Update utils/ingestion.py

utils/ingestion.py

@@ -96,16 +96,22 @@ class DocumentProcessor:
         ids = []
 
         for idx, chunk in enumerate(processed_chunks):
-            embedding = self.embed_model.encode(chunk['text'])
-            documents.append(chunk['text'])
+            text = chunk.get('text', '').strip()
+            if not text:
+                print(f"Skipping empty chunk at index {idx}")
+                continue  # Skip empty chunks
+
+            embedding = self.embed_model.embed_documents([text])[0]  # ✅ Correct method
+            documents.append(text)
             embeddings.append(embedding)
             metadata_list.append({
-                "headings": json.dumps(chunk['headings']),
-                "page": chunk['page_info'],
-                "content_type": chunk['content_type']
+                "headings": json.dumps(chunk.get('headings', [])),
+                "page": chunk.get('page_info', None),
+                "content_type": chunk.get('content_type', None)
             })
             ids.append(str(idx))
 
+
         collection.add(
             ids=ids,
             embeddings=embeddings,