mirror of
https://github.com/opendatalab/MinerU.git
synced 2026-03-27 02:58:54 +07:00
feat: add MinerU configuration options for vlm/hybrid backend
This commit is contained in:
@@ -125,3 +125,9 @@ Here are the environment variables and their descriptions:
|
||||
- `MINERU_HYBRID_FORCE_PIPELINE_ENABLE`:
|
||||
* Used to force the text extraction part in `hybrid-*` backends to be processed using small models.
|
||||
* Defaults to `false`. Can be set to `true` via environment variable to enable this feature, thereby reducing hallucinations in certain extreme cases.
|
||||
|
||||
- `MINERU_VL_MODEL_NAME`:
|
||||
* Used to specify the model name for the vlm/hybrid backend, allowing you to designate the model required for MinerU to run when multiple models exist on a remote openai-server.
|
||||
|
||||
- `MINERU_VL_API_KEY`:
|
||||
* Used to specify the API Key for the vlm/hybrid backend, enabling authentication on the remote openai-server.
|
||||
|
||||
@@ -119,4 +119,10 @@ MinerU命令行工具的某些参数存在相同功能的环境变量配置,
|
||||
|
||||
- `MINERU_HYBRID_FORCE_PIPELINE_ENABLE`:
|
||||
* 用于强制将 hybrid-* 后端中的 文本提取部分使用 小模型 进行处理
|
||||
* 默认为`false`,可通过环境变量设置为`true`来启用该功能,从而在某些极端情况下减少幻觉的发生。
|
||||
* 默认为`false`,可通过环境变量设置为`true`来启用该功能,从而在某些极端情况下减少幻觉的发生。
|
||||
|
||||
- `MINERU_VL_MODEL_NAME`:
|
||||
* 用于指定 vlm/hybrid 后端使用的模型名称,这将允许您在同时存在多个模型的远程openai-server中指定 MinerU 运行所需的模型。
|
||||
|
||||
- `MINERU_VL_API_KEY`:
|
||||
* 用于指定 vlm/hybrid 后端使用的API Key,这将允许您在远程openai-server中进行身份验证。
|
||||
Reference in New Issue
Block a user