51 lines
2.1 KiB
Python
51 lines
2.1 KiB
Python
# app/agents.py
|
||
import asyncio
|
||
import random
|
||
from .schemas import ReceiptInfo, InvoiceInfo, ReceiptItem
|
||
|
||
# --- Agent核心功能 (占位符/模拟实现) ---
|
||
# 在实际应用中，这些函数将被替换为调用LangChain和LLM的真实逻辑。
|
||
|
||
async def agent_classify_document(text: str) -> str:
|
||
"""Agent 1: 文件分类 (模拟)"""
|
||
print("--- [Agent 1] 正在进行文档分类...")
|
||
await asyncio.sleep(0.5) # 模拟网络延迟
|
||
doc_types = ["信件", "收据", "发票", "合约"]
|
||
if "发票" in text: return "发票"
|
||
if "收据" in text or "小票" in text: return "收据"
|
||
if "合同" in text or "协议" in text: return "合约"
|
||
return random.choice(doc_types)
|
||
|
||
async def agent_extract_receipt_info(text: str) -> ReceiptInfo:
|
||
"""Agent 2: 收据信息提取 (模拟)"""
|
||
print("--- [Agent 2] 正在提取收据信息...")
|
||
await asyncio.sleep(1) # 模拟LLM处理时间
|
||
return ReceiptInfo(
|
||
merchant_name="模拟超市",
|
||
transaction_date="2025-08-10",
|
||
total_amount=198.50,
|
||
items=[ReceiptItem(name="牛奶", quantity=2, price=11.5)]
|
||
)
|
||
|
||
async def agent_extract_invoice_info(text: str) -> InvoiceInfo:
|
||
"""Agent 3: 发票信息提取 (模拟)"""
|
||
print("--- [Agent 3] 正在提取发票信息...")
|
||
await asyncio.sleep(1) # 模拟LLM处理时间
|
||
return InvoiceInfo(
|
||
invoice_number="INV123456789",
|
||
issue_date="2025-08-09",
|
||
seller_name="模拟科技有限公司",
|
||
total_amount_in_figures=12000.00
|
||
)
|
||
|
||
async def agent_vectorize_and_store(doc_id: str, text: str, category: str, vector_db: dict):
|
||
"""Agent 4: 向量化并存储 (模拟)"""
|
||
print(f"--- [Agent 4] 正在向量化文档 (ID: {doc_id})...")
|
||
await asyncio.sleep(0.5)
|
||
chunks = [text[i:i+200] for i in range(0, len(text), 200)]
|
||
vector_db[doc_id] = {
|
||
"metadata": {"category": category, "chunk_count": len(chunks)},
|
||
"content_chunks": chunks,
|
||
"vectors": [random.random() for _ in range(len(chunks) * 128)]
|
||
}
|
||
print(f"--- [Agent 4] 文档 {doc_id} 已存入向量数据库。") |