diff --git a/ai-service/app/api/admin/kb.py b/ai-service/app/api/admin/kb.py
index e150d72..e185e0e 100644
--- a/ai-service/app/api/admin/kb.py
+++ b/ai-service/app/api/admin/kb.py
@@ -442,13 +442,15 @@ async def _index_document(tenant_id: str, job_id: str, doc_id: str, content: byt
                 logger.info(f"[INDEX] Total chunks: {len(all_chunks)}")
 
             qdrant = await get_qdrant_client()
-            await qdrant.ensure_collection_exists(tenant_id)
+            await qdrant.ensure_collection_exists(tenant_id, use_multi_vector=True)
+
+            from app.services.embedding.nomic_provider import NomicEmbeddingProvider
+            use_multi_vector = isinstance(embedding_provider, NomicEmbeddingProvider)
+            logger.info(f"[INDEX] Using multi-vector format: {use_multi_vector}")
 
             points = []
             total_chunks = len(all_chunks)
             for i, chunk in enumerate(all_chunks):
-                embedding = await embedding_provider.embed(chunk.text)
-                
                 payload = {
                     "text": chunk.text,
                     "source": doc_id,
@@ -461,13 +463,26 @@ async def _index_document(tenant_id: str, job_id: str, doc_id: str, content: byt
                 if chunk.source:
                     payload["filename"] = chunk.source
                 
-                points.append(
-                    PointStruct(
-                        id=str(uuid.uuid4()),
-                        vector=embedding,
-                        payload=payload,
+                if use_multi_vector:
+                    embedding_result = await embedding_provider.embed_document(chunk.text)
+                    points.append({
+                        "id": str(uuid.uuid4()),
+                        "vector": {
+                            "full": embedding_result.embedding_full,
+                            "dim_256": embedding_result.embedding_256,
+                            "dim_512": embedding_result.embedding_512,
+                        },
+                        "payload": payload,
+                    })
+                else:
+                    embedding = await embedding_provider.embed(chunk.text)
+                    points.append(
+                        PointStruct(
+                            id=str(uuid.uuid4()),
+                            vector=embedding,
+                            payload=payload,
+                        )
                     )
-                )
                 
                 progress = 20 + int((i + 1) / total_chunks * 70)
                 if i % 10 == 0 or i == total_chunks - 1:
@@ -478,7 +493,10 @@ async def _index_document(tenant_id: str, job_id: str, doc_id: str, content: byt
 
             if points:
                 logger.info(f"[INDEX] Upserting {len(points)} vectors to Qdrant...")
-                await qdrant.upsert_vectors(tenant_id, points)
+                if use_multi_vector:
+                    await qdrant.upsert_multi_vector(tenant_id, points)
+                else:
+                    await qdrant.upsert_vectors(tenant_id, points)
 
             await kb_service.update_job_status(
                 tenant_id, job_id, IndexJobStatus.COMPLETED.value, progress=100