{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "872bb8b5",
   "metadata": {},
   "source": [
    "# Transformation\n",
    "\n",
    "This notebook showcases using a generic transformation chain.\n",
    "\n",
    "As an example, we will create a dummy transformation that takes in a super long text, filters the text to only the first 3 paragraphs, and then passes that into an `LLMChain` to summarize those."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "bbbb4330",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.chains import TransformChain, LLMChain, SimpleSequentialChain\n",
    "from langchain.llms import OpenAI\n",
    "from langchain.prompts import PromptTemplate"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "8ae5937c",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"../../state_of_the_union.txt\") as f:\n",
    "    state_of_the_union = f.read()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "98739592",
   "metadata": {},
   "outputs": [],
   "source": [
    "def transform_func(inputs: dict) -> dict:\n",
    "    text = inputs[\"text\"]\n",
    "    shortened_text = \"\\n\\n\".join(text.split(\"\\n\\n\")[:3])\n",
    "    return {\"output_text\": shortened_text}\n",
    "\n",
    "\n",
    "transform_chain = TransformChain(\n",
    "    input_variables=[\"text\"], output_variables=[\"output_text\"], transform=transform_func\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "e9397934",
   "metadata": {},
   "outputs": [],
   "source": [
    "template = \"\"\"Summarize this text:\n",
    "\n",
    "{output_text}\n",
    "\n",
    "Summary:\"\"\"\n",
    "prompt = PromptTemplate(input_variables=[\"output_text\"], template=template)\n",
    "llm_chain = LLMChain(llm=OpenAI(), prompt=prompt)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "06f51f17",
   "metadata": {},
   "outputs": [],
   "source": [
    "sequential_chain = SimpleSequentialChain(chains=[transform_chain, llm_chain])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "f7caa1ee",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "' The speaker addresses the nation, noting that while last year they were kept apart due to COVID-19, this year they are together again. They are reminded that regardless of their political affiliations, they are all Americans.'"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sequential_chain.run(state_of_the_union)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e3ca6409",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}