Update app.py

app.py

@@ -74,30 +74,16 @@ As an AI, provide accurate and relevant information based on the provided docume
 callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
 
 # Function to create a conversational chain
-def create_conversational_chain(database):
-    model_name = 'TheBloke/Llama-2-7b-chat-hf'
-    model_directory = "files"
-    #Check if the model file exists in the specified directory
-    model_file = os.path.join(model_directory, model_name)
-    if os.path.exists(model_file):
-        model_path = model_file
-        print("Model file found in the directory. Using the local model file.")
-    else:
-        model_path = "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q8_0.gguf"
-        print("Model file not found in the directory. Downloading the model from the repository.")
-    #Load the model
-    model = AutoModelForCausalLM.from_pretrained(model_path)
-    print(model_path)
+def create_conversational_chain(vectordb):
     llama_llm = LlamaCpp(
-        # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llama-2-7b-chat.Q8_0.gguf
-        model_path = model_path,
-        temperature=0.75,
-        max_tokens=200,
-        top_p=1,
-        callback_manager=callback_manager,
-        n_ctx=3000)
-
-    retriever = database.as_retriever()
+    model_path="llama-2-7b-chat.Q8_0.gguf",
+    temperature=0.75,
+    max_tokens=200,
+    top_p=1,
+    callback_manager=callback_manager,
+    n_ctx=3000)
+
+    retriever = vectordb.as_retriever()
     CONDENSE_QUESTION_PROMPT = PromptTemplate.from_template(template)
 
     memory = ConversationBufferMemory(
@@ -109,10 +95,9 @@ def create_conversational_chain(database):
                            #condense_question_prompt=CONDENSE_QUESTION_PROMPT,
                            memory=memory,
                            return_source_documents=True))
-    print("Conversational Chain created.")
+    print("Conversational Chain created for the LLM using the vector store")
     return conversation_chain
 
-# Function to validate the answer against source documents
 def validate_answer(response_answer, source_documents):
     model = SentenceTransformer('all-MiniLM-L6-v2')
     similarity_threshold = 0.5