app.py

import streamlit as st
from PIL import Image
from datetime import time as t
import time

from operator import itemgetter  
import os
import json
import getpass
import openai
  
from langchain.vectorstores import Pinecone
from langchain.embeddings import OpenAIEmbeddings  
import pinecone


from results import results_agent
from filter import filter_agent
from reranker import reranker
from utils import build_filter

OPENAI_API = st.secrets["OPENAI_API"]
PINECONE_API = st.secrets["PINECONE_API"]
openai.api_key = OPENAI_API


pinecone.init(
    api_key= PINECONE_API,
    environment="gcp-starter" 
)
index_name = "use-class-db"

embeddings = OpenAIEmbeddings(openai_api_key = OPENAI_API)

index = pinecone.Index(index_name)

k = 5





st.title("USC GPT - Find the perfect class")

class_time = st.slider(
    "Filter Class Times:",
    value=(t(11, 30), t(12, 45)))

# st.write("You're scheduled for:", class_time)

units = st.slider(
    "Number of units",
    1, 4,
    value = (1, 4)
)


# for message in st.session_state.messages:
#     with st.chat_message(message["role"]):
#         st.markdown(message["content"])


for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.markdown(message["content"])

assistant = st.chat_message("assistant")
initial_message = "How can I help you today?"

def assistant_response(response):
    message_placeholder = assistant.empty()
    full_response = ""
    assistant_response = response
    # Simulate stream of response with milliseconds delay
    for chunk in assistant_response.split():
        full_response += chunk + " "
        time.sleep(0.05)
        # Add a blinking cursor to simulate typing
        message_placeholder.markdown(full_response + "▌")
    message_placeholder.markdown(full_response)
    # Add assistant response to chat history
    st.session_state.messages.append({"role": "assistant", "content": full_response})

if "messages" not in st.session_state:
    st.session_state.messages = []
    assistant_response(initial_message)

if prompt := st.chat_input("What kind of class are you looking for?"):
    with st.chat_message("user"):
        st.markdown(prompt)
    st.session_state.messages.append({"role": "user", "content": prompt})
    assistant_response("Yah I'm tired af right now boi")
    


# if prompt := st.chat_input("What kind of class are you looking for?"):
#     # Display user message in chat message container
#     with st.chat_message("user"):
#         st.markdown(prompt)
#     # Add user message to chat history
#     st.session_state.messages.append({"role": "user", "content": prompt})

#     response = filter_agent(prompt, OPENAI_API)
#     query = response

#     response = index.query(
#         vector= embeddings.embed_query(query),
#         # filter= build_filter(json),
#         top_k=5,
#         include_metadata=True
#     )
#     response = reranker(query, response)
#     result_query = 'Original Query:' + query + 'Query Results:' + str(response)
#     assistant_response = results_agent(result_query, OPENAI_API)

#     if assistant_response:
#         with st.chat_message("assistant"):
#             message_placeholder = st.empty()
#             full_response = ""
#             # Simulate stream of response with milliseconds delay
#             for chunk in assistant_response.split():
#                 full_response += chunk + " "
#                 time.sleep(0.05)
#                 # Add a blinking cursor to simulate typing
#                 message_placeholder.markdown(full_response + "▌")
#             message_placeholder.markdown(full_response)
#         # Add assistant response to chat history
#         st.session_state.messages.append({"role": "assistant", "content": full_response})