知识库文档解析报错：code=105000004 ，dense_text_content vector dim 1024 not match collection definition, which has dim of 2048

**Describe the bug**

A clear and concise description of what the bug is.
知识库中添加文件向量化失败,看起来.env的配置没有生效，在模型管理后台也配置了openai的bge-m3，但都没用

报错：
code=105000004 message=SearchStore operation failed: store search store failed, err: [Store] upsert failed, params column dense_text_content vector dim 1024 not match collection definition, which has dim of 2048

.env embedding配置：
export EMBEDDING_TYPE="openai"
export EMBEDDING_MAX_BATCH_SIZE=100

export ARK_EMBEDDING_BASE_URL="" # (string, required) Ark embedding base_url
export ARK_EMBEDDING_MODEL="" # (string, required) Ark embedding model
export ARK_EMBEDDING_API_KEY="" # (string, required) Ark embedding api_key
export ARK_EMBEDDING_DIMS="2048" # (int, required) Ark embedding dimensions
export ARK_EMBEDDING_API_TYPE="" # (string, optional) Ark embedding api type, should be "text_api" / "multi_modal_api". Default "text_api".

export OPENAI_EMBEDDING_BASE_URL="http://xxxx:8090/v1" # (string, required) OpenAI embedding base_url
export OPENAI_EMBEDDING_MODEL="bge-m3" # (string, required) OpenAI embedding model
export OPENAI_EMBEDDING_API_KEY="" # (string, required) OpenAI embedding api_key
export OPENAI_EMBEDDING_BY_AZURE=false # (bool, optional) OpenAI embedding by_azure
export OPENAI_EMBEDDING_API_VERSION="" # (string, optional) OpenAI embedding azure api version
export OPENAI_EMBEDDING_DIMS=1024 # (int, required) OpenAI embedding dimensions
export OPENAI_EMBEDDING_REQUEST_DIMS=1024 # (int, optional) OpenAI embedding dimensions in requests, need to be empty if api doesn't support specifying dimensions.

**To Reproduce**

Steps to reproduce the behavior:
1. Go to '...'
2. Click on '....'
3. Scroll down to '....'
4. See error

**Expected behavior**

A clear and concise description of what you expected to happen.

**Screenshots**

If applicable, add screenshots to help explain your problem.

**Version:**

Please provide the version of {project_name} you are using.

**Environment:**

The output of `go env`.

**Additional context**

Add any other context about the problem here.

Start by checking how the .env embedding settings are loaded and how the vector collection dimension is defined. Compare the configured/requested 1024-dimensional embedding with the collection's 2048-dimensional definition; done means file vectorization succeeds without the dimension-mismatch error.

Written by the indexing model from the issue text.