Batch embeddings (#668)

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

Updated CLI, SDK and APIs

tests/unit/test_embeddings/test_fastembed_dynamic_model.py

@@ -103,12 +103,12 @@ class TestFastEmbedDynamicModelLoading(IsolatedAsyncioTestCase):
         mock_text_embedding_class.reset_mock()
 
         # Act
-        result = await processor.on_embeddings("test text")
+        result = await processor.on_embeddings(["test text"])
 
         # Assert
         mock_fastembed_instance.embed.assert_called_once_with(["test text"])
         assert processor.cached_model_name == "test-model"  # Still using default
-        assert result == [[0.1, 0.2, 0.3, 0.4, 0.5]]
+        assert result == [[[0.1, 0.2, 0.3, 0.4, 0.5]]]
 
     @patch('trustgraph.embeddings.fastembed.processor.TextEmbedding')
     @patch('trustgraph.base.async_processor.AsyncProcessor.__init__')
@@ -126,7 +126,7 @@ class TestFastEmbedDynamicModelLoading(IsolatedAsyncioTestCase):
         mock_text_embedding_class.reset_mock()
 
         # Act
-        result = await processor.on_embeddings("test text", model="custom-model")
+        result = await processor.on_embeddings(["test text"], model="custom-model")
 
         # Assert
         mock_text_embedding_class.assert_called_once_with(model_name="custom-model")
@@ -149,16 +149,16 @@ class TestFastEmbedDynamicModelLoading(IsolatedAsyncioTestCase):
         initial_call_count = mock_text_embedding_class.call_count
 
         # Act - switch between models
-        await processor.on_embeddings("text1", model="model-a")
+        await processor.on_embeddings(["text1"], model="model-a")
         call_count_after_a = mock_text_embedding_class.call_count
 
-        await processor.on_embeddings("text2", model="model-a")  # Same, no reload
+        await processor.on_embeddings(["text2"], model="model-a")  # Same, no reload
         call_count_after_a_repeat = mock_text_embedding_class.call_count
 
-        await processor.on_embeddings("text3", model="model-b")  # Different, reload
+        await processor.on_embeddings(["text3"], model="model-b")  # Different, reload
         call_count_after_b = mock_text_embedding_class.call_count
 
-        await processor.on_embeddings("text4", model="model-a")  # Back to A, reload
+        await processor.on_embeddings(["text4"], model="model-a")  # Back to A, reload
         call_count_after_a_again = mock_text_embedding_class.call_count
 
         # Assert
@@ -183,7 +183,7 @@ class TestFastEmbedDynamicModelLoading(IsolatedAsyncioTestCase):
         initial_count = mock_text_embedding_class.call_count
 
         # Act
-        result = await processor.on_embeddings("test text", model=None)
+        result = await processor.on_embeddings(["test text"], model=None)
 
         # Assert
         # No reload, using cached default