{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "os.environ['LANGCHAIN_TRACING_V2'] = 'true'\n",
    "os.environ['LANGCHAIN_ENDPOINT'] = 'https://api.smith.langchain.com'\n",
    "# os.environ['LANGCHAIN_API_KEY'] = <your api key>\n",
    "\n",
    "os.environ['OPENAI_API_BASE'] = 'http://192.168.1.7:1234/v1/'\n",
    "os.environ['OPENAI_API_KEY'] = 'lm-studio'"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Load documents"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pathlib import Path\n",
    "\n",
    "from langchain_community.document_loaders import TextLoader\n",
    "\n",
    "\n",
    "data_path = Path(\"vs_data\")\n",
    "\n",
    "documents = [\n",
    "    TextLoader(doc_path).load()[0]\n",
    "    for doc_path in data_path.iterdir()\n",
    "]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Split documents"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
    "text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(\n",
    "    chunk_size=300, \n",
    "    chunk_overlap=50)\n",
    "\n",
    "splits = text_splitter.split_documents(documents)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_openai import OpenAIEmbeddings\n",
    "from langchain_community.vectorstores import Chroma\n",
    "\n",
    "vectorstore = Chroma.from_documents(documents=splits, \n",
    "                                    embedding=OpenAIEmbeddings(model='nomic-ai/nomic-embed-text-v1.5-GGUF', check_embedding_ctx_length=False, timeout=0.1, max_retries=50))\n",
    "\n",
    "retriever = vectorstore.as_retriever()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Create chain"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'The evolution of Lightning Ring is Thunder Loop. To get Thunder Loop, you need to evolve Lightning Ring with Duplicator.'"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from langchain.prompts import ChatPromptTemplate\n",
    "from langchain_core.output_parsers import StrOutputParser\n",
    "from langchain_openai import ChatOpenAI\n",
    "from langchain_core.runnables import RunnablePassthrough\n",
    "\n",
    "template = \"\"\"Answer the question based on the context below. If the\n",
    "question cannot be answered using the information provided answer\n",
    "with \"I don't know\".\n",
    "\n",
    "Context: {context}\n",
    "\n",
    "Question: {question}\n",
    "\n",
    "Answer: \"\"\"\n",
    "\n",
    "prompt = ChatPromptTemplate.from_template(template)\n",
    "\n",
    "llm = ChatOpenAI(temperature=0)\n",
    "\n",
    "def format_docs(docs):\n",
    "    return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
    "\n",
    "rag_chain = (\n",
    "    {\"context\": retriever | format_docs, \n",
    "     \"question\": RunnablePassthrough()} \n",
    "    | prompt\n",
    "    | llm\n",
    "    | StrOutputParser()\n",
    ")\n",
    "\n",
    "rag_chain.invoke(\"What is the evolution of Lightning ring and how do i get it?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}