diff --git a/app/docker-compose.yml b/app/docker-compose.yml
index fb7640a..76a4bbc 100644
--- a/app/docker-compose.yml
+++ b/app/docker-compose.yml
@@ -7,4 +7,4 @@ services:
     ports:
       - "8501:8501"
     volumes:
-      - ./llmops/src/rag_cot/chroma_db:/app/llmops/src/rag_cot/chroma_db
+      - ./llmops/src/rag_cot_evaluation/chroma_db:/app/llmops/src/rag_cot_evaluation/chroma_db
diff --git a/app/llmops/components/test_rag_cot/run.py b/app/llmops/components/test_rag_cot/run.py
index b18e6aa..6e404a3 100644
--- a/app/llmops/components/test_rag_cot/run.py
+++ b/app/llmops/components/test_rag_cot/run.py
@@ -11,6 +11,7 @@ from langchain_deepseek import ChatDeepSeek
 from langchain_community.llms.moonshot import Moonshot
 import sys
 
+
 logging.basicConfig(level=logging.INFO, format="%(asctime)-15s %(message)s")
 logger = logging.getLogger()
 
diff --git a/app/llmops/main.py b/app/llmops/main.py
index 670a7fa..4bd19ce 100644
--- a/app/llmops/main.py
+++ b/app/llmops/main.py
@@ -8,7 +8,8 @@ _steps = [
     "get_documents",
     "etl_chromadb_pdf",
     "etl_chromadb_scanned_pdf", # the performance for scanned pdf may not be good
-    "rag_cot",
+    "rag_cot_evaluation",
+    "test_rag_cot"
 ]
 
 
@@ -100,7 +101,7 @@ def go(config: DictConfig):
                     "embedding_model": config["etl"]["embedding_model"]
                 },
             )
-        if "rag_cot" in active_steps:
+        if "rag_cot_evaluation" in active_steps:
 
             if config["prompt_engineering"]["run_id_chromadb"] == "None":
                 # Look for run_id that has artifact logged as documents
@@ -120,7 +121,7 @@ def go(config: DictConfig):
                 run_id = config["prompt_engineering"]["run_id_chromadb"]
 
             _ = mlflow.run(
-                os.path.join(hydra.utils.get_original_cwd(), "src", "rag_cot"),
+                os.path.join(hydra.utils.get_original_cwd(), "src", "rag_cot_evaluation"),
                 "main",
                 parameters={
                     "query": config["prompt_engineering"]["query"],
@@ -138,7 +139,7 @@ def go(config: DictConfig):
                 "main",
                 parameters={
                     "query": config["prompt_engineering"]["query"],
-                    "input_chromadb_local": os.path.join(hydra.utils.get_original_cwd(), "src", "rag_cot", "chroma_db"),
+                    "input_chromadb_local": os.path.join(hydra.utils.get_original_cwd(), "src", "rag_cot_evaluation", "chroma_db"),
                     "embedding_model": config["etl"]["embedding_model"],
                     "chat_model_provider": config["prompt_engineering"]["chat_model_provider"]
                 },
diff --git a/app/llmops/src/rag_cot/MLproject b/app/llmops/src/rag_cot_evaluation/MLproject
similarity index 100%
rename from app/llmops/src/rag_cot/MLproject
rename to app/llmops/src/rag_cot_evaluation/MLproject
diff --git a/app/llmops/src/rag_cot/python_env.yml b/app/llmops/src/rag_cot_evaluation/python_env.yml
similarity index 100%
rename from app/llmops/src/rag_cot/python_env.yml
rename to app/llmops/src/rag_cot_evaluation/python_env.yml
diff --git a/app/llmops/src/rag_cot/run.py b/app/llmops/src/rag_cot_evaluation/run.py
similarity index 100%
rename from app/llmops/src/rag_cot/run.py
rename to app/llmops/src/rag_cot_evaluation/run.py
diff --git a/app/streamlit/Chatbot.py b/app/streamlit/Chatbot.py
index 16266d4..ce971e5 100644
--- a/app/streamlit/Chatbot.py
+++ b/app/streamlit/Chatbot.py
@@ -8,14 +8,21 @@ from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain_deepseek import ChatDeepSeek
 from langchain_community.llms.moonshot import Moonshot
 
+import torch
+torch.classes.__path__ = [os.path.join(torch.__path__[0], torch.classes.__file__)] 
+
+# # # or simply:
+# torch.classes.__path__ = []
+
+
 os.environ["TOKENIZERS_PARALLELISM"] = "false"
-GEMINI_API_KEY = config("GOOGLE_API_KEY", cast=str)
-DEEKSEEK_API_KEY = config("DEEKSEEK_API_KEY", cast=str)
-MOONSHOT_API_KEY = config("MOONSHOT_API_KEY", cast=str)
-CHAT_MODEL_PROVIDER = config("CHAT_MODEL_PROVIDER", cast=str)
-INPUT_CHROMADB_LOCAL = config("INPUT_CHROMADB_LOCAL", cast=str)
-EMBEDDING_MODEL = config("EMBEDDING_MODEL", cast=str)
-COLLECTION_NAME = config("COLLECTION_NAME", cast=str)
+GEMINI_API_KEY = config("GOOGLE_API_KEY", cast=str, default="123456")
+DEEKSEEK_API_KEY = config("DEEKSEEK_API_KEY", cast=str, default="123456")
+MOONSHOT_API_KEY = config("MOONSHOT_API_KEY", cast=str, default="123456")
+CHAT_MODEL_PROVIDER = config("CHAT_MODEL_PROVIDER", cast=str, default="gemini")
+INPUT_CHROMADB_LOCAL = config("INPUT_CHROMADB_LOCAL", cast=str, default="../llmops/src/rag_cot_evaluation/chroma_db")
+EMBEDDING_MODEL = config("EMBEDDING_MODEL", cast=str, default="paraphrase-multilingual-mpnet-base-v2")
+COLLECTION_NAME = config("COLLECTION_NAME", cast=str, default="rag_experiment")
 
 st.title("💬 RAG AI for Medical Guideline")
 st.caption(f"🚀 A RAG AI for Medical Guideline powered by {CHAT_MODEL_PROVIDER}")
@@ -24,12 +31,15 @@ if "messages" not in st.session_state:
 for msg in st.session_state.messages:
     st.chat_message(msg["role"]).write(msg["content"])
 
+print('i am here1')
 # Load data from ChromaDB
 chroma_client = chromadb.PersistentClient(path=INPUT_CHROMADB_LOCAL)
 collection = chroma_client.get_collection(name=COLLECTION_NAME)
+print('i am here2')
 
 # Initialize embedding model
 model = SentenceTransformer(EMBEDDING_MODEL) 
+print('i am here3')
 
 if CHAT_MODEL_PROVIDER == "deepseek":
     # Initialize DeepSeek model
@@ -78,6 +88,7 @@ Provide the answer with language that is similar to the question asked.
 """
 answer_prompt = PromptTemplate(template=answer_template, input_variables=["cot", "question"])
 answer_chain = answer_prompt | llm
+print('i am here4')
 
 if prompt := st.chat_input():
     
diff --git a/app/streamlit/Dockerfile b/app/streamlit/Dockerfile
index b335644..1c55f0c 100644
--- a/app/streamlit/Dockerfile
+++ b/app/streamlit/Dockerfile
@@ -9,6 +9,10 @@ RUN pip install --no-cache-dir -r requirements.txt
 COPY Chatbot.py .
 COPY .env .
 
+# Run python to initialize download of SentenceTransformer model
+COPY initialize_sentence_transformer.py .
+RUN python initialize_sentence_transformer.py
+
 EXPOSE 8501
 
 ENTRYPOINT ["streamlit", "run", "Chatbot.py"]
\ No newline at end of file
diff --git a/app/streamlit/app_test.py b/app/streamlit/app_test.py
index dce15fd..f187126 100644
--- a/app/streamlit/app_test.py
+++ b/app/streamlit/app_test.py
@@ -1,52 +1,7 @@
-import datetime
 from unittest.mock import patch
 from streamlit.testing.v1 import AppTest
-from openai.types.chat import ChatCompletionMessage
-from openai.types.chat.chat_completion import ChatCompletion, Choice
 
 
-# See https://github.com/openai/openai-python/issues/715#issuecomment-1809203346
-def create_chat_completion(response: str, role: str = "assistant") -> ChatCompletion:
-    return ChatCompletion(
-        id="foo",
-        model="gpt-3.5-turbo",
-        object="chat.completion",
-        choices=[
-            Choice(
-                finish_reason="stop",
-                index=0,
-                message=ChatCompletionMessage(
-                    content=response,
-                    role=role,
-                ),
-            )
-        ],
-        created=int(datetime.datetime.now().timestamp()),
-    )
-
-
-# @patch("langchain_deepseek.ChatDeepSeek.__call__")
-# @patch("langchain_google_genai.ChatGoogleGenerativeAI.invoke")
-# @patch("langchain_community.llms.moonshot.Moonshot.__call__")
-# def test_Chatbot(moonshot_llm, gemini_llm, deepseek_llm):
-#     at = AppTest.from_file("Chatbot.py").run()
-#     assert not at.exception
-    
-#     QUERY = "What is the best treatment for hypertension?"
-#     RESPONSE = "The best treatment for hypertension is..."
-    
-#     deepseek_llm.return_value.content = RESPONSE
-#     gemini_llm.return_value.content = RESPONSE
-#     moonshot_llm.return_value = RESPONSE
-    
-#     at.chat_input[0].set_value(QUERY).run()
-    
-#     assert any(mock.called for mock in [deepseek_llm, gemini_llm, moonshot_llm])
-#     assert at.chat_message[1].markdown[0].value == QUERY
-#     assert at.chat_message[2].markdown[0].value == RESPONSE
-#     assert at.chat_message[2].avatar == "assistant"
-#     assert not at.exception
-
 
 @patch("langchain.llms.OpenAI.__call__")
 def test_Langchain_Quickstart(langchain_llm):
@@ -59,3 +14,4 @@ def test_Langchain_Quickstart(langchain_llm):
     at.button[0].set_value(True).run()
     print(at)
     assert at.info[0].value == RESPONSE
+
diff --git a/app/streamlit/initialize_sentence_transformer.py b/app/streamlit/initialize_sentence_transformer.py
new file mode 100644
index 0000000..3026701
--- /dev/null
+++ b/app/streamlit/initialize_sentence_transformer.py
@@ -0,0 +1,7 @@
+from decouple import config
+from sentence_transformers import SentenceTransformer
+
+EMBEDDING_MODEL = config("EMBEDDING_MODEL", cast=str, default="paraphrase-multilingual-mpnet-base-v2")
+
+# Initialize embedding model
+model = SentenceTransformer(EMBEDDING_MODEL) 
\ No newline at end of file