Container image Copyright (c) 2016-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.

This container image and its contents are governed by the NVIDIA Deep Learning Container License.
By pulling and using the container, you accept the terms and conditions of this license:
https://developer.nvidia.com/ngc/nvidia-deep-learning-container-license

A copy of this license is made available in this container at /NGC-DL-CONTAINER-LICENSE for your convenience.

WARNING: The NVIDIA Driver was not detected.  GPU functionality will not be available.
   Use the NVIDIA Container Toolkit to start this container with GPU support; see
   https://docs.nvidia.com/datacenter/cloud-native/ .

*************************
** DEPRECATION NOTICE! **
*************************
THIS IMAGE IS DEPRECATED and is scheduled for DELETION.
    https://gitlab.com/nvidia/container-images/cuda/blob/master/doc/support-policy.md

2025-03-07 09:11:30 | DEBUG | c10d-NullHandler | Added handler to logger: c10d-NullHandler
2025-03-07 09:11:30 b02a346d6774 dbgpt.app.base[1] INFO Database dbgpt already exists
2025-03-07 09:11:30 b02a346d6774 dbgpt.component[1] INFO Register component with name dbgpt_unified_metadata_db_manager_factory and instance: <dbgpt.storage.metadata.db_factory.UnifiedDBManagerFactory object at 0x744c0fd6bcd0>
2025-03-07 09:11:32 b02a346d6774 dbgpt.component[1] INFO Register component with name dbgpt_thread_pool_default and instance: <dbgpt.util.executor_utils.DefaultExecutorFactory object at 0x744be6e27fa0>
2025-03-07 09:11:32 b02a346d6774 dbgpt.component[1] INFO Register component with name dbgpt_default_scheduler and instance: <dbgpt.app.initialization.scheduler.DefaultScheduler object at 0x744be6e320b0>
2025-03-07 09:11:32 b02a346d6774 dbgpt.component[1] INFO Register component with name dbgpt_model_controller and instance: <dbgpt.model.cluster.controller.controller.ModelControllerAdapter object at 0x744c3898fb20>
2025-03-07 09:11:32 b02a346d6774 dbgpt.component[1] INFO Register component with name dbgpt_connector_manager and instance: <dbgpt.datasource.manages.connector_manager.ConnectorManager object at 0x744be6e6d960>
2025-03-07 09:11:32 b02a346d6774 dbgpt.component[1] INFO Register component with name dbgpt_plugin_hub and instance: <dbgpt.serve.agent.hub.controller.ModulePlugin object at 0x744be6ec64d0>
2025-03-07 09:11:32 b02a346d6774 dbgpt.component[1] INFO Register component with name dbgpt_multi_agents and instance: <dbgpt.serve.agent.agents.controller.MultiAgents object at 0x744be7795540>
2025-03-07 09:11:32 b02a346d6774 dbgpt.app.initialization.embedding_component[1] INFO Register local LocalEmbeddingFactory
2025-03-07 09:11:32 b02a346d6774 dbgpt.model.adapter.embeddings_loader[1] INFO [EmbeddingsModelWorker] Parameters of device is None, use cpu
2025-03-07 09:11:32 b02a346d6774 dbgpt.app.initialization.embedding_component[1] INFO 

=========================== EmbeddingModelParameters ===========================

model_name: text2vec
model_path: /app/models/text2vec-large-chinese
device: cpu
normalize_embeddings: None
rerank: False
max_length: None

======================================================================


2025-03-07 09:11:33 b02a346d6774 datasets[1] INFO PyTorch version 2.2.1 available.
2025-03-07 09:11:33 b02a346d6774 datasets[1] INFO Duckdb version 1.1.3 available.
2025-03-07 09:11:33 b02a346d6774 sentence_transformers.SentenceTransformer[1] INFO Load pretrained SentenceTransformer: /app/models/text2vec-large-chinese


=========================== WebServerParameters ===========================

host: 0.0.0.0
port: 5670
daemon: False
log_level: INFO
log_file: dbgpt_webserver.log
tracer_file: dbgpt_webserver_tracer.jsonl
tracer_to_open_telemetry: False
otel_exporter_otlp_traces_endpoint: None
otel_exporter_otlp_traces_insecure: None
otel_exporter_otlp_traces_certificate: None
otel_exporter_otlp_traces_headers: None
otel_exporter_otlp_traces_timeout: None
otel_exporter_otlp_traces_compression: None
controller_addr: None
model_name: proxyllm
share: False
remote_embedding: False
remote_rerank: False
light: False
tracer_storage_cls: None
disable_alembic_upgrade: False
awel_dirs: None
default_thread_pool_size: None

======================================================================


Traceback (most recent call last):
  File "/app/dbgpt/app/dbgpt_server.py", line 289, in <module>
    run_webserver()
  File "/app/dbgpt/app/dbgpt_server.py", line 275, in run_webserver
    param = initialize_app(param)
  File "/app/dbgpt/app/dbgpt_server.py", line 171, in initialize_app
    initialize_components(
  File "/app/dbgpt/app/component_configs.py", line 51, in initialize_components
    _initialize_embedding_model(
  File "/app/dbgpt/app/initialization/embedding_component.py", line 32, in _initialize_embedding_model
    system_app.register(
  File "/app/dbgpt/component.py", line 195, in register
    instance = component(self, *args, **kwargs)
  File "/app/dbgpt/app/initialization/embedding_component.py", line 96, in __init__
    self._model = self._load_model()
  File "/app/dbgpt/app/initialization/embedding_component.py", line 131, in _load_model
    return loader.load(self._default_model_name, model_params)
  File "/app/dbgpt/model/adapter/embeddings_loader.py", line 84, in load
    return HuggingFaceEmbeddings(**kwargs)
  File "/app/dbgpt/rag/embedding/embeddings.py", line 93, in __init__
    kwargs["client"] = sentence_transformers.SentenceTransformer(
  File "/usr/local/lib/python3.10/dist-packages/sentence_transformers/SentenceTransformer.py", line 295, in __init__
    raise ValueError(f"Path {model_name_or_path} not found")
ValueError: Path /app/models/text2vec-large-chinese not found  这个报错怎么剞劂

报错内容如上，下面给出解决办法

        这个错误表明容器在启动时无法找到指定的模型路径 `/app/models/text2vec-large-chinese`。要解决这个问题，你可以按照以下步骤进行排查和修复：

### 1. 检查模型路径
确保模型文件确实存在于容器中的 `/app/models/text2vec-large-chinese` 路径下。你可以通过以下命令进入容器并检查路径：

```bash
docker exec -it <container_id> /bin/bash
ls /app/models/text2vec-large-chinese
```

如果路径不存在或模型文件缺失，你需要将模型文件放入正确的位置。

### 2. 挂载模型文件
如果你在本地有模型文件，可以通过挂载卷的方式将模型文件挂载到容器中的指定路径。例如：

```bash
docker run -v /path/to/your/local/models:/app/models <image_name>
```

这样，容器内的 `/app/models` 路径就会映射到你本地的模型文件路径。

### 3. 修改模型路径配置
如果模型文件不在 `/app/models/text2vec-large-chinese` 路径下，你可以修改配置文件或环境变量，指定正确的模型路径。具体方法取决于你的应用配置方式。

### 4. 下载模型文件
如果模型文件缺失，你可以尝试在容器启动时自动下载模型文件。你可以在启动脚本中添加下载模型的逻辑，例如：

```python
from sentence_transformers import SentenceTransformer

model = SentenceTransformer('text2vec-large-chinese')
model.save('/app/models/text2vec-large-chinese')
```

### 5. 检查 Dockerfile
如果你在构建自定义镜像，确保 Dockerfile 中有正确的指令将模型文件复制到容器中。例如：

```Dockerfile
COPY /path/to/your/local/models /app/models
```

### 6. 检查日志和配置文件
查看应用日志和配置文件，确认模型路径是否正确配置。如果有配置文件，检查是否有拼写错误或路径错误。

### 7. 重新构建镜像
如果你修改了 Dockerfile 或模型路径，记得重新构建镜像并重新启动容器：

```bash
docker build -t <image_name> .
docker run <image_name>
```

### 8. 检查容器启动命令
确保容器启动命令中没有覆盖或错误配置模型路径的环境变量或参数。