{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a9f7a25f",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/kpatelis/projects/Agents_Course_Assignment/.venv/lib/python3.12/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"
     ]
    }
   ],
   "source": [
    "import os\n",
    "import json\n",
    "from dotenv import load_dotenv\n",
    "from supabase.client import Client, create_client\n",
    "from langchain_huggingface import HuggingFaceEmbeddings\n",
    "from langchain.schema import Document\n",
    "\n",
    "load_dotenv()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2c948d46",
   "metadata": {},
   "outputs": [],
   "source": [
    "supabase: Client = create_client(\n",
    "    os.environ.get(\"SUPABASE_URL\"), \n",
    "    os.environ.get(\"SUPABASE_SERVICE_KEY\"))\n",
    "\n",
    "embeddings = HuggingFaceEmbeddings(model_name=\"Alibaba-NLP/gte-modernbert-base\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "f2c5492b",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('metadata.jsonl', 'r') as jsonl_file:\n",
    "    json_list = list(jsonl_file)\n",
    "\n",
    "documents = []\n",
    "for json_str in json_list:\n",
    "    json_data = json.loads(json_str)\n",
    "    content = f\"Question : {json_data['Question']}\\n\\nFinal answer : {json_data['Final answer']}\"\n",
    "    embedding = embeddings.embed_query(content)\n",
    "    document = {\n",
    "        \"content\" : content,\n",
    "        \"metadata\" : {\n",
    "            \"source\" : json_data['task_id']\n",
    "        },\n",
    "        \"embedding\" : embedding,\n",
    "    }\n",
    "    documents.append(document)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "26ddbafd",
   "metadata": {},
   "outputs": [],
   "source": [
    "# pgvector needs to be enabled, to turn to vector database\n",
    "# Table needs to be created beforehand in Supabase, with column types\n",
    "try:\n",
    "    response = (\n",
    "        supabase.table(\"gaia_documents\")\n",
    "        .insert(documents)\n",
    "        .execute()\n",
    "    )\n",
    "except Exception as exception:\n",
    "    print(\"Error inserting data into Supabase:\", exception)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}