Ask Question

Ask Travel Question (RAG 知识库问答)

回答用户关于差旅政策、报销、预订、城市指南等的问题，使用 RAGKnowledgeAgent 从本地知识库检索并生成答案。

When to Use

• 用户问「XX标准是多少」「如何报销」「航班延误怎么办」等
• 需要基于企业/项目知识文档回答时

Agent

• RAGKnowledgeAgent (agents/rag_knowledge_agent.py)
• 所有子 Agent 均使用 model 对象（非 model_config_name），需先创建 OpenAIChatModel
• 异步：reply() 为 async，需 await

初始化与调用

import asyncio
from agentscope.message import Msg
from agentscope.model import OpenAIChatModel
from config_agentscope import init_agentscope
from config import LLM_CONFIG
from agents.rag_knowledge_agent import RAGKnowledgeAgent
import json

async def ask_question(user_query: str):
    init_agentscope()
    model = OpenAIChatModel(
        model_name=LLM_CONFIG["model_name"],
        api_key=LLM_CONFIG["api_key"],
        client_kwargs={"base_url": LLM_CONFIG["base_url"], "timeout": 60},
        temperature=LLM_CONFIG.get("temperature", 0.7),
        max_tokens=LLM_CONFIG.get("max_tokens", 2000),
    )
    # 嵌入模型路径从 config.RAG_CONFIG 读取，默认 data/models/bge-small-zh-v1.5
    rag_agent = RAGKnowledgeAgent(
        name="RAGKnowledgeAgent",
        model=model,
        knowledge_base_path="./data/rag_knowledge",
        collection_name="business_travel_knowledge",
        top_k=3,
    )
    if not getattr(rag_agent, "initialized", True):
        return {"error": "RAG 未初始化，请先运行 python scripts/init_knowledge_base.py"}
    user_msg = Msg(name="user", content=user_query, role="user")
    result = await rag_agent.reply(user_msg)
    return json.loads(result.content) if isinstance(result.content, str) else result.content

# 使用
data = asyncio.run(ask_question("北京的住宿标准是多少？"))
# data: {"status": "success"|"no_knowledge", "answer": "...", "retrieved_documents": [...], "query": "..."}