import gradio as gr
import pandas as pd
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import Chroma, faiss
from langchain_community.llms import HuggingFaceEndpoint, HuggingFaceHub
from langchain.chains import LLMChain
from langchain_community.document_loaders.csv_loader import CSVLoader
from langchain_community.document_loaders import PyPDFLoader
from langchain.text_splitter import CharacterTextSplitter
from langchain_community.document_loaders import TextLoader
from langchain_community import vectorstores
from langchain.prompts import PromptTemplate
from langchain.chains import RetrievalQA
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain.text_splitter import CharacterTextSplitter, RecursiveCharacterTextSplitter
from langchain.vectorstores import DocArrayInMemorySearch
from langchain.document_loaders import TextLoader
from langchain.chains import RetrievalQA,  ConversationalRetrievalChain
from langchain.memory import ConversationBufferMemory
from langchain.chat_models import ChatOpenAI
from langchain.document_loaders import TextLoader
from langchain.document_loaders import PyPDFLoader
import panel as pn
import param
import re
import os

api_token = os.environ.get('HUGGINGFACEHUB_API_TOKEN')

memory = ConversationBufferMemory(
    memory_key="chat_history",
    return_messages=True
)

model = HuggingFaceHub(
    huggingfacehub_api_token=api_token,
    repo_id="mistralai/Mistral-7B-Instruct-v0.2",
    task="conversational",
    model_kwargs={"temperature": 0.8, "max_length": 1000},
)
template = """Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer. Use three sentences maximum. Keep the answer as concise as possible. Always say "thanks for asking!" at the end of the answer. 
{context}
Question: {question}
Helpful Answer:"""
QA_CHAIN_PROMPT = PromptTemplate.from_template(template)

def load_db(file, k):
    # load documents
    loader = PyPDFLoader(file)
    documents = loader.load()
    # split documents
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=150)
    docs = text_splitter.split_documents(documents)
    # define embedding
    embeddings = HuggingFaceEmbeddings()
    # create vector database from data
    db = vectorstores.FAISS.from_documents(docs, embeddings)
    # define retriever
    retriever = db.as_retriever(search_type="similarity", search_kwargs={"k": k})
    # create a chatbot chain. Memory is managed externally.
    question_generator_chain = LLMChain(llm=model, prompt=QA_CHAIN_PROMPT)

    qa = ConversationalRetrievalChain.from_llm(
        llm=model,
        chain_type="stuff",
        retriever=retriever,
        return_source_documents=True,
        return_generated_question=True,
    )

    return qa

def greet(name, pdf_file):
    a = load_db(pdf_file, 3)
    r = a.invoke({"question": name, "chat_history": []})
    match = re.search(r'Helpful Answer:(.*)', r['answer'])
    if match:
        helpful_answer = match.group(1).strip()
        return helpful_answer
    else:
        return "No helpful answer found."

iface = gr.Interface(fn=greet, inputs=["text", "file"], outputs="text")
iface.launch(share=True)