diff --git a/trustgraph-flow/trustgraph/agent/react/tools.py b/trustgraph-flow/trustgraph/agent/react/tools.py
index 18675084..71fe7409 100644
--- a/trustgraph-flow/trustgraph/agent/react/tools.py
+++ b/trustgraph-flow/trustgraph/agent/react/tools.py
@@ -154,7 +154,8 @@ class RowEmbeddingsQueryImpl:
         logger.debug("Getting embeddings for row query...")
 
         query_text = arguments.get("query")
-        vectors = await embeddings_client.embed(query_text)
+        all_vectors = await embeddings_client.embed([query_text])
+        vectors = all_vectors[0] if all_vectors else []
 
         # Now query row embeddings
         client = self.context("row-embeddings-query-request")
diff --git a/trustgraph-flow/trustgraph/extract/kg/ontology/extract.py b/trustgraph-flow/trustgraph/extract/kg/ontology/extract.py
index a0d9a3fe..11767d0b 100644
--- a/trustgraph-flow/trustgraph/extract/kg/ontology/extract.py
+++ b/trustgraph-flow/trustgraph/extract/kg/ontology/extract.py
@@ -148,8 +148,8 @@ class Processor(FlowProcessor):
 
             # Detect embedding dimension by embedding a test string
             logger.info("Detecting embedding dimension from embeddings service...")
-            test_embedding_response = await embeddings_client.embed("test")
-            test_embedding = test_embedding_response[0]  # Extract from [[vector]]
+            test_embedding_response = await embeddings_client.embed(["test"])
+            test_embedding = test_embedding_response[0][0]  # Extract first vector from first text
             dimension = len(test_embedding)
             logger.info(f"Detected embedding dimension: {dimension}")
 
diff --git a/trustgraph-flow/trustgraph/extract/kg/ontology/ontology_embedder.py b/trustgraph-flow/trustgraph/extract/kg/ontology/ontology_embedder.py
index 8eee76b4..4bff6551 100644
--- a/trustgraph-flow/trustgraph/extract/kg/ontology/ontology_embedder.py
+++ b/trustgraph-flow/trustgraph/extract/kg/ontology/ontology_embedder.py
@@ -153,13 +153,11 @@ class OntologyEmbedder:
             # Get embeddings for batch
             texts = [elem['text'] for elem in batch]
             try:
-                # Call embedding service for each text
-                # Note: embed() returns 2D array [[vector]], so extract first element
-                embedding_tasks = [self.embedding_service.embed(text) for text in texts]
-                embeddings_responses = await asyncio.gather(*embedding_tasks)
+                # Single batch embedding call
+                embeddings_response = await self.embedding_service.embed(texts)
 
-                # Extract vectors from responses (each is [[vector]])
-                embeddings_list = [resp[0] for resp in embeddings_responses]
+                # Extract first vector from each text's vector set
+                embeddings_list = [resp[0] for resp in embeddings_response]
 
                 # Convert to numpy array
                 embeddings = np.array(embeddings_list)
@@ -218,9 +216,9 @@ class OntologyEmbedder:
             return None
 
         try:
-            # embed() returns 2D array [[vector]], extract first element
-            embedding_response = await self.embedding_service.embed(text)
-            return np.array(embedding_response[0])
+            # embed() with single text, extract first vector from first text
+            embedding_response = await self.embedding_service.embed([text])
+            return np.array(embedding_response[0][0])
         except Exception as e:
             logger.error(f"Failed to embed text: {e}")
             return None
@@ -239,11 +237,10 @@ class OntologyEmbedder:
             return None
 
         try:
-            # Call embed() for each text (returns [[vector]] per call)
-            embedding_tasks = [self.embedding_service.embed(text) for text in texts]
-            embeddings_responses = await asyncio.gather(*embedding_tasks)
-            # Extract first vector from each response
-            embeddings_list = [resp[0] for resp in embeddings_responses]
+            # Single batch embedding call
+            embeddings_response = await self.embedding_service.embed(texts)
+            # Extract first vector from each text's vector set
+            embeddings_list = [resp[0] for resp in embeddings_response]
             return np.array(embeddings_list)
         except Exception as e:
             logger.error(f"Failed to embed texts: {e}")
diff --git a/trustgraph-flow/trustgraph/retrieval/document_rag/document_rag.py b/trustgraph-flow/trustgraph/retrieval/document_rag/document_rag.py
index f192bcf3..6402010a 100644
--- a/trustgraph-flow/trustgraph/retrieval/document_rag/document_rag.py
+++ b/trustgraph-flow/trustgraph/retrieval/document_rag/document_rag.py
@@ -24,12 +24,13 @@ class Query:
         if self.verbose:
             logger.debug("Computing embeddings...")
 
-        qembeds = await self.rag.embeddings_client.embed(query)
+        qembeds = await self.rag.embeddings_client.embed([query])
 
         if self.verbose:
             logger.debug("Embeddings computed")
 
-        return qembeds
+        # Return the vector set for the first (only) text
+        return qembeds[0] if qembeds else []
 
     async def get_docs(self, query):
 
diff --git a/trustgraph-flow/trustgraph/retrieval/graph_rag/graph_rag.py b/trustgraph-flow/trustgraph/retrieval/graph_rag/graph_rag.py
index 7ccba248..21d5aed1 100644
--- a/trustgraph-flow/trustgraph/retrieval/graph_rag/graph_rag.py
+++ b/trustgraph-flow/trustgraph/retrieval/graph_rag/graph_rag.py
@@ -72,12 +72,13 @@ class Query:
         if self.verbose:
             logger.debug("Computing embeddings...")
 
-        qembeds = await  self.rag.embeddings_client.embed(query)
+        qembeds = await self.rag.embeddings_client.embed([query])
 
         if self.verbose:
             logger.debug("Done.")
 
-        return qembeds
+        # Return the vector set for the first (only) text
+        return qembeds[0] if qembeds else []
 
     async def get_entities(self, query):