Delete app.py

app.py

@@ -1,76 +0,0 @@
-from Functions.write_stream import user_data
-import streamlit as st
-from llama_index.core import SimpleDirectoryReader, VectorStoreIndex, ServiceContext
-from llama_index.llms.llama_cpp import LlamaCPP
-from llama_index.llms.llama_cpp.llama_utils import messages_to_prompt, completion_to_prompt
-from langchain.embeddings.huggingface import HuggingFaceEmbeddings
-
-
-directory = "Knowledge Base/"
-
-
-documents = SimpleDirectoryReader(directory).load_data()
-
-llm = LlamaCPP(
-# You can pass in the URL to a GGML model to download it automatically
-model_url='https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q2_K.gguf',
-# optionally, you can set the path to a pre-downloaded model instead of model_url
-model_path=None,
-temperature=0.75,
-max_new_tokens=256,
-# llama2 has a context window of 4096 tokens, but we set it lower to allow for some wiggle room
-context_window=3900,
-messages_to_prompt=messages_to_prompt,
-completion_to_prompt=completion_to_prompt,
-verbose=True,
-)
-print("working -3")
-
-embed_model = HuggingFaceEmbeddings(model_name="thenlper/gte-large")
-
-print("working -2")
-
-service_context = ServiceContext.from_defaults(
-    chunk_size= 256,
-    llm=llm,
-    embed_model=embed_model
-)
-print("working -1")
-
-index = VectorStoreIndex.from_documents(documents, service_context=service_context, show_progress=True)
-print("working 0")
-
-query_engine = index.as_query_engine()
-
-
-
-###############=============    USER INTERFACE (UI    )###############=============
-
-
-st.title("Wiki Bot")
-
-if "messages" not in st.session_state:
-    st.session_state.messages = []
-
-
-for message in st.session_state.messages:
-    with st.chat_message(message["role"]):
-        st.markdown(message["content"])
-
-
-prompt = st.chat_input("Enter Your Question:")
-
-
-if prompt:
-
-    with st.chat_message("user"):
-        st.markdown(prompt)
-    st.session_state.messages.append({"role":"user","content":prompt})
-    
-    reply= query_engine.query(prompt)
-    response = user_data(function_name=reply)
-
-    with st.chat_message("assistant"):
-        st.write_stream(response)
-    print("working!!")
-    st.session_state.messages.append({"role":"assistant","content":reply})