{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "aa309a80",
   "metadata": {},
   "source": [
    "# QA Eval"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "9c01a3a5",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.evaluation.qa.chat_eval_chain import QAEvalChatChain\n",
    "from langchain.chat_models import ChatOpenAI\n",
    "\n",
    "model = ChatOpenAI(temperature=0)\n",
    "\n",
    "eval_chain = QAEvalChatChain.from_model(model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "c12568a6",
   "metadata": {},
   "outputs": [],
   "source": [
    "examples = [\n",
    "    {\n",
    "        \"question\": \"Roger has 5 tennis balls. He buys 2 more cans of tennis balls. Each can has 3 tennis balls. How many tennis balls does he have now?\",\n",
    "        \"answer\": \"11\"\n",
    "    },\n",
    "    {\n",
    "        \"question\": 'Is the following sentence plausible? \"Joao Moutinho caught the screen pass in the NFC championship.\"',\n",
    "        \"answer\": \"No\"\n",
    "    }\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "207bb5b6",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.prompts import PromptTemplate\n",
    "from langchain.chains import LLMChain\n",
    "from langchain.llms import OpenAI"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "3d4b9cda",
   "metadata": {},
   "outputs": [],
   "source": [
    "prompt = PromptTemplate(template=\"Question: {question}\\nAnswer:\", input_variables=[\"question\"])\n",
    "llm = OpenAI(model_name=\"text-davinci-003\", temperature=0)\n",
    "chain = LLMChain(llm=llm, prompt=prompt)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "c03c4047",
   "metadata": {},
   "outputs": [],
   "source": [
    "predictions = chain.apply(examples)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "3871729e",
   "metadata": {},
   "outputs": [],
   "source": [
    "graded_outputs = eval_chain.evaluate(examples, predictions, question_key=\"question\", prediction_key=\"text\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "788f841a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Example 0:\n",
      "Question: Roger has 5 tennis balls. He buys 2 more cans of tennis balls. Each can has 3 tennis balls. How many tennis balls does he have now?\n",
      "Real Answer: 11\n",
      "Predicted Answer:  11 tennis balls\n",
      "Predicted Grade: GRADE: CORRECT\n",
      "\n",
      "Example 1:\n",
      "Question: Is the following sentence plausible? \"Joao Moutinho caught the screen pass in the NFC championship.\"\n",
      "Real Answer: No\n",
      "Predicted Answer:  No, this sentence is not plausible. Joao Moutinho is a professional soccer player, not an American football player, so it is not likely that he would be catching a screen pass in the NFC championship.\n",
      "Predicted Grade: GRADE: CORRECT\n",
      "\n"
     ]
    }
   ],
   "source": [
    "for i, eg in enumerate(examples):\n",
    "    print(f\"Example {i}:\")\n",
    "    print(\"Question: \" + eg['question'])\n",
    "    print(\"Real Answer: \" + eg['answer'])\n",
    "    print(\"Predicted Answer: \" + predictions[i]['text'])\n",
    "    print(\"Predicted Grade: \" + graded_outputs[i]['text'])\n",
    "    print()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2a8d822c",
   "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": "3.9.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}