111 lines
3.2 KiB
Python
111 lines
3.2 KiB
Python
|
"""
|
|||
|
|
报告生成器
|
|||
|
|
将分析计划 + 探索结果 + 洞察，综合为一份可读报告。
|
|||
|
|
"""
|
|||
|
|
import json
|
|||
|
|
from typing import Any
|
|||
|
|
|
|||
|
|
import openai
|
|||
|
|
from config import LLM_CONFIG
|
|||
|
|
from explorer import ExplorationStep
|
|||
|
|
from insights import Insight
|
|||
|
|
|
|||
|
|
|
|||
|
|
REPORT_PROMPT = """你是一个数据分析报告撰写专家。基于以下信息撰写报告。
|
|||
|
|
|
|||
|
|
## 用户问题
|
|||
|
|
{question}
|
|||
|
|
|
|||
|
|
## 分析计划
|
|||
|
|
{plan}
|
|||
|
|
|
|||
|
|
## 探索过程
|
|||
|
|
{exploration}
|
|||
|
|
|
|||
|
|
## 主动洞察
|
|||
|
|
{insights_text}
|
|||
|
|
|
|||
|
|
## 撰写要求
|
|||
|
|
1. **开头**：一句话总结核心结论（先给答案）
|
|||
|
|
2. **核心发现**：按重要性排列，每个发现带具体数字
|
|||
|
|
3. **深入洞察**：异常、趋势、关联（从洞察中提取）
|
|||
|
|
4. **建议**：基于数据的行动建议
|
|||
|
|
5. **审计**：末尾附上所有执行的 SQL
|
|||
|
|
|
|||
|
|
使用 Markdown，中文撰写。
|
|||
|
|
语气：专业但不枯燥，像一个聪明的分析师在做简报。"""
|
|||
|
|
|
|||
|
|
|
|||
|
|
class ReportGenerator:
|
|||
|
|
"""报告生成器"""
|
|||
|
|
|
|||
|
|
def __init__(self):
|
|||
|
|
self.client = openai.OpenAI(
|
|||
|
|
api_key=LLM_CONFIG["api_key"],
|
|||
|
|
base_url=LLM_CONFIG["base_url"],
|
|||
|
|
)
|
|||
|
|
self.model = LLM_CONFIG["model"]
|
|||
|
|
|
|||
|
|
def generate(
|
|||
|
|
self,
|
|||
|
|
question: str,
|
|||
|
|
plan: dict,
|
|||
|
|
steps: list[ExplorationStep],
|
|||
|
|
insights: list[Insight],
|
|||
|
|
) -> str:
|
|||
|
|
"""生成分析报告"""
|
|||
|
|
|
|||
|
|
# 构建探索过程文本
|
|||
|
|
exploration = self._build_exploration(steps)
|
|||
|
|
|
|||
|
|
# 构建洞察文本
|
|||
|
|
insights_text = self._build_insights(insights)
|
|||
|
|
|
|||
|
|
prompt = REPORT_PROMPT.format(
|
|||
|
|
question=question,
|
|||
|
|
plan=json.dumps(plan, ensure_ascii=False, indent=2),
|
|||
|
|
exploration=exploration,
|
|||
|
|
insights_text=insights_text,
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
response = self.client.chat.completions.create(
|
|||
|
|
model=self.model,
|
|||
|
|
messages=[
|
|||
|
|
{"role": "system", "content": "你是专业的数据分析师，撰写清晰、有洞察力的分析报告。"},
|
|||
|
|
{"role": "user", "content": prompt},
|
|||
|
|
],
|
|||
|
|
temperature=0.3,
|
|||
|
|
max_tokens=4096,
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
return response.choices[0].message.content
|
|||
|
|
|
|||
|
|
def _build_exploration(self, steps: list[ExplorationStep]) -> str:
|
|||
|
|
parts = []
|
|||
|
|
for step in steps:
|
|||
|
|
if step.action == "done":
|
|||
|
|
parts.append(f"### 探索结束\n{step.reasoning}")
|
|||
|
|
continue
|
|||
|
|
|
|||
|
|
if step.success:
|
|||
|
|
parts.append(
|
|||
|
|
f"### 第 {step.round_num} 轮：{step.purpose}\n"
|
|||
|
|
f"思考: {step.reasoning}\n"
|
|||
|
|
f"SQL: `{step.sql}`\n"
|
|||
|
|
f"结果 ({step.row_count} 行):\n"
|
|||
|
|
f"列: {step.columns}\n"
|
|||
|
|
f"数据: {json.dumps(step.rows, ensure_ascii=False)}"
|
|||
|
|
)
|
|||
|
|
else:
|
|||
|
|
parts.append(
|
|||
|
|
f"### 第 {step.round_num} 轮：{step.purpose}\n"
|
|||
|
|
f"SQL: `{step.sql}`\n"
|
|||
|
|
f"执行失败: {step.error}"
|
|||
|
|
)
|
|||
|
|
return "\n\n".join(parts) if parts else "无探索步骤"
|
|||
|
|
|
|||
|
|
def _build_insights(self, insights: list[Insight]) -> str:
|
|||
|
|
if not insights:
|
|||
|
|
return "未检测到异常。"
|
|||
|
|
return "\n".join(str(i) for i in insights)
|