From 4fb602242de2939b1e55125d2db4ab0c588745cd Mon Sep 17 00:00:00 2001
From: Cyber MacGeddon <cybermaggedon@gmail.com>
Date: Wed, 12 Nov 2025 16:50:47 +0000
Subject: [PATCH] Fix nltk stuff

---
 .../extract/kg/ontology/ontology_embedder.py      | 15 +++++++++++----
 .../extract/kg/ontology/text_processor.py         | 11 +++++++++--
 2 files changed, 20 insertions(+), 6 deletions(-)

diff --git a/trustgraph-flow/trustgraph/extract/kg/ontology/ontology_embedder.py b/trustgraph-flow/trustgraph/extract/kg/ontology/ontology_embedder.py
index cbb0f0bf..4fdaaf7f 100644
--- a/trustgraph-flow/trustgraph/extract/kg/ontology/ontology_embedder.py
+++ b/trustgraph-flow/trustgraph/extract/kg/ontology/ontology_embedder.py
@@ -3,6 +3,7 @@ Ontology embedder component for OntoRAG system.
 Generates and stores embeddings for ontology elements.
 """
 
+import asyncio
 import logging
 import numpy as np
 from typing import Dict, List, Any, Optional
@@ -152,8 +153,12 @@ class OntologyEmbedder:
             # Get embeddings for batch
             texts = [elem['text'] for elem in batch]
             try:
-                # Call embedding service (async)
-                embeddings = await self.embedding_service.embed_batch(texts)
+                # Call embedding service for each text (EmbeddingsClient.embed() is single-text)
+                embedding_tasks = [self.embedding_service.embed(text) for text in texts]
+                embeddings_list = await asyncio.gather(*embedding_tasks)
+
+                # Convert to numpy array
+                embeddings = np.array(embeddings_list)
 
                 # Store in vector store
                 ids = [elem['id'] for elem in batch]
@@ -226,8 +231,10 @@ class OntologyEmbedder:
             return None
 
         try:
-            embeddings = await self.embedding_service.embed_batch(texts)
-            return embeddings
+            # EmbeddingsClient.embed() is single-text, so call in parallel
+            embedding_tasks = [self.embedding_service.embed(text) for text in texts]
+            embeddings_list = await asyncio.gather(*embedding_tasks)
+            return np.array(embeddings_list)
         except Exception as e:
             logger.error(f"Failed to embed texts: {e}")
             return None
diff --git a/trustgraph-flow/trustgraph/extract/kg/ontology/text_processor.py b/trustgraph-flow/trustgraph/extract/kg/ontology/text_processor.py
index b0231e3d..685699d1 100644
--- a/trustgraph-flow/trustgraph/extract/kg/ontology/text_processor.py
+++ b/trustgraph-flow/trustgraph/extract/kg/ontology/text_processor.py
@@ -26,9 +26,16 @@ except LookupError:
             pass
 
 try:
-    nltk.data.find('taggers/averaged_perceptron_tagger')
+    nltk.data.find('taggers/averaged_perceptron_tagger_eng')
 except LookupError:
-    nltk.download('averaged_perceptron_tagger', quiet=True)
+    try:
+        nltk.download('averaged_perceptron_tagger_eng', quiet=True)
+    except:
+        # Fallback to older name
+        try:
+            nltk.download('averaged_perceptron_tagger', quiet=True)
+        except:
+            pass
 
 try:
     nltk.data.find('corpora/stopwords')