Implementation

trustgraph-base/trustgraph/api/flow.py

@@ -544,30 +544,29 @@ class FlowInstance:
             input
         )["response"]
 
-    def embeddings(self, text):
+    def embeddings(self, texts):
         """
-        Generate vector embeddings for text.
+        Generate vector embeddings for one or more texts.
 
-        Converts text into dense vector representations suitable for semantic
+        Converts texts into dense vector representations suitable for semantic
         search and similarity comparison.
 
         Args:
-            text: Input text to embed
+            texts: List of input texts to embed
 
         Returns:
-            list[float]: Vector embedding
+            list[list[list[float]]]: Vector embeddings, one set per input text
 
         Example:
             ```python
             flow = api.flow().id("default")
-            vectors = flow.embeddings("quantum computing")
-            print(f"Embedding dimension: {len(vectors)}")
+            vectors = flow.embeddings(["quantum computing"])
+            print(f"Embedding dimension: {len(vectors[0][0])}")
             ```
         """
 
-        # The input consists of a text block
         input = {
-            "text": text
+            "texts": texts
         }
 
         return self.request(

trustgraph-base/trustgraph/api/socket_client.py

@@ -712,27 +712,27 @@ class SocketFlowInstance:
 
         return self.client._send_request_sync("document-embeddings", self.flow_id, request, False)
 
-    def embeddings(self, text: str, **kwargs: Any) -> Dict[str, Any]:
+    def embeddings(self, texts: list, **kwargs: Any) -> Dict[str, Any]:
         """
-        Generate vector embeddings for text.
+        Generate vector embeddings for one or more texts.
 
         Args:
-            text: Input text to embed
+            texts: List of input texts to embed
             **kwargs: Additional parameters passed to the service
 
         Returns:
-            dict: Response containing vectors
+            dict: Response containing vectors (one set per input text)
 
         Example:
             ```python
             socket = api.socket()
             flow = socket.flow("default")
 
-            result = flow.embeddings("quantum computing")
+            result = flow.embeddings(["quantum computing"])
             vectors = result.get("vectors", [])
             ```
         """
-        request = {"text": text}
+        request = {"texts": texts}
         request.update(kwargs)
 
         return self.client._send_request_sync("embeddings", self.flow_id, request, False)

trustgraph-base/trustgraph/messaging/translators/embeddings.py

@@ -5,15 +5,15 @@ from .base import MessageTranslator
 
 class EmbeddingsRequestTranslator(MessageTranslator):
     """Translator for EmbeddingsRequest schema objects"""
-    
+
     def to_pulsar(self, data: Dict[str, Any]) -> EmbeddingsRequest:
         return EmbeddingsRequest(
-            text=data["text"]
+            texts=data["texts"]
         )
-    
+
     def from_pulsar(self, obj: EmbeddingsRequest) -> Dict[str, Any]:
         return {
-            "text": obj.text
+            "texts": obj.texts
         }