# [doc-llm-autotest 基于大模型的文档自动化测试平台:：用户提交文件进行文档测试](https://link.juejin.cn?target=https%3A%2F%2Fwww.cnblogs.com%2Fxiaojp65536%2Fp%2F19321881 "https://www.cnblogs.com/xiaojp65536/p/19321881") \[合集 - 文档自动化测试平台(1)
1.doc-llm-autotest 基于大模型的文档自动化测试平台:：用户提交文件进行文档测试12-08
收起
一、技术选型与功能设计
使用minio服务，进行文件的中转与存储。用户提交文件到doc-llm-controller，控制面将文件转存到minio中，关联此次任务id。然后doc-llm-worker轮询redis发现有需要执行的任务，拿到id后，根据id从minio拿取文件，然后将文件解析成结构化信息，再提交到大模型，进行文档测试。
那么此部分功能流程图大致如下：
相对应的，在整体业务流程中补充文件存取步骤，最后如下：
二、minio配置与使用
minio安装部署：我们使用docker镜像来部署minio服务，暴露9000端口提供给我们自己服务使用：
bash
docker run -d --name doc-llm-minio -p 9000:9000 -p 9001:9001 --restart=always -e MINIO_ROOT_USER=root -e MINIO_ROOT_PASSWORD=password -v /home/workspace/minio:/data minio/minio:latest server /data --console-address ":9001"通过python来调用minio服务：
arduino
# minio下载
pip install minio
python
from minio import Minio
from minio.error import S3Error
import io
# 配置minio
client = Minio(
"localhost:9000",
access_key="root",
secret_key="xiao1234",
secure=False,
)
bucket_name = "doc-llm-bucket"
try:
if not client.bucket_exists(bucket_name):
client.make_bucket(bucket_name)
else:
print(f"Bucket '{bucket_name}' already exists.")
except S3Error as e:
print(f"Error occurred: {e}")
# 通过python上传文件到minio
def upload_file(local_file_path, object_name):
try:
client.fput_object(bucket_name, object_name, local_file_path)
print(f"'{local_file_path}' is successfully uploaded as '{object_name}' to bucket '{bucket_name}'.")
except S3Error as e:
print(f"Error occurred while uploading: {e}")
# 文件下载
def download_file(object_name, local_file_path):
try:
client.fget_object(bucket_name, object_name, local_file_path)
print(f"'{object_name}' is successfully downloaded to '{local_file_path}'.")
except S3Error as e:
print(f"Error occurred while downloading: {e}")
# 列出所有文件
def list_files():
try:
objects = client.list_objects(bucket_name)
print(f"Objects in bucket '{bucket_name}':")
for obj in objects:
print(f"- {obj.object_name} (size: {obj.size} bytes)")
except S3Error as e:
print(f"Error occurred while listing objects: {e}")
# 删除指定文件
def delete_file(object_name):
try:
client.remove_object(bucket_name, object_name)
print(f"'{object_name}' is successfully deleted from bucket '{bucket_name}'.")
except S3Error as e:
print(f"Error occurred while deleting: {e}")测试效果如下：
三、控制面doc-llm-controller服务适配
总体思路：
接口层接收到带文件的创建任务请求，先新增一条任务数据到mysql，其中doc字段为__PENDING_FILE__。然后拿到任务id后，调用推送文件服务将文件关联任务id一起推送到minio，结束后更新任务信息doc字段为：f"minio://{MINIO_BUCKET}/{object_name}"。
至此控制面业务结束。
services层：
新增file_service.py，提供minio服务的调用
python
# 代码样例
def _ensure_bucket():
"""确保 bucket 存在"""
if not _minio_client.bucket_exists(MINIO_BUCKET):
_minio_client.make_bucket(MINIO_BUCKET)
def save_task_file(task_id: int, file_obj: FileStorage) -> str:
"""
把用户上传的文件存到 MinIO，文件名格式：{task_id}_{orig_filename}
返回存入数据库的 doc 字段值，例如：minio://doc-llm-bucket/123_xxx.docx
...
doc_path = f"minio://{MINIO_BUCKET}/{object_name}"
return doc_path
python
# doc_check_service
def update_task_doc(task_id: int, doc: str) -> None:
"""更新任务的 doc 字段"""
task = task_service.get_task_by_id(task_id)
if not task:
raise TaskNotFoundError(f"任务 {task_id} 不存在")
task_service.update_task_doc(task_id, doc)
# task_service
def update_task_doc(task_id: int, doc: str) -> None:
"""更新任务的 doc 字段"""
with get_session() as session:
task = session.scalar(
select(TaskDocLLM).where(TaskDocLLM.task_id == task_id)
)
if not task:
raise ValueError(f"任务 {task_id} 不存在")
task.doc = doc更新接口函数，兼容传文本信息、文本文件两种方式：
ini
@bp.route("/tasks/", methods=["POST"])
def create_doc_task():
# 判断是不是文件上传
if request.content_type and "multipart/form-data" in request.content_type:
return _create_task_with_file()
# 默认走老的 JSON 逻辑
return _create_task_with_json()
def _create_task_with_json():
...
task_id = doc_check_service.submit_doc_task(task_name, doc, product, feature)
...
def _create_task_with_file():
....
try:
# 1. 先写一条任务，doc 用占位符，保证非空
placeholder_doc = "__PENDING_FILE__"
task_id = doc_check_service.submit_doc_task(
task_name=task_name,
doc=placeholder_doc,
product=product,
feature=feature,
)
doc_path = file_service.save_task_file(task_id, file_obj)
# 3. 回写 doc 字段
doc_check_service.update_task_doc(task_id, doc_path)
...用postman测试下接口效果，大致是OK的：
接口请求：
flask这边日志、数据库、minio表现都OK，数据一致性有保障：
四、数据面doc-llm-worker服务适配
当前数据流的流转：从时间先后顺序，最先会写入task到mysql，此时doc字段是pending字样，然后写入task_id到redis，再就是把文件传给minio，最后更新mysql.doc为minio的文件路径。
doc-llm-worker初始逻辑是：读redis队列找到需要执行的任务，读mysql拿到doc文本信息，调用大模型进行测试。因此数据面doc-llm-worker要做一些适配：
1.新增文件任务的下载
从minio下载文件，在file_service层补充函数：
python
def download_file(bucket: str, object_name: str) -> bytes:
"""
从 MinIO 下载文件并返回 bytes 内容。
调用方式：
content = download_file("doc-llm-bucket", "15_readme.txt")
text = content.decode("utf-8")
"""
try:
response = _minio_client.get_object(bucket, object_name)
data = response.read()
return data
except S3Error as e:
raise RuntimeError(f"Download from minio failed: {e}") from e2.将文件解析
其中如果doc是纯文本的话走老逻辑；是minio格式的话，走文件下载，然后解析成文本；是pending的话，等待知道文件上传ok
新增doc_loader.py
python
# app/worker/doc_loader.py
import logging
from typing import Tuple
from app.services import file_service
PENDING_MARK = "__PENDING_FILE__"
def _is_minio_path(doc: str) -> bool:
"""
判断 doc 是否为 MinIO 路径：
- /bucket/object_name
- minio://bucket/object_name
"""
...
def _parse_minio_path(doc: str) -> Tuple[str, str]:
"""解析 doc 字段为 (bucket, object_name)"""
...
def load_doc_for_task(task) -> str:
"""
根据任务对象，返回真正要给 LLM 的 doc 文本（str）
1. doc == "__PENDING_FILE__" -> 抛 DocPendingError
2. doc 是 MinIO 路径 (/bucket/obj) -> 从 MinIO 下载并 decode
3. 其他 -> 当作普通文本直接返回
"""
doc = (task.doc or "").strip()
if not doc:
raise DocPathError(f"task {task.id} doc is empty")
if doc == PENDING_MARK:
raise DocPendingError(f"task {task.id} doc is still pending file upload")
if _is_minio_path(doc):
bucket, object_name = _parse_minio_path(doc)
logging.info(
f"task {task.id} doc is minio path, bucket={bucket}, object={object_name}"
)
content_bytes = file_service.download_file(bucket, object_name)
return content_bytes.decode("utf-8", errors="replace")
return doc3.worker的处理
读redis队列，根据任务id找到这条task，但当文件任务doc字段还是"PENDING_FILE"时，做阻塞等待，直到doc字段更新为"minio://{bucket}/{object_name}"，从minio下载文件再处理，适配doc_llm_test_worker
新增阻塞等待函数
python
def wait_for_doc_ready(task_id: int):
"""
当 doc == "__PENDING_FILE__" 时，等待 doc 字段被控制面更新。
超过最大重试次数仍未更新则抛出异常。
"""
PENDING_RETRY_INTERVAL = 2
PENDING_RETRY_MAX = 5
for i in range(PENDING_RETRY_MAX):
time.sleep(PENDING_RETRY_INTERVAL)
task = task_service.get_task_by_id(task_id)
if not task:
raise RuntimeError(f"task {task_id} disappeared during pending wait")
doc = (task.doc or "").strip()
if doc != doc_loader.PENDING_MARK:
logging.info(f"task {task_id} doc is ready after {i+1} retries: {doc}")
return task
logging.info(f"task {task_id} doc still pending (retry {i+1}/{PENDING_RETRY_MAX})")
raise RuntimeError(f"task {task_id} doc still pending after max retries")适配文档处理函数process_task
python
def process_task(task_id: int):
"""处理文档检查任务"""
logging.info(f"start process task {task_id}")
...
try:
try:
doc_text = doc_loader.load_doc_for_task(task)
except doc_loader.DocPendingError as e:
logging.info(f"task {task_id} doc pending, waiting...")
try:
task = wait_for_doc_ready(task_id)
doc_text = doc_loader.load_doc_for_task(task)
except Exception as e2:
logging.error(f"task {task_id} pending wait failed: {e2}")
task_service.mark_task_failed(task_id, str(e2))
return
except doc_loader.DocPathError as e:
logging.error(f"task {task_id} invalid doc path: {e}")
task_service.mark_task_failed(task_id, str(e))
return测试效果：
数据库数据
&x-orig-expires=1765277283&x-orig-sign=Whtv5x93h9vggTE%2FW5awUqo5oyg%3D)
worker处理日志：
最终效果：
五、前端界面适配接口
补充文本上传的操作方式，适配
旧的文本输入方式：
新支持的文件输入方式