app.py

from llama_index import SimpleDirectoryReader, LLMPredictor, PromptHelper, StorageContext, ServiceContext, GPTVectorStoreIndex, load_index_from_storage
from langchain.chat_models import ChatOpenAI
import gradio as gr
import sys
import os

#from langchain.chat_models import ChatOpenAI

os.environ["OPENAI_API_KEY"]

def construct_index(directory_path):
    max_input_size = 4096
    num_outputs = 512
    max_chunk_overlap = 0.2
    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=1.0, model_name="gpt-4", max_tokens=num_outputs))

    documents = SimpleDirectoryReader(directory_path).load_data()

    index = GPTVectorStoreIndex(documents, llm_predictor=llm_predictor, prompt_helper=prompt_helper)

    #index.save_to_disk('index.json')
    index.storage_context.persist(persist_dir="index.json")

    return index

def chatbot(input_text):
    #query_engine = index.as_query_engine()
    index = GPTVectorStoreIndex.load_from_disk('index.json')
    response = index.query(input_text, response_mode="compact")
    return response.response

iface = gr.Interface(fn=chatbot,
                     inputs=gr.components.Textbox(lines=7, label="Ingrese su pregunta"),
                     outputs="text",
                     title="Demo Galicia")

index = construct_index("docs")
iface.launch(share=True, debug=True)