isNullExample-AddingNewProperty.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "64406e3b-95eb-4541-9c77-80817d9bfc9b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import weaviate\n",
    "client = weaviate.Client(\"http://localhost:8080\")\n",
    "client.is_ready()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "6c11210f-2546-40c5-8be9-e31698b074db",
   "metadata": {},
   "outputs": [],
   "source": [
    "client.schema.delete_all()\n",
    "class_obj = {'class': 'Label',\n",
    " 'description': 'Labels for documents',\n",
    " 'invertedIndexConfig': {'bm25': {'b': 0.75, 'k1': 1.2},\n",
    "  'cleanupIntervalSeconds': 60,\n",
    "  'indexNullState': True,\n",
    "  'stopwords': {'additions': None, 'preset': 'en', 'removals': None}},\n",
    " 'moduleConfig': {'text2vec-openai': {'model': 'ada',\n",
    "   'modelVersion': '002',\n",
    "   'type': 'text',\n",
    "   'vectorizeClassName': False}},\n",
    " 'properties': [{'dataType': ['text'],\n",
    "   'description': 'Content of the label',\n",
    "   'indexFilterable': True,\n",
    "   'indexSearchable': True,\n",
    "   'moduleConfig': {'text2vec-openai': {'skip': False,\n",
    "     'vectorizePropertyName': False}},\n",
    "   'name': 'content',\n",
    "   'tokenization': 'field'},],\n",
    " 'replicationConfig': {'factor': 1},\n",
    " 'shardingConfig': {'virtualPerPhysical': 128,\n",
    "  'desiredCount': 1,\n",
    "  'actualCount': 1,\n",
    "  'desiredVirtualCount': 128,\n",
    "  'actualVirtualCount': 128,\n",
    "  'key': '_id',\n",
    "  'strategy': 'hash',\n",
    "  'function': 'murmur3'},\n",
    " 'vectorIndexConfig': {'skip': False,\n",
    "  'cleanupIntervalSeconds': 300,\n",
    "  'maxConnections': 64,\n",
    "  'efConstruction': 128,\n",
    "  'ef': -1,\n",
    "  'dynamicEfMin': 100,\n",
    "  'dynamicEfMax': 500,\n",
    "  'dynamicEfFactor': 8,\n",
    "  'vectorCacheMaxObjects': 1000000000000,\n",
    "  'flatSearchCutoff': 40000,\n",
    "  'distance': 'cosine',\n",
    "  'pq': {'enabled': False,\n",
    "   'bitCompression': False,\n",
    "   'segments': 0,\n",
    "   'centroids': 256,\n",
    "   'encoder': {'type': 'kmeans', 'distribution': 'log-normal'}}},\n",
    " 'vectorIndexType': 'hnsw',\n",
    " 'vectorizer': 'text2vec-openai'}\n",
    "\n",
    "# add the schema\n",
    "client.schema.create_class(class_obj)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "aa40f993-e441-4f80-aafc-a298611f76e0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'cf991339-1c7f-4aea-b1ea-cf39e250b34d'"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# add an object before adding this new property\n",
    "client.data_object.create({\"content\": \"Sample Content, only content\"}, \"Label\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "cf8d11bc-2a7b-4ee0-aa8a-f4fc8c20d5ed",
   "metadata": {},
   "outputs": [],
   "source": [
    "# let's add a new type property\n",
    "add_prop = {'dataType': ['text'],\n",
    "   'description': 'type or substype of the label, used for filtering',\n",
    "   'indexFilterable': True,\n",
    "   'indexSearchable': True,\n",
    "   'moduleConfig': {'text2vec-openai': {'skip': True,\n",
    "     'vectorizePropertyName': False}},\n",
    "   'name': 'type',\n",
    "   'tokenization': 'word'}\n",
    "\n",
    "client.schema.property.create('Label', add_prop)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "6fb6ff33-ee73-45d1-843f-f03003451f19",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'data': {'Get': {'Label': [{'content': 'Sample Content, only content',\n",
       "     'type': None}]}}}"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# for now we only have one object\n",
    "client.query.get(\"Label\", \"content type\").do()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "b24ae198-26d1-4fad-8a47-0f097612f850",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'data': {'Get': {'Label': []}}}"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# the previously added object will not appear on the filter\n",
    "client.query.get(\"Label\", \"content type\").with_where({\n",
    "    \"path\": \"type\",\n",
    "    \"operator\": \"IsNull\",\n",
    "    \"valueBoolean\": True\n",
    "}).do()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "b9ac5af7-624e-41ca-8e91-1036b160379b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'e5ba4f5f-9104-49f1-90d7-85592b6644c4'"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# but, if we add a new object\n",
    "client.data_object.create({\"content\": \"Sample Content, only content, no type, added later\"}, \"Label\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "9a7b7997-06bf-4903-a00d-6f64710143a9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'data': {'Get': {'Label': [{'content': 'Sample Content, only content, no type, added later',\n",
       "     'type': None}]}}}"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# if will then appear with the isNull filter\n",
    "client.query.get(\"Label\", \"content type\").with_where({\n",
    "    \"path\": \"type\",\n",
    "    \"operator\": \"IsNull\",\n",
    "    \"valueBoolean\": True\n",
    "}).do()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "b2576b12-2696-4b2e-9939-2aee01c23c2c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'data': {'Get': {'Label': [{'content': 'Sample Content, only content',\n",
       "     'type': None},\n",
       "    {'content': 'Sample Content, only content, no type, added later',\n",
       "     'type': None}]}}}"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# It should show both objects\n",
    "client.query.get(\"Label\", \"content type\").do()"
   ]
  }
 ],
 "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": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}