64 lines
5.0 KiB
Plaintext
64 lines
5.0 KiB
Plaintext
nohup: ignoring input
|
||
INFO:__main__:🚀 启动时自动初始化VDB多模态检索系统...
|
||
INFO:multimodal_retrieval_vdb:检测到 2 个GPU
|
||
INFO:multimodal_retrieval_vdb:使用GPU: [0, 1], 主设备: cuda:0
|
||
INFO:multimodal_retrieval_vdb:GPU内存已清理
|
||
INFO:multimodal_retrieval_vdb:正在加载模型到GPU: [0, 1]
|
||
INFO:multimodal_retrieval_vdb:GPU内存已清理
|
||
🚀 启动VDB多模态检索Web应用
|
||
============================================================
|
||
访问地址: http://localhost:5000
|
||
新功能:
|
||
🗄️ 百度VDB - 向量数据库存储
|
||
📊 实时统计 - VDB数据统计信息
|
||
🔄 数据同步 - 本地文件到VDB存储
|
||
支持功能:
|
||
📝 文搜文 - 文本查找相似文本
|
||
🖼️ 文搜图 - 文本查找相关图片
|
||
📝 图搜文 - 图片查找相关文本
|
||
🖼️ 图搜图 - 图片查找相似图片
|
||
📤 批量上传 - 图片和文本数据管理
|
||
GPU配置:
|
||
🖥️ 检测到 2 个GPU
|
||
GPU 0: NVIDIA GeForce RTX 4090 (23.6GB)
|
||
GPU 1: NVIDIA GeForce RTX 4090 (23.6GB)
|
||
VDB配置:
|
||
🌐 服务器: http://180.76.96.191:5287
|
||
👤 用户: root
|
||
🗄️ 数据库: multimodal_retrieval
|
||
============================================================
|
||
|
||
Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s]
|
||
Loading checkpoint shards: 25%|██▌ | 1/4 [03:18<09:56, 198.90s/it]
|
||
Loading checkpoint shards: 25%|██▌ | 1/4 [03:25<10:15, 205.19s/it]
|
||
WARNING:multimodal_retrieval_vdb:网络加载失败，尝试本地缓存: CUDA out of memory. Tried to allocate 130.00 MiB. GPU 0 has a total capacity of 23.64 GiB of which 117.00 MiB is free. Process 3982470 has 384.00 MiB memory in use. Process 729183 has 2.64 GiB memory in use. Process 726298 has 7.43 GiB memory in use. Process 726164 WARNING:multimodal_retrieval_vdb:Tokenizer网络加载失败，尝试本地: (MaxRetryError("HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /api/models/OpenSearch-AI/Ops-MM-embedding-v1-7B/tree/main/additional_chat_templates?recursive=False&expand=False (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f92386b4280>: Failed to establish a new connection: [Errno 101] Network is unreachable'))"), '(Request ID: 103ac836-6599-4fe2-a569-aed9c945525c)')
|
||
The image processor of type `Qwen2VLImageProcessor` is now loaded as a fast processor by default, even if the model checkpoint was saved with a slow processor. This is a breaking change and may produce slightly different outputs. To continue using the slow processor, instantiate this class with `use_fast=False`. Note that this behavior will be extended to all models in a future release.
|
||
WARNING:multimodal_retrieval_vdb:Processor加载失败，使用tokenizer: (MaxRetryError("HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /api/models/OpenSearch-AI/Ops-MM-embedding-v1-7B/tree/main/additional_chat_templates?recursive=False&expand=False (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7fbad64d1510>: Failed to establish a new connection: [Errno 101] Network is unreachable'))"), '(Request ID: 96f18121-7beb-4e1a-87cd-c50edf682933)')
|
||
You have video processor config saved in `preprocessor.json` file which is deprecated. Video processor configs should be saved in their own `video_preprocessor.json` file. You can rename the file or load and save the processor back which renames it automatically. Loading from `preprocessor.json` will be removed in v5.0.
|
||
INFO:multimodal_retrieval_vdb:模型加载完成
|
||
INFO:baidu_vdb_backend:✅ 成功连接到百度VDB: http://180.76.96.191:5287
|
||
INFO:baidu_vdb_backend:使用现有数据库: multimodal_retrieval
|
||
INFO:baidu_vdb_backend:创建文本向量表: text_vectors
|
||
ERROR:baidu_vdb_backend:❌ 创建文本表失败: Database.create_table() missing 1 required positional argument: 'partition'
|
||
ERROR:baidu_vdb_backend:❌ 表操作失败: Database.create_table() missing 1 required positional argument: 'partition'
|
||
ERROR:multimodal_retrieval_vdb:❌ VDB后端初始化失败: Database.create_table() missing 1 required positional argument: 'partition'
|
||
WARNING:multimodal_retrieval_vdb:⚠️ 系统将在无VDB模式下运行，数据将不会持久化
|
||
INFO:multimodal_retrieval_vdb:多模态检索系统初始化完成
|
||
ERROR:__main__:❌ VDB系统自动初始化失败: VDB连接失败
|
||
ERROR:__main__:Traceback (most recent call last):
|
||
File "/root/mmeb/web_app_vdb.py", line 667, in auto_initialize
|
||
raise Exception("VDB连接失败")
|
||
Exception: VDB连接失败
|
||
|
||
* Serving Flask app 'web_app_vdb'
|
||
* Debug mode: off
|
||
Address already in use
|
||
Port 5000 is in use by another program. Either identify and stop that program, or start the server with a different port.
|
||
<EFBFBD><EFBFBD>败
|
||
ERROR:__main__:Traceback (most recent call last):
|
||
File "/root/mmeb/web_app_vdb.py", line 664, in auto_initialize
|
||
raise Exception("模型加载失败")
|
||
Exception: 模型加载失败
|
||
|
||
* Serving Flask app 'web_app_vdb'
|
||
* Debug mode: off
|
||
Address already in use
|
||
Port 5000 is in use by another program. Either identify and stop that program, or start the server with a different port.
|