Union[Dict, BaseChatModel]]] = None,
        system_message: Optional[str] = DEFAULT_SYSTEM_MESSAGE,
        name: Optional[str] = DEFAULT_NAME,
        description: Optional[str] = DEFAULT_DESC,
        files: Optional[List[str]] = None
    )

​
How It Works

  1. Parse & Chunk: Documents are split into chunks (~1000 tokens each)
  2. Parallel Analysis: Multiple agents process chunks concurrently
  3. RAG Retrieval: Relevant content is retrieved from all responses
  4. Final Synthesis: Summary agent generates final answer

​
Usage Example

from qwen_agent.agents import ParallelDocQA
from qwen_agent.llm.schema import Message

# For large documents
agent = ParallelDocQA(
    llm={'model': 'qwen-max', 'api_key': 'your-api-key'},
    files=['large_research_paper.pdf']  # 100+ pages
)

messages = [
    Message(role='user', content='Summarize the key findings')
]

for response in agent.run(messages):
    print(response[-1].content)

​
See Also

Build docs developers (and LLMs) love

Get started for freeTalk to us