chromadb_copy_collection.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "initial_id",
   "metadata": {
    "collapsed": true,
    "ExecuteTime": {
     "end_time": "2023-11-20T15:03:48.616101Z",
     "start_time": "2023-11-20T15:03:33.351050Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1000\n",
      "{'ids': ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9'], 'embeddings': None, 'metadatas': [None, None, None, None, None, None, None, None, None, None], 'documents': ['document 0', 'document 1', 'document 2', 'document 3', 'document 4', 'document 5', 'document 6', 'document 7', 'document 8', 'document 9'], 'uris': None, 'data': None}\n"
     ]
    }
   ],
   "source": [
    "from chromadb import Settings\n",
    "import chromadb\n",
    "\n",
    "client = chromadb.PersistentClient(path=\"test\", settings=Settings(allow_reset=True))\n",
    "client.reset() #reset the database so we can run this script multiple times\n",
    "col = client.get_or_create_collection(\"test\")\n",
    "\n",
    "col.add(ids=[f\"{i}\" for i in range(1000)],documents=[f\"document {i}\" for i in range(1000)])\n",
    "# client.delete_collection(\"test1\")\n",
    "newCol = client.get_or_create_collection(\"test1\")\n",
    "\n",
    "\n",
    "for i in range(0,1000,10):\n",
    "    batch = col.get(include = [\"metadatas\",\"documents\",\"embeddings\"], limit=10, offset=i)\n",
    "    newCol.add(ids=batch[\"ids\"],documents=batch[\"documents\"],metadatas=batch[\"metadatas\"],embeddings=batch[\"embeddings\"])\n",
    "\n",
    "print(newCol.count())\n",
    "print(newCol.get(offset=0, limit=10)) #get first 10 documents"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [],
   "metadata": {
    "collapsed": false
   },
   "id": "74a7cd788009f4e0"
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}