{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "04cabe4c",
   "metadata": {},
   "source": [
    "Uncommend and run if dependencies are not installed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "cc4d2b9b",
   "metadata": {},
   "outputs": [],
   "source": [
    "# !pip install -q pyyaml\n",
    "# !pip install -q requests\n",
    "# !pip install -q dotenv\n",
    "# !pip install -qU langchain-community\n",
    "# !pip install -q pypdf\n",
    "# %pip install -qU langchain-groq\n",
    "# !pip install -q chromadb\n",
    "# !pip install -q sentence-transformers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "7cdfaebc",
   "metadata": {},
   "outputs": [],
   "source": [
    "import sys\n",
    "import os\n",
    "\n",
    "project_root = os.path.abspath(\"..\")  # adjust this depending on where your notebook lives\n",
    "if project_root not in sys.path:\n",
    "    sys.path.insert(0, project_root)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "72e187e0",
   "metadata": {},
   "outputs": [],
   "source": [
    "from src.pipeline import ChatPipeline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "f79416f1",
   "metadata": {},
   "outputs": [],
   "source": [
    "from src.utils import load_config"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "ba557b13",
   "metadata": {},
   "outputs": [],
   "source": [
    "cp = ChatPipeline()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "49dc2580",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "d:\\Thesis\\Vinayak Rana\\LLM\\RAG\\src\\embedding.py:16: LangChainDeprecationWarning: The class `HuggingFaceEmbeddings` was deprecated in LangChain 0.2.2 and will be removed in 1.0. An updated version of the class exists in the :class:`~langchain-huggingface package and should be used instead. To use it run `pip install -U :class:`~langchain-huggingface` and import as `from :class:`~langchain_huggingface import HuggingFaceEmbeddings``.\n",
      "  return HuggingFaceEmbeddings(model_name=self.model_name)\n",
      "c:\\Users\\vinny\\Miniconda3\\envs\\scholarchatbot\\lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n",
      "d:\\Thesis\\Vinayak Rana\\LLM\\RAG\\src\\pipeline.py:79: LangChainDeprecationWarning: Since Chroma 0.4.x the manual persistence method is no longer supported as docs are automatically persisted.\n",
      "  vector_store.persist()\n",
      "d:\\Thesis\\Vinayak Rana\\LLM\\RAG\\llm\\answer_generator.py:23: LangChainDeprecationWarning: Please see the migration guide at: https://python.langchain.com/docs/versions/migrating_memory/\n",
      "  self.memory = ConversationBufferWindowMemory(\n"
     ]
    }
   ],
   "source": [
    "cp.setup(arxiv_id=\"2407.05040\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "ca77354b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Based on the provided context, here\\'s a differentiation between Self-Instruct, Evol-Instruct, and OSSInstruct:\\n\\n1. **Self-Instruct**: This technique is used to align language models with self-generated instructions. It involves generating instruction-following data points through the Self-Instruct technique, which is utilized in Codealpaca and CodeLlama. The Self-Instruct technique is described in the paper \"Self-instruct: Aligning language models with self-generated instructions\" by Yizhong Wang et al. (2022).\\n\\n2. **Evol-Instruct**: This technique is used to evolve instruction-following data in both depth and breadth dimensions. It is employed in Wizardcoder to further evolve the Codealpaca dataset. The Evol-Instruct method is described in the paper \"EvolInstruct\" by Can Xu et al. (2023a).\\n\\n3. **OSSInstruct**: This technique is used to create instruction-following data from unlabeled open-source code snippets. It is employed in Magicoder to construct a method. The OSSInstruct technique is not described in detail in the provided context, but it is mentioned as a distinct method used in Magicoder.\\n\\nIn summary, Self-Instruct generates instruction-following data points, Evol-Instruct evolves instruction-following data, and OSSInstruct creates instruction-following data from open-source code snippets.'"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cp.query(\"can you differentiate between self instruct , evol instruct and OSS ?\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "scholarchatbot",
   "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": "3.10.18"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}