refactor: 架构重组 — doc/bot → core/infra,新增 Agent 调度模块
- src/doc/ 拆分为 src/core/extraction/, matching/, validation/(核心业务逻辑) - src/bot/ 重命名为 src/infra/browser/(浏览器自动化基础设施) - fill_consumable_doc.py → src/infra/documents/consumable.py - 新增 Agent 调度模块:coordinator.py, events.py, session.py,重构 orchestrator.py - 更新 AGENTS.md、README.md 及所有子目录 README
This commit is contained in:
20
scripts/README.md
Normal file
20
scripts/README.md
Normal file
@@ -0,0 +1,20 @@
|
||||
---
|
||||
last_reviewed: 2026-06-15
|
||||
---
|
||||
|
||||
# scripts — 调试脚本与数据目录
|
||||
|
||||
## 子目录
|
||||
|
||||
| 目录 | 说明 |
|
||||
|------|------|
|
||||
| `data/` | CLI 模式的数据目录:发票源文件、`config.json`、`.invoice_cache` 缓存 |
|
||||
|
||||
## 脚本
|
||||
|
||||
| 文件 | 说明 |
|
||||
|------|------|
|
||||
| `debug_stream_fields.py` | 诊断 stream_chat 返回对象的字段结构 |
|
||||
| `test_application_extract.py` | 测试出差申请单提取 |
|
||||
| `test_multimodal.py` | 测试多模态 LLM 识别 |
|
||||
| `test_travel_info.py` | 测试差旅信息提取 |
|
||||
@@ -10,7 +10,7 @@ from dotenv import load_dotenv # noqa: E402
|
||||
from llama_index.core.llms import ChatMessage # noqa: E402
|
||||
|
||||
from src.config import get_llm_config # noqa: E402
|
||||
from src.doc.llm_extractor import _create_llm # noqa: E402
|
||||
from src.core.extraction import _create_llm # noqa: E402
|
||||
|
||||
load_dotenv(Path(__file__).parent / ".env")
|
||||
|
||||
|
||||
@@ -31,7 +31,7 @@ sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding="utf-8", errors="repla
|
||||
|
||||
sys.path.insert(0, str(ROOT)) # noqa: E402
|
||||
|
||||
from src.doc.llm_extractor import extract_document # noqa: E402
|
||||
from src.core.extraction import extract_document # noqa: E402
|
||||
|
||||
|
||||
def test_single_file(file_path: Path) -> None:
|
||||
|
||||
@@ -15,8 +15,8 @@ sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding="utf-8", errors="repla
|
||||
ROOT = Path(__file__).resolve().parent.parent
|
||||
sys.path.insert(0, str(ROOT)) # noqa: E402
|
||||
|
||||
from src.doc.llm_extractor import extract_document # noqa: E402
|
||||
from src.doc.pdf import render_pdf_to_images # noqa: E402
|
||||
from src.core.extraction import extract_document # noqa: E402
|
||||
from src.infra.documents.pdf import render_pdf_to_images # noqa: E402
|
||||
|
||||
|
||||
def test_render() -> None:
|
||||
|
||||
@@ -15,7 +15,7 @@ from pathlib import Path
|
||||
ROOT = Path(__file__).resolve().parent.parent
|
||||
sys.path.insert(0, str(ROOT)) # noqa: E402
|
||||
|
||||
from src.doc.llm_extractor import extract_travel_info # noqa: E402
|
||||
from src.core.extraction import extract_travel_info # noqa: E402
|
||||
|
||||
|
||||
def main() -> None:
|
||||
|
||||
Reference in New Issue
Block a user