{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "import datetime\n",
    "import gradio as gr\n",
    "from dotenv import load_dotenv\n",
    "from langchain.vectorstores import Chroma\n",
    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
    "from langchain.chat_models import ChatOpenAI\n",
    "from langchain.prompts import PromptTemplate\n",
    "from langchain.chains import RetrievalQA\n",
    "from langchain.chains import ConversationalRetrievalChain\n",
    "from langchain.memory import ConversationBufferMemory\n",
    "\n",
    "\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# from langchain.memory import MemoryViewMemory\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "gpt-3.5-turbo-0301\n"
     ]
    }
   ],
   "source": [
    "import datetime\n",
    "current_date = datetime.datetime.now().date()\n",
    "if current_date < datetime.date(2023, 9, 2):\n",
    "    llm_name = \"gpt-3.5-turbo-0301\"\n",
    "else:\n",
    "    llm_name = \"gpt-3.5-turbo\"\n",
    "print(llm_name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "def chatWithNCAIR(question, history):\n",
    "    load_dotenv()\n",
    "\n",
    "    persist_directory = 'docs/chroma/'\n",
    "    embedding = OpenAIEmbeddings()\n",
    "    vectordb = Chroma(persist_directory=persist_directory, embedding_function=embedding)\n",
    "    llm = ChatOpenAI(model_name=llm_name, temperature=0)\n",
    "\n",
    "    template = \"\"\"Use the following pieces of context to answer the question at the end. \n",
    "    If you don't know the answer, just say that you don't know, don't try to make up an answer. \n",
    "    Use three sentences maximum. Keep the answer as concise as possible. \n",
    "    Always say \"thank you for choosing NCAIR BOT!\" at the end of the answer. \n",
    "    {context}\n",
    "    Question: {question}\n",
    "    Helpful Answer:\"\"\"\n",
    "    QA_CHAIN_PROMPT = PromptTemplate(input_variables=[\"context\", \"question\"],template=template,)\n",
    "\n",
    "    # Run chain\n",
    "    from langchain.chains import RetrievalQA\n",
    "    # question = \"Will interns go through the fabLab during the onboarding?\"\n",
    "    qa_chain = RetrievalQA.from_chain_type(llm,\n",
    "        retriever=vectordb.as_retriever(),\n",
    "        return_source_documents=True,\n",
    "        chain_type_kwargs={\"prompt\": QA_CHAIN_PROMPT})\n",
    "\n",
    "    memory = ConversationBufferMemory(\n",
    "    memory_key=\"chat_history\",\n",
    "    return_messages=True\n",
    "    )\n",
    "    retriever=vectordb.as_retriever()\n",
    "    qa = ConversationalRetrievalChain.from_llm(\n",
    "    llm,\n",
    "    retriever=retriever,\n",
    "    memory=memory\n",
    "    )\n",
    "\n",
    "\n",
    "    result = qa({\"question\": question})\n",
    "    return result[\"answer\"]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Yes, as an intern in NCAIR, you will first undergo the onboarding session in Fablab, PCB, shopbot, 3D printing, solid work, and then go through compulsory NADIT programs.'"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chatWithNCAIR(\"Will interns go through the fabLab during the onboarding?\",\"\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# chatWithNCAIR(\"Is it compulsory?\",\"\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "# ! pip install --upgrade gradio"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:7860\n",
      "Running on public URL: https://0e3e0326bf1f8474c9.gradio.live\n",
      "\n",
      "This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"https://0e3e0326bf1f8474c9.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": []
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "demo = gr.ChatInterface(fn=chatWithNCAIR,\n",
    "    chatbot=gr.Chatbot(height=300, min_width=40),\n",
    "    textbox=gr.Textbox(placeholder=\"Ask me a question relating to NCAIR\"),\n",
    "    title=\"Chat with NCAIR💬\",\n",
    "    description=\"Ask NCAIR any question\",\n",
    "    theme=\"soft\",\n",
    "    cache_examples=True,\n",
    "    retry_btn=None,\n",
    "    undo_btn=\"Delete Previous\",\n",
    "    clear_btn=\"Clear\",)\n",
    "\n",
    "demo.launch(share=True)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.10.8"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}