diff --git a/llm-modules/local-embedding/src/main/kotlin/cc/unitmesh/cf/LocalEmbedding.kt b/llm-modules/local-embedding/src/main/kotlin/cc/unitmesh/cf/LocalEmbedding.kt
index b67df7b..b94d3fd 100644
--- a/llm-modules/local-embedding/src/main/kotlin/cc/unitmesh/cf/LocalEmbedding.kt
+++ b/llm-modules/local-embedding/src/main/kotlin/cc/unitmesh/cf/LocalEmbedding.kt
@@ -68,7 +68,7 @@ open class LocalEmbedding(
 
     companion object {
         /**
-         * Create a new instance of [STEmbedding] with default model.
+         * Create a new instance of [LocalEmbedding] with default model.
          * We use official model: [all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2)
          * We can use [optimum](https://github.com/huggingface/optimum) to transform the model to onnx.
          */
diff --git a/llm-modules/local-embedding/src/main/kotlin/cc/unitmesh/cf/STEmbedding.kt b/llm-modules/local-embedding/src/main/kotlin/cc/unitmesh/cf/STEmbedding.kt
deleted file mode 100644
index b8a2d20..0000000
--- a/llm-modules/local-embedding/src/main/kotlin/cc/unitmesh/cf/STEmbedding.kt
+++ /dev/null
@@ -1,19 +0,0 @@
-package cc.unitmesh.cf
-
-import ai.djl.huggingface.tokenizers.HuggingFaceTokenizer
-import ai.onnxruntime.OrtEnvironment
-import ai.onnxruntime.OrtSession
-
-@Deprecated("Use LocalEmbedding instead")
-class STEmbedding(
-    private val tokenizer: HuggingFaceTokenizer,
-    private val session: OrtSession,
-    private val env: OrtEnvironment,
-) : LocalEmbedding(tokenizer, session, env) {
-
-    companion object {
-        fun create(): LocalEmbedding {
-            return LocalEmbedding.create()
-        }
-    }
-}
diff --git a/server/src/test/kotlin/RagIntegrationTests.kt b/server/src/test/kotlin/RagIntegrationTests.kt
index 7de3c8b..fbd0a4c 100644
--- a/server/src/test/kotlin/RagIntegrationTests.kt
+++ b/server/src/test/kotlin/RagIntegrationTests.kt
@@ -1,5 +1,4 @@
 import cc.unitmesh.cf.LocalEmbedding
-import cc.unitmesh.cf.STEmbedding
 import cc.unitmesh.cf.infrastructure.llms.embedding.SentenceTransformersEmbedding
 import cc.unitmesh.nlp.embedding.Embedding
 import cc.unitmesh.rag.document.Document