revise the embed method

docs/en/notes/guide/selector/selector_offline_near.md

@@ -53,10 +53,13 @@ if __name__ == "__main__":
     near = offline_near_Selector(
         candidate_path="OpenDCAI/DataFlex-selector-openhermes-10w", # split = train
         query_path="OpenDCAI/DataFlex-selector-openhermes-10w", # split = vaildation
-
-        # If you want to use vllm,please add "vllm:" before model's name
-        # Otherwise it automatically use sentence-transfromer
-        embed_model="vllm:Qwen/Qwen3-Embedding-0.6B",
+        # It automatically try vllm first, then sentence-transformers
+        embed_model="Qwen/Qwen3-Embedding-0.6B",
+        # support method:
+        #auto(It automatically try vllm first, then sentence-transformers),
+        #vllm,
+        #sentence-transformer
+        embed_method= "auto",
         batch_size=32,
         save_indices_path="top_indices.npy",
         max_K=1000,
@@ -65,7 +68,7 @@ if __name__ == "__main__":
     near.selector()
 ```
 
-Note: model_name is used to encode the already-tokenized text into sentence embeddings (e.g., 512-dim), supporting both vLLM and sentence-transformer inference.
+Note: model_name is used to encode the already-tokenized text into sentence embeddings (e.g., 1024-dim), supporting both vLLM and sentence-transformer inference.
 
 Output: save as the indices matrix that contain the max_K close data for each query
 ---

docs/en/notes/guide/selector/selector_offline_tsds.md

@@ -77,12 +77,14 @@ Modify training set, embedding model, and parameters inside
 ```python
 if __name__ == "__main__":
     tsds = offline_tsds_Selector(
-        candidate_path="OpenDCAI/DataFlex-selector-openhermes-10w", # training set
-        query_path="OpenDCAI/DataFlex-selector-openhermes-10w",     # validation set
-
-        # If you want to use vllm, please add "vllm:" before the model name
-        # Otherwise it automatically uses sentence-transformer
-        embed_model="vllm:Qwen/Qwen3-Embedding-0.6B", # embedding model
+        candidate_path="OpenDCAI/DataFlex-selector-openhermes-10w",
+        query_path="OpenDCAI/DataFlex-selector-openhermes-10w",
+        embed_model="Qwen/Qwen3-Embedding-0.6B",
+        # support method:
+        #auto(It automatically try vllm first, then sentence-transformers),
+        #vllm,
+        #sentence-transformer
+        embed_method="auto",
         batch_size=32,
         save_probs_path="tsds_probs.npy",
         max_K=5000,
@@ -94,7 +96,7 @@ if __name__ == "__main__":
     tsds.selector()
 ```
 
-Note: model_name is used to encode the already-tokenized text into sentence embeddings (e.g., 512-dim), supporting both vLLM and sentence-transformer inference.
+Note: model_name is used to encode the already-tokenized text into sentence embeddings (e.g., 1024-dim), supporting both vLLM and sentence-transformer inference.
 
 Output: a sampling probability for each training sample.
 ---

docs/zh/notes/guide/selector/selector_offline_near.md

@@ -48,10 +48,13 @@ if __name__ == "__main__":
     near = offline_near_Selector(
         candidate_path="OpenDCAI/DataFlex-selector-openhermes-10w", # split = train
         query_path="OpenDCAI/DataFlex-selector-openhermes-10w", # split = vaildation
-
-        # If you want to use vllm,please add "vllm:" before model's name
-        # Otherwise it automatically use sentence-transfromer
-        embed_model="vllm:Qwen/Qwen3-Embedding-0.6B",
+        # It automatically try vllm first, then sentence-transformers
+        embed_model="Qwen/Qwen3-Embedding-0.6B",
+        # support method:
+        #auto(It automatically try vllm first, then sentence-transformers),
+        #vllm,
+        #sentence-transformer
+        embed_method= "auto",
         batch_size=32,
         save_indices_path="top_indices.npy",
         max_K=1000,
@@ -61,7 +64,7 @@ if __name__ == "__main__":
 
 ```
 
-> **注意**：此处的 `model_name` 用于将**tokenized**后的文本进一步编码为**句向量**（例如 512 维），支持vllm和sentence-transformer 推理。
+> **注意**：此处的 `model_name` 用于将**tokenized**后的文本进一步编码为**句向量**（例如 1024 维），支持vllm和sentence-transformer 推理。
 
 **最终保存为每个query的max_K个最邻近训练数据的索引矩阵 （ N ,max_K ）**
 

docs/zh/notes/guide/selector/selector_offline_tsds.md

@@ -76,12 +76,14 @@ pip install faiss-cpu vllm sentence-transformer
 ```python
 if __name__ == "__main__":
     tsds = offline_tsds_Selector(
-        candidate_path="OpenDCAI/DataFlex-selector-openhermes-10w",#训练集
-        query_path="OpenDCAI/DataFlex-selector-openhermes-10w",#验证集
-
-        # If you want to use vllm,please add "vllm:" before model's name
-        # Otherwise it automatically use sentence-transfromer
-        embed_model="vllm:Qwen/Qwen3-Embedding-0.6B",#编码模型
+        candidate_path="OpenDCAI/DataFlex-selector-openhermes-10w",
+        query_path="OpenDCAI/DataFlex-selector-openhermes-10w",
+        embed_model="Qwen/Qwen3-Embedding-0.6B",
+        # support method:
+        #auto(It automatically try vllm first, then sentence-transformers),
+        #vllm,
+        #sentence-transformer
+        embed_method="auto",
         batch_size=32,
         save_probs_path="tsds_probs.npy",
         max_K=5000,
@@ -94,7 +96,7 @@ if __name__ == "__main__":
 
 ```
 
-> **注意**：此处的 `model_name` 用于将**tokenized**后的文本进一步编码为**句向量**（例如 512 维），支持vllm和sentence-transformer 推理。
+> **注意**：此处的 `model_name` 用于将**tokenized**后的文本进一步编码为**句向量**（例如 1024 维），支持vllm和sentence-transformer 推理。
 
 **最终保存为每个训练样本的采样概率**