Update app.py

app.py

@@ -20,11 +20,6 @@ from langchain_core.chat_history import BaseChatMessageHistory
 from langchain_community.chat_message_histories import ChatMessageHistory
 from multiprocessing import Process
 
-print()
-print("-------")
-print("started")
-print("-------")
-
 if not os.path.isdir('database'):
     os.system("unzip database.zip")
 
@@ -42,21 +37,16 @@ print("-------")
 
 persist_directory = 'db'
 
-# embedding = HuggingFaceInferenceAPIEmbeddings(api_key=os.environ["HUGGINGFACE_API_KEY"], model=)
 model_name = "BAAI/bge-large-en"
 model_kwargs = {'device': 'cpu'}
 encode_kwargs = {'normalize_embeddings': True}
-embedding = HuggingFaceBgeEmbeddings(
+"""embedding = HuggingFaceBgeEmbeddings(
     model_name=model_name,
     model_kwargs=model_kwargs,
     encode_kwargs=encode_kwargs,
     show_progress=True,
-)
-
-print()
-print("-------")
-print("Embeddings")
-print("-------")
+)"""
+embedding = HuggingFaceInferenceAPIEmbeddings(api_key=os.environ["HUGGINGFACE_API_KEY"], model=model_name)
 
 async def echo(websocket):
     global retriever, conversational_rag_chain
@@ -93,7 +83,7 @@ def format_docs(docs):
 retriever = vectorstore.as_retriever()
 
 prompt = hub.pull("rlm/rag-prompt")
-llm = HuggingFaceEndpoint(repo_id="mistralai/Mixtral-8x7B-Instruct-v0.1")
+llm = HuggingFaceEndpoint(repo_id="mistralai/Mistral-7B-Instruct-v0.3")
 rag_chain = (
     {"context": retriever | format_docs, "question": RunnablePassthrough()}
     | prompt
@@ -101,11 +91,6 @@ rag_chain = (
     | StrOutputParser()
 )
 
-print()
-print("-------")
-print("Retriever, Prompt, LLM, Rag_Chain")
-print("-------")
-
 ### Contextualize question ###
 contextualize_q_system_prompt = """Given a chat history and the latest user question \
 which might reference context in the chat history, formulate a standalone question \