diff --git a/build.gradle b/build.gradle
index fe060a4..384becd 100644
--- a/build.gradle
+++ b/build.gradle
@@ -44,7 +44,7 @@ dependencies {
     testImplementation 'org.jetbrains.kotlin:kotlin-test-junit5'
     testImplementation("org.mockito.kotlin:mockito-kotlin:5.3.1")
     testRuntimeOnly 'org.junit.platform:junit-platform-launcher'
-    runtimeOnly 'org.postgresql:postgresql'
+    implementation 'org.postgresql:postgresql'   // ← 변경
     testRuntimeOnly("com.h2database:h2")
 
     // swagger
@@ -53,6 +53,9 @@ dependencies {
     // s3
     implementation(platform("software.amazon.awssdk:bom:2.25.70"))
     implementation("software.amazon.awssdk:s3")
+
+    // pgvector
+    implementation("com.pgvector:pgvector:0.1.6")
 }
 
 dependencyManagement {
diff --git a/src/main/kotlin/simplerag/ragback/domain/index/entity/ChunkEmbedding.kt b/src/main/kotlin/simplerag/ragback/domain/index/entity/ChunkEmbedding.kt
index 127770b..464f227 100644
--- a/src/main/kotlin/simplerag/ragback/domain/index/entity/ChunkEmbedding.kt
+++ b/src/main/kotlin/simplerag/ragback/domain/index/entity/ChunkEmbedding.kt
@@ -1,8 +1,8 @@
 package simplerag.ragback.domain.index.entity
 
+import com.pgvector.PGvector
 import jakarta.persistence.*
 import simplerag.ragback.global.entity.BaseEntity
-import simplerag.ragback.global.util.FloatArrayToPgVectorStringConverter
 
 // 임베딩 크기를 서비스단에서 검증을 해줘야함
 @Entity
@@ -13,9 +13,8 @@ class ChunkEmbedding(
     @Lob
     val content: String,
 
-    @Convert(converter = FloatArrayToPgVectorStringConverter::class)
-    @Column(name = "embedding", nullable = false)
-    private var _embedding: FloatArray,
+    @Column(name = "embedding", columnDefinition = "vector")
+    var embedding: PGvector,
 
     @Column(name = "embedding_dim", nullable = false)
     val embeddingDim: Int,
@@ -27,16 +26,4 @@ class ChunkEmbedding(
     @Id @GeneratedValue(strategy = GenerationType.IDENTITY)
     @Column(name = "chunk_embeddings_id")
     val id: Long? = null,
-) : BaseEntity() {
-
-    @get:Transient
-    val embedding: FloatArray get() = _embedding.copyOf()
-
-    fun updateEmbedding(newVec: FloatArray) {
-        require(newVec.size == embeddingDim) {
-            "Embedding dimension mismatch: expected=$embeddingDim, got=${newVec.size}"
-        }
-        _embedding = newVec.copyOf()
-    }
-
-}
\ No newline at end of file
+) : BaseEntity()
\ No newline at end of file
diff --git a/src/main/kotlin/simplerag/ragback/domain/index/entity/enums/EmbeddingModel.kt b/src/main/kotlin/simplerag/ragback/domain/index/entity/enums/EmbeddingModel.kt
index 6729034..a7bcda4 100644
--- a/src/main/kotlin/simplerag/ragback/domain/index/entity/enums/EmbeddingModel.kt
+++ b/src/main/kotlin/simplerag/ragback/domain/index/entity/enums/EmbeddingModel.kt
@@ -6,36 +6,21 @@ enum class EmbeddingModel(
 ) {
     // OpenAI
     TEXT_EMBEDDING_3_SMALL(1536, "text-embedding-3-small"),
-    TEXT_EMBEDDING_3_LARGE(3072, "text-embedding-3-large"),
 
     // SBERT / HuggingFace
     ALL_MINILM_L6_V2(384, "sentence-transformers/all-MiniLM-L6-v2"),
     ALL_MP_NET_BASE_V2(768, "sentence-transformers/all-mpnet-base-v2"),
-    MULTI_QA_MP_NET_BASE_DOT_V1(768, "sentence-transformers/multi-qa-mpnet-base-dot-v1"),
     DISTILUSE_BASE_MULTILINGUAL_CASED_V2(512, "sentence-transformers/distiluse-base-multilingual-cased-v2"),
-    PARAPHRASE_MULTILINGUAL_MINILM_L12_V2(384, "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"),
-    KO_SBERT_V1(768, "jhgan/ko-sbert-v1"),
-    KOR_SROBERTA(768, "jhgan/ko-sroberta-medium-nli"),
-
-    // Korean specific
-    BM_KO_SMALL(512, "bespin-global/klue-sroberta-base-continue-learning-by-mnr"),
 
-    // Instructor / Mistral
-    INSTRUCTOR_BASE(768, "hkunlp/instructor-base"),
-    INSTRUCTOR_XL(1024, "hkunlp/instructor-xl"),
-    MISTRAL_EMBED(1024, "mistral-embed"),
+    // Korean
+    KO_SBERT_V1(768, "jhgan/ko-sbert-v1"),
 
-    // BGE / E5 etc
-    BGE_SMALL_EN(384, "BAAI/bge-small-en-v1.5"),
+    // BGE
     BGE_BASE_EN(768, "BAAI/bge-base-en-v1.5"),
-    BGE_LARGE_EN(1024, "BAAI/bge-large-en-v1.5"),
     BGE_M3(1024, "BAAI/bge-m3"),
-    E5_SMALL(384, "intfloat/e5-small-v2"),
-    E5_BASE(768, "intfloat/e5-base-v2"),
-    E5_LARGE(1024, "intfloat/e5-large-v2"),
 
-    // Old word vectors
-    FASTTEXT_KO(300, "fasttext-ko-300d");
+    // E5
+    E5_BASE(768, "intfloat/e5-base-v2");
 
     companion object {
         fun findByModelId(modelId: String): EmbeddingModel? {
diff --git a/src/main/kotlin/simplerag/ragback/global/util/FloatArrayToPgVectorStringConverter.kt b/src/main/kotlin/simplerag/ragback/global/util/FloatArrayToPgVectorStringConverter.kt
deleted file mode 100644
index 04e1d23..0000000
--- a/src/main/kotlin/simplerag/ragback/global/util/FloatArrayToPgVectorStringConverter.kt
+++ /dev/null
@@ -1,34 +0,0 @@
-package simplerag.ragback.global.util
-
-import jakarta.persistence.AttributeConverter
-import jakarta.persistence.Converter
-
-@Converter(autoApply = false)
-class FloatArrayToPgVectorStringConverter : AttributeConverter<FloatArray, String> {
-    override fun convertToDatabaseColumn(attribute: FloatArray?): String {
-        requireNotNull(attribute) { "Embedding (FloatArray) must not be null" }
-        require(attribute.isNotEmpty()) { "Embedding must not be empty; expected fixed dimension (e.g., 1536)" }
-        require(attribute.all { !it.isNaN() && !it.isInfinite() }) {
-            "Embedding must not contain NaN/Infinity"
-        }
-        return attribute.joinToString(prefix = "[", postfix = "]", separator = ",") { it.toString() }
-    }
-
-    override fun convertToEntityAttribute(dbData: String?): FloatArray {
-        if (dbData.isNullOrBlank()) return floatArrayOf()
-        val body = dbData.trim().removePrefix("[").removeSuffix("]").trim()
-        if (body.isBlank()) return floatArrayOf()
-        return try {
-            body.split(',')
-                .map { it.trim().toFloat() }
-                .toFloatArray()
-                .also { arr ->
-                    require(arr.all { it.isFinite() }) {
-                        "Embedding must not contain NaN/Infinity (db → entity)"
-                    }
-                }
-        } catch (e: NumberFormatException) {
-            throw IllegalArgumentException("Invalid vector literal for pgvector: '$dbData'", e)
-        }
-    }
-}
\ No newline at end of file