Base Service (trustgraph-base/trustgraph/base/embeddings_service.py):

- Changed on_request to use request.texts

FastEmbed Processor
(trustgraph-flow/trustgraph/embeddings/fastembed/processor.py):
- on_embeddings(texts, model=None) now processes full batch efficiently
- Returns [[v.tolist()] for v in vecs] - list of vector sets

Ollama Processor (trustgraph-flow/trustgraph/embeddings/ollama/processor.py):
- on_embeddings(texts, model=None) passes list directly to Ollama
- Returns [[embedding] for embedding in embeds.embeddings]

EmbeddingsClient (trustgraph-base/trustgraph/base/embeddings_client.py):
- embed(texts, timeout=300) accepts list of texts

Tests Updated:
- test_fastembed_dynamic_model.py - 4 tests updated for new interface
- test_ollama_dynamic_model.py - 4 tests updated for new interface

trustgraph-flow/trustgraph/embeddings/fastembed/processor.py

@@ -46,17 +46,22 @@ class Processor(EmbeddingsService):
         else:
             logger.debug(f"Using cached model: {model_name}")
 
-    async def on_embeddings(self, text, model=None):
+    async def on_embeddings(self, texts, model=None):
+
+        if not texts:
+            return []
 
         use_model = model or self.default_model
 
         # Reload model if it has changed
         self._load_model(use_model)
 
-        vecs = self.embeddings.embed([text])
+        # FastEmbed processes the full batch efficiently
+        vecs = list(self.embeddings.embed(texts))
 
+        # Return list of vector sets, one per input text
         return [
-            v.tolist()
+            [v.tolist()]
             for v in vecs
         ]
 

trustgraph-flow/trustgraph/embeddings/ollama/processor.py

@@ -30,16 +30,24 @@ class Processor(EmbeddingsService):
         self.client = Client(host=ollama)
         self.default_model = model
 
-    async def on_embeddings(self, text, model=None):
+    async def on_embeddings(self, texts, model=None):
+
+        if not texts:
+            return []
 
         use_model = model or self.default_model
 
+        # Ollama handles batch input efficiently
         embeds = self.client.embed(
             model = use_model,
-            input = text
+            input = texts
         )
 
-        return embeds.embeddings
+        # Return list of vector sets, one per input text
+        return [
+            [embedding]
+            for embedding in embeds.embeddings
+        ]
 
     @staticmethod
     def add_args(parser):