app.py

import os
import gradio as gr
import gradio
from git import Repo
from llama_index import GPTSimpleVectorIndex, SimpleDirectoryReader, ServiceContext,LLMPredictor
from langchain.chat_models import ChatOpenAI
from llama_index.llm_predictor.chatgpt import ChatGPTLLMPredictor
import huggingface_hub
from huggingface_hub import Repository, login, HfApi
from datetime import datetime
import csv



access_token_read = "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"
access_token_write = "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"
login(token = access_token_read)

hf_token = "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"
#api = HfApi()
#api.login(token=hf_token)


DATASET_REPO_URL = "https://huggingface.co/datasets/diazcalvi/mybrain"
DATA_FILENAME = "kion.json"
#DATA_FILE = os.path.join("vdb", DATA_FILENAME)

HF_TOKEN = hf_token
print("is none?", HF_TOKEN is None)

print("hfh", huggingface_hub.__version__)

os.system("git config --global user.name \"diazcalvi\"")
os.system("git config --global user.email \"diazcalvi@gmail.com\"")

#repo = Repository(
#    repository_name=DATASET_REPO_URL,
#    token=hf_token,
#)
#

repo = Repository(
    local_dir="vdb", clone_from=DATASET_REPO_URL, use_auth_token=hf_token
)
##

#local_repo_path = "vdb"
#repo.clone(local_repo_path)

#index_name = "./data/kion.json"
index_name =  "./vdb/" + DATA_FILENAME
documents_folder = "./documents"

print("DATAFILE:" + index_name)

#@st.experimental_memo
#@st.cache_resource
def initialize_index(index_name, documents_folder):
    #llm_predictor = ChatGPTLLMPredictor()
    llm_predictor = LLMPredictor(llm=ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo")) #	text-davinci-003"))"gpt-3.5-turbo"
    
    service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor)
    
    if os.path.exists(index_name):
        index = GPTSimpleVectorIndex.load_from_disk(index_name)
    else:
        documents = SimpleDirectoryReader(documents_folder).load_data()
        index = GPTSimpleVectorIndex.from_documents(documents)
        index.save_to_disk(index_name)
        #print("Saving to DATAFILE:" + DATA_FILE)
        #commit_url = repo.push_to_hub()
        #print(commit_url)
        #index.save_to_disk(DATA_FILE)
        
        
        user = "diazcalvi"
        #repo_name = "mybrain"
        repo = Repository(
        user,
        DATASET_REPO_URL,
        token=hf_token,
        )
        local_repo_path = "vdb"
        myrepo = Repo(local_repo_path)
        #myrepo.git.add(update=True)
        myrepo.git.add(all=True)
        myrepo.git.commit("-m", "commit message")
        myrepo.git.push("--force")

    return index

#@st.experimental_memo
#@st.cache_data(max_entries=200, persist=True)
def query_index(_index, query_text):
    response = _index.query(query_text)
    return str(response)

def generate_html() -> str:
    with open(DATA_FILE) as csvfile:
        reader = csv.DictReader(csvfile)
        rows = []
        for row in reader:
            rows.append(row)
        rows.reverse()
        if len(rows) == 0:
            return "no messages yet"
        else:
            html = "<div class='chatbot'>"
            for row in rows:
                html += "<div>"
                html += f"<span>{row['name']}</span>"
                html += f"<span class='message'>{row['message']}</span>"
                html += "</div>"
            html += "</div>"
            return html


def store_message(name: str, message: str):
    if name and message:
        print(DATA_FILE)
        print(DATA_FILENAME)
        print(DATASET_REPO_URL)
        with open(DATA_FILE, "a") as csvfile:
            writer = csv.DictWriter(csvfile, fieldnames=["name", "message", "time"])
            writer.writerow(
                {"name": name, "message": message, "time": str(datetime.now())}
            )
        commit_url = repo.push_to_hub()
        print(commit_url)

    return commit_url #generate_html()



def greet(text):
    response = query_index(index, "Act as a Context expert and answer this with detail:" + text + ". (Include the context reference details, file name, page number, and date if available)")
    return response




index = None
api_key = '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'#st.text_input("Enter your OpenAI API key here:", type="password")
if api_key:
    os.environ['OPENAI_API_KEY'] = api_key
    index = initialize_index(index_name, documents_folder)    


if index is None:
    st.warning("Please enter your api key first.")



gradio_interface = gradio.Interface(
  fn=greet,
  inputs="text",
  outputs="text",
  examples=[
    ["What can I ask you? Give me 10 different examples."]
  ],
  title="AI KB",
  description="Enter a query about your data",
  article="© Carlos Diaz Calvi 2023"
)
gradio_interface.launch()