{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.indexes import VectorstoreIndexCreator\n",
    "from langchain.document_loaders.hugging_face_dataset import HuggingFaceDatasetLoader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset_name=\"tweet_eval\"\n",
    "page_content_column=\"text\"\n",
    "name=\"stance_climate\"\n",
    "\n",
    "\n",
    "loader=HuggingFaceDatasetLoader(dataset_name,page_content_column,name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/tutu/anaconda3/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n",
      "Found cached dataset tweet_eval (/Users/tutu/.cache/huggingface/datasets/tweet_eval/stance_climate/1.1.0/12aee5282b8784f3e95459466db4cdf45c6bf49719c25cdb0743d71ed0410343)\n",
      "100%|██████████| 3/3 [00:00<00:00, 301.87it/s]\n",
      "Using embedded DuckDB without persistence: data will be transient\n"
     ]
    }
   ],
   "source": [
    "index = VectorstoreIndexCreator().from_loaders([loader])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "query = \"What are the most used hashtag?\"\n",
    "result = index.query(query)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "' The most used hashtags in this context are #SemST, #TakeDownTheFlag, #LoveWins, #Sustainability, and #Environmental.'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.10"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}