{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "hello world\n"
     ]
    }
   ],
   "source": [
    "print(\"hello world\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\Ritesh.Thawkar\\Desktop\\website-demos\\env\\Lib\\site-packages\\pinecone\\data\\index.py:1: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from tqdm.autonotebook import tqdm\n"
     ]
    }
   ],
   "source": [
    "from pinecone import Pinecone\n",
    "\n",
    "# Initialize the Pinecone client\n",
    "pc = Pinecone(api_key='ca8e6a33-7355-453f-ad4b-80c8a1c6a9c7')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define your index name\n",
    "index_name = 'vector-store-index'\n",
    "index = pc.Index(index_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'dimension': 768,\n",
       " 'index_fullness': 0.0,\n",
       " 'namespaces': {'': {'vector_count': 16294}},\n",
       " 'total_vector_count': 16294}"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "index.describe_index_stats()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "vector_ids = [str(i) for i in range(1, 16295)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "from concurrent.futures import ThreadPoolExecutor, as_completed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "def update_vector(vector_id):\n",
    "    try:\n",
    "        # Fetch the vector\n",
    "        vector = index.fetch([vector_id])\n",
    "        \n",
    "        # Check if the vector exists\n",
    "        if vector and vector['vectors']:\n",
    "            prev_text = vector['vectors'][vector_id].metadata['text']\n",
    "            \n",
    "            # Update the vector's metadata\n",
    "            index.update(\n",
    "                id=vector_id, \n",
    "                set_metadata={\"context\": prev_text},\n",
    "            )\n",
    "            return f\"Updated vector {vector_id}.\"\n",
    "        else:\n",
    "            return f\"Vector {vector_id} not found.\"\n",
    "    except Exception as e:\n",
    "        return f\"Error updating vector {vector_id}: {e}\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Use ThreadPoolExecutor for parallel execution\n",
    "with ThreadPoolExecutor(max_workers=10) as executor:  # Adjust max_workers as needed\n",
    "    future_to_vector_id = {executor.submit(update_vector, vector_id): vector_id for vector_id in vector_ids}\n",
    "    \n",
    "    for future in as_completed(future_to_vector_id):\n",
    "        vector_id = future_to_vector_id[future]\n",
    "        try:\n",
    "            result = future.result()\n",
    "        except Exception as e:\n",
    "            print(f\"Error processing vector {vector_id}: {e}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Specify the ID of the vector you want to update\n",
    "vector_ids = [str(i) for i in range(1, 16295)]\n",
    "\n",
    "for vector_id in vector_ids:\n",
    "    # Fetch the vector\n",
    "    vector = index.fetch([vector_id])\n",
    "\n",
    "    prev_text = vector['vectors'][vector_id].metadata['text']\n",
    "\n",
    "    index.update(\n",
    "        id=vector_id, \n",
    "        set_metadata={\"context\": prev_text},\n",
    "    )\n",
    "\n",
    "# Check if the vector exists\n",
    "# if vector and vector.ids:\n",
    "#     # Get the current metadata\n",
    "#     current_metadata = vector.vectors[vector_id].metadata\n",
    "    \n",
    "#     # Update the key name in the metadata\n",
    "#     if 'text' in current_metadata:\n",
    "#         current_metadata['context'] = current_metadata.pop('text')\n",
    "    \n",
    "#     # Upsert the updated vector back to the index\n",
    "#     index.upsert(vectors=[(vector_id, vector.vectors[vector_id].values, current_metadata)])\n",
    "#     print(f\"Updated metadata for vector {vector_id}.\")\n",
    "# else:\n",
    "#     print(f\"Vector with ID {vector_id} not found.\")\n",
    "\n",
    "# Optionally, close the index\n",
    "# index.close()\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "env",
   "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": "3.12.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}