change ksize in RAG

semantic_search/all_search_execute.py

@@ -401,7 +401,7 @@ def handler(input_,session_id):
     
     if(len(hybrid_payload["query"]["hybrid"]["queries"])==1):
         if(st.session_state.input_mvector_rerank and 'Vector Search' in search_types):
-            path = "retail-search-colbert-description/_search" 
+            path = "retail-search-colbert-description-reindex/_search" 
             url = host + path
             r = requests.get(url, auth=awsauth, json=hybrid_payload, headers=headers)
             response_ = json.loads(r.text)

utilities/mvectors.py

@@ -10,7 +10,7 @@ runtime = boto3.client('sagemaker-runtime',aws_access_key_id=st.secrets['user_ac
     aws_secret_access_key=st.secrets['user_secret_key'],region_name='us-east-1')
 # Load Tokenizer from HuggingFace Hub
 tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/all-MiniLM-L6-v2')
-endpoint_name = 'huggingface-pytorch-inference-2025-05-21-16-31-07-967'
+endpoint_name = 'all-MiniLM-L6-v2-model'
 
 
 def mean_pooling(token_embeddings, attention_mask):