Update agent.py

agent.py

@@ -138,16 +138,14 @@ sentence_transformer.max_seq_length = 512  # Set max sequence length
 # Initialize embeddings with the model name (dim=768)
 embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
 
+#from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer("sentence-transformers/all-mpnet-base-v2")
+query = "What is vector search?"
+query_embedding = model.encode(query)
+
+print("Embedding Length:", len(query_embedding))  # Ensure it's 768
 
-try:
-    results = retriever.get_relevant_documents("What is vector search?")
-    if not results:
-        raise ValueError("No documents found in the search results.")
-    # Access the first result safely if it exists
-    first_result = results[0]
-    print("First result:", first_result)
-except Exception as e:
-    print(f"Error: {e}")