{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.vectorstores import FAISS\n",
    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
    "from langchain import OpenAI\n",
    "from langchain.chains import RetrievalQA\n",
    "from langchain.document_loaders import DirectoryLoader\n",
    "import magic\n",
    "import os\n",
    "import nltk\n",
    "\n",
    "openai_api_key = os.getenv(\"OPENAI_API_KEY\")\n",
    "data_location= os.getenv(\"VECTOR_DATA_DIR\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Chroma"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from modules.vector_stores.vector_stores.chroma_manager import get_default_chroma_mgr\n",
    "\n",
    "chroma_mgr = get_default_chroma_mgr(persisted=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "chroma_mgr.persist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from modules.vector_stores.retrieval.basic_qa import get_default_qa\n",
    "\n",
    "qa = get_default_qa(chroma_mgr.db)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Cite sources\n",
    "def process_llm_response(llm_response):\n",
    "    print(llm_response['result'])\n",
    "    print('\\n\\nSources:')\n",
    "    for source in llm_response[\"source_documents\"]:\n",
    "        print(source.metadata['source'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# full example\n",
    "query = \"What is a date table?\"\n",
    "resp = qa.ask(query)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## FAISS"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from modules.vector_stores.loaders.pypdf_load_strategy import PyPDFLoadStrategy, PyPDFConfig, get_default_pypdf_loader\n",
    "from modules.vector_stores.embedding.openai import OpenAIEmbeddings, OpenAIEmbedConfig, get_default_openai_embeddings\n",
    "def get_example_pdf_embedding():\n",
    "    dir_location = \"../data\"\n",
    "    loader = get_default_pypdf_loader(dir_location)\n",
    "    documents = loader.load()\n",
    "    embeddings = get_default_openai_embeddings()\n",
    "    index = FAISS.from_documents(documents, embeddings)\n",
    "    return index\n",
    "index = get_example_pdf_embedding()\n",
    "llm = OpenAI(openai_api_key=openai_api_key)\n",
    "qa = RetrievalQA.from_chain_type(llm=llm, chain_type=\"stuff\", retriever=index.as_retriever())\n",
    "qa = RetrievalQA.from_chain_type(llm=llm,\n",
    "                                chain_type=\"stuff\",\n",
    "                                retriever=index.as_retriever(),\n",
    "                                return_source_documents=True)\n",
    "query = \"What is a date table?\"\n",
    "result = qa({\"query\": query})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "docsearch = FAISS.from_documents(documents, embeddings)\n",
    "llm = OpenAI(openai_api_key=openai_api_key)\n",
    "qa = RetrievalQA.from_chain_type(llm=llm, chain_type=\"stuff\", retriever=docsearch.as_retriever())\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "qa = RetrievalQA.from_chain_type(llm=llm,\n",
    "                                chain_type=\"stuff\",\n",
    "                                retriever=docsearch.as_retriever(),\n",
    "                                return_source_documents=True)\n",
    "query = \"What is a date table?\"\n",
    "result = qa({\"query\": query})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "result\n"
   ]
  }
 ],
 "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": "3.10.6"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}