import streamlit as st
from langchain_core.messages import AIMessage, HumanMessage
from langchain_community.document_loaders import WebBaseLoader
from langchain_openai import ChatOpenAI
from langchain_chroma import Chroma
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_huggingface.embeddings import HuggingFaceEndpointEmbeddings
from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain.chains.history_aware_retriever import create_history_aware_retriever
from langchain.chains.retrieval import create_retrieval_chain
from langchain.chains.combine_documents import create_stuff_documents_chain
from dotenv import load_dotenv
import os

load_dotenv()

llm = ChatOpenAI(temperature=0.5, model="mistralai/mistral-7b-instruct:free",base_url="https://openrouter.ai/api/v1",api_key=os.getenv("OPENAI_API_KEY"))

def get_vector_store(url):
    loader = WebBaseLoader(url)
    documents = loader.load()

    # splitting into chunks
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
    documents_chunks = text_splitter.split_documents(documents=documents)

    # converting the chunks into embeddings
    embeddings = HuggingFaceEndpointEmbeddings(huggingfacehub_api_token=os.getenv("HF_TOKEN"))

    # store the embeddings in a database
    vector_store = Chroma.from_documents(documents_chunks, embeddings)
    return vector_store

def get_context_retiriever(vector_store):
    retriever = vector_store.as_retriever()
    prompt = ChatPromptTemplate.from_messages([
      MessagesPlaceholder(variable_name="chat_history"),
      ("user", "{input}"),
      ("user", "Given the above conversation, generate a search query to look up in order to get information relevant to the conversation")
    ])
    retriever_chain = create_history_aware_retriever(llm=llm, retriever=retriever, prompt=prompt)
    return retriever_chain

def get_conversational_chain(retriever_chain):
    prompt = ChatPromptTemplate.from_messages([
      ("system", "Answer the user's questions based on the below context:\n\n{context}"),
      MessagesPlaceholder(variable_name="chat_history"),
      ("user", "{input}"),
    ])
    stuff_documnets_chain = create_stuff_documents_chain(llm, prompt)
    return create_retrieval_chain(retriever_chain, stuff_documnets_chain)

def get_response(user_input):
    retriever_chain = get_context_retiriever(st.session_state.vector_store)
    conversational_chain = get_conversational_chain(retriever_chain)
    response = conversational_chain.invoke({
        "chat_history": st.session_state.chat_history,
        "input": user_input
    })
    return response['answer']

st.set_page_config(page_title="Chat with websites", page_icon="🤖")
st.title("Chat with websites")
st.caption("Follow me on Github: [samagra44](https://github.com/samagra44)")
with st.sidebar:
    st.header("Settings")
    website_url = st.text_input("Website URL")

if website_url is None or website_url == "":
    st.info("Please enter a website URL")

else:
    if "chat_history" not in st.session_state:
        st.session_state.chat_history = [
            AIMessage(content="Hello, I am a bot. How can I help you?"),
        ]
    if "vector_store" not in st.session_state:
        st.session_state.vector_store = get_vector_store(website_url)    

    user_query = st.chat_input("Type your message here...")
    if user_query is not None and user_query != "":
        response = get_response(user_query)
        st.session_state.chat_history.append(HumanMessage(content=user_query))
        st.session_state.chat_history.append(AIMessage(content=response))
        
    for message in st.session_state.chat_history:
        if isinstance(message, AIMessage):
            with st.chat_message("AI"):
                st.write(message.content)
        elif isinstance(message, HumanMessage):
            with st.chat_message("Human"):
                st.write(message.content)