{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "26b62e0c",
   "metadata": {},
   "outputs": [],
   "source": [
    "%load_ext autoreload\n",
    "%autoreload "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "b1a6a020",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/zuppif/miniconda3/envs/activeloop/lib/python3.9/site-packages/deeplake/util/check_latest_version.py:32: UserWarning: A newer version of deeplake (3.4.3) is available. It's recommended that you update to the latest version using `pip install -U deeplake`.\n",
      "  warnings.warn(\n",
      "-"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "This dataset can be visualized in Jupyter Notebook by ds.visualize() or at https://app.activeloop.ai/zuppif/disney-lyrics\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "|"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "hub://zuppif/disney-lyrics loaded successfully.\n",
      "\n",
      "Deep Lake Dataset in hub://zuppif/disney-lyrics already exists, loading from the storage\n",
      "Dataset(path='hub://zuppif/disney-lyrics', read_only=True, tensors=['embedding', 'ids', 'metadata', 'text'])\n",
      "\n",
      "  tensor     htype     shape      dtype  compression\n",
      "  -------   -------   -------    -------  ------- \n",
      " embedding  generic  (85, 1536)  float32   None   \n",
      "    ids      text     (85, 1)      str     None   \n",
      " metadata    json     (85, 1)      str     None   \n",
      "   text      text     (85, 1)      str     None   \n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r",
      " \r",
      "\r",
      " \r"
     ]
    }
   ],
   "source": [
    "from dotenv import load_dotenv\n",
    "load_dotenv() \n",
    "from names import DATASET_ID, MODEL_ID\n",
    "from data import load_db\n",
    "import os\n",
    "from langchain.chains import RetrievalQA, ConversationalRetrievalChain\n",
    "from langchain.vectorstores import DeepLake\n",
    "from langchain.llms import OpenAI\n",
    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
    "from langchain.chat_models import ChatOpenAI\n",
    "\n",
    "embeddings = OpenAIEmbeddings(model=MODEL_ID)\n",
    "dataset_path = f\"hub://{os.environ['ACTIVELOOP_ORG_ID']}/{DATASET_ID}\"\n",
    "\n",
    "db = load_db(dataset_path, embedding_function=embeddings, token=os.environ['ACTIVELOOP_TOKEN'], org_id=os.environ[\"ACTIVELOOP_ORG_ID\"], read_only=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "07d8a381",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.chains import LLMChain\n",
    "from langchain.prompts import PromptTemplate\n",
    "from pathlib import Path\n",
    "\n",
    "prompt = PromptTemplate(\n",
    "    input_variables=[\"content\"],\n",
    "    template=Path(\"prompts/bot.prompt\").read_text(),\n",
    ")\n",
    "\n",
    "llm = ChatOpenAI(temperature=0.7)\n",
    "\n",
    "chain = LLMChain(llm=llm, prompt=prompt)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "id": "ebca722d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Melancholy, Coziness, Nostalgia, Calmness.'"
      ]
     },
     "execution_count": 81,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "emotions = chain.run(content=\"It's rainy\")\n",
    "emotions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "id": "9598a36c",
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'https://open.spotify.com/embed/track/5EeQQ8BVJTRkp1AIKJILGY?utm_source=generator'"
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "doc, score = db.similarity_search_with_score(emotions, distance_metric=\"cos\")[0]\n",
    "doc.metadata[\"embed_url\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "d6214e40",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "        <iframe\n",
       "            width=\"700\"\n",
       "            height=\"350\"\n",
       "            src=\"https://open.spotify.com/embed/track/5EeQQ8BVJTRkp1AIKJILGY?utm_source=generator\"\n",
       "            frameborder=\"0\"\n",
       "            allowfullscreen\n",
       "            \n",
       "        ></iframe>\n",
       "        "
      ],
      "text/plain": [
       "<IPython.lib.display.IFrame at 0x7fb0be920a00>"
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "doc.metadata[\"embed_url\"]\n",
    "\n",
    "from IPython.display import IFrame\n",
    "IFrame(doc.metadata[\"embed_url\"], width=700, height=350)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "28ae2c63",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Dataset(path='hub://zuppif/disney-lyrics', read_only=True, index=Index([()]), tensors=['embedding', 'ids', 'metadata', 'text'])"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "db.ds.query(\"select * where contains(\\\"text\\\", 'Did they') limit 2\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1780552c",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}