{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "f5a0d75d",
   "metadata": {},
   "outputs": [],
   "source": [
    "import chromadb\n",
    "from llama_index.core import StorageContext\n",
    "from llama_index.vector_stores.chroma import ChromaVectorStore\n",
    "# from llama_index.embeddings.fastembed import FastEmbedEmbedding\n",
    "from llama_index.core import VectorStoreIndex, SimpleDirectoryReader\n",
    "from llama_index.core import SimpleDirectoryReader, StorageContext, VectorStoreIndex\n",
    "\n",
    "# embed_model = FastEmbedEmbedding(model_name=\"BAAI/bge-small-en-v1.5\")\n",
    "data_dir = r\"knowledge_base\\raw\\classification\"\n",
    "\n",
    "documents = SimpleDirectoryReader(str(data_dir)).load_data()\n",
    "data_path = r\"knowledge_base\\vector\\classification\"\n",
    "db = chromadb.PersistentClient(path=data_path)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b52b6ba8",
   "metadata": {},
   "source": [
    "### Storing the data locally"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "348df588",
   "metadata": {},
   "outputs": [],
   "source": [
    "chroma_collection = db.get_or_create_collection(\"classification_db\")\n",
    "vector_store = ChromaVectorStore(chroma_collection=chroma_collection)\n",
    "storage_context = StorageContext.from_defaults(vector_store=vector_store)\n",
    "index = VectorStoreIndex.from_documents(\n",
    "    documents=documents,\n",
    "    storage_context=storage_context,\n",
    "    show_progress=True,\n",
    "    # embed_model=embed_model\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f7411c03",
   "metadata": {},
   "source": [
    "### Loading the locally stored vector index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "4d9cbd1b",
   "metadata": {},
   "outputs": [],
   "source": [
    "import chromadb\n",
    "from llama_index.core import StorageContext\n",
    "from llama_index.core import VectorStoreIndex\n",
    "from llama_index.core.retrievers import VectorIndexRetriever\n",
    "from llama_index.vector_stores.chroma import ChromaVectorStore\n",
    "# from llama_index.embeddings.fastembed import FastEmbedEmbedding\n",
    "\n",
    "# embed_model = FastEmbedEmbedding(model_name=\"BAAI/bge-small-en-v1.5\")\n",
    "\n",
    "data_path = r\"knowledge_base\\vector\\classification\"\n",
    "db = chromadb.PersistentClient(path=data_path)\n",
    "chroma_collection = db.get_or_create_collection(\"classification_db\")\n",
    "vector_store = ChromaVectorStore(chroma_collection=chroma_collection)\n",
    "storage_context = StorageContext.from_defaults(vector_store=vector_store)\n",
    "\n",
    "index = VectorStoreIndex.from_vector_store(vector_store, storage_context=storage_context)\n",
    "retriever = VectorIndexRetriever(\n",
    "    index, \n",
    "    # embed_model=embed_model\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "05804310",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "dev",
   "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": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}