from llama_index import SimpleDirectoryReader, GPTListIndex, GPTVectorStoreIndex, LLMPredictor, PromptHelper
from langchain.chat_models import ChatOpenAI
import gradio as gr
import sys
import os
 
 
from llama_index import StorageContext, load_index_from_storage
 
os.environ["OPENAI_API_KEY"] = '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'
 
def construct_index(base_directory):
    full_path = os.path.join(base_directory, "docs")
    max_input_size = 40960
    num_outputs = 5120
    max_chunk_overlap = 0.4
    chunk_size_limit = 600
 
    prompt_helper = PromptHelper(max_input_size, num_outputs, max_chunk_overlap, chunk_size_limit=chunk_size_limit)
 
    llm_predictor = LLMPredictor(llm=ChatOpenAI(temperature=0.8, model_name="gpt-3.5-turbo-0613", max_tokens=num_outputs))
 
    documents = SimpleDirectoryReader(full_path).load_data()
 
    index = GPTVectorStoreIndex.from_documents(documents, llm_predictor=llm_predictor, prompt_helper=prompt_helper)
    index.storage_context.persist()
    #print(index)
    #index.save_to_disk('index.json')
    return index
 
def chatbot(input_text):
    #index = GPTVectorStoreIndex.load_from_disk('index.json')
    # rebuild storage context
    # load index
    storage_context = StorageContext.from_defaults(persist_dir='./storage')##########
    index = load_index_from_storage(storage_context)######################
    query_engine = index.as_query_engine()
    response = query_engine.query(input_text)
    return response.response
 
iface = gr.Interface(fn=chatbot,
                     inputs=gr.components.Textbox(lines=7, label="Enter your text"),
                     outputs="text",
                     title="MCQ AI Chatbot")
 
#index = construct_index("docs")
index = construct_index("")
 
iface.launch(share=True)