import gradio as gr
from langchain.llms import Replicate
from langchain.vectorstores import Pinecone
from langchain.text_splitter import CharacterTextSplitter
from langchain.document_loaders import PyPDFLoader
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.chains import ConversationalRetrievalChain
from datasets import load_dataset
import os
import pinecone


key = os.environ.get('API')
yeh = os.environ.get('pineapi')
os.environ["REPLICATE_API_TOKEN"] = key
pinecone.init(api_key=yeh, environment='gcp-starter')


import sentence_transformers
import faiss

def loading_pdf():
    return "Loading..."

def pdf_changes(pdf_doc):
    
    loader = PyPDFLoader(pdf_doc.name)
    documents = loader.load()
    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
    texts = text_splitter.split_documents(documents)
    
    embeddings = HuggingFaceEmbeddings()

    index_name = "chatbot"
    index = pinecone.Index(index_name)
    vectordb = Pinecone.from_documents(texts, embeddings, index_name=index_name)

    llm = Replicate(
        model="a16z-infra/llama13b-v2-chat:df7690f1994d94e96ad9d568eac121aecf50684a0b0963b25a41cc40061269e5",
        input={"temperature": 0.2, "max_length": 3000, "length_penalty":1.5, "num_beams":3}
    )
    global qa 
    qa = ConversationalRetrievalChain.from_llm(
        llm,
        vectordb.as_retriever(search_kwargs={'k': 2}),
        return_source_documents=True
    )
    return "Ready"

def add_text(history, text):
    history = history + [(text, None)]
    return history, ""

def bot(history):
    response = infer(history[-1][0])
    history[-1][1] = response['result']
    return history

def infer(question):
    
    query = question
    result = qa({"query": query})

    return result

css="""
#col-container {max-width: 700px; margin-left: auto; margin-right: auto;}
"""

title = """
<div style="text-align: center;max-width: 700px;">
    <h1>Chat with PDF</h1>   
"""


with gr.Blocks(css=css) as demo:
    with gr.Column(elem_id="col-container"):
        gr.HTML(title)
        with gr.Column():
            pdf_doc = gr.File(label="Load a PDF", file_types=['.pdf'], type="file")
            load_pdf = gr.Button("Load PDF")
            langchain_status = gr.Textbox(label="Status", placeholder="", interactive=False)
        chatbot = gr.Chatbot([], elem_id="chatbot").style(height=350)
        question = gr.Textbox(label="Question", placeholder="Type your question and hit Enter ")
        submit_btn = gr.Button("Send message") 
    load_pdf.click(pdf_changes, inputs=[pdf_doc], outputs=[langchain_status], queue=False)
    question.submit(add_text, [chatbot, question], [chatbot, question]).then(
        bot, chatbot, chatbot
    )
    submit_btn.click(add_text, [chatbot, question], [chatbot, question]).then(
        bot, chatbot, chatbot
    )

demo.launch()