langchain/docs/modules/prompts/output_parsers/examples/structured.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "91871002",
   "metadata": {},
   "source": [
    "# Structured Output Parser\n",
    "\n",
    "While the Pydantic/JSON parser is more powerful, we initially experimented data structures having text fields only."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b492997a",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.output_parsers import StructuredOutputParser, ResponseSchema\n",
    "from langchain.prompts import PromptTemplate, ChatPromptTemplate, HumanMessagePromptTemplate\n",
    "from langchain.llms import OpenAI\n",
    "from langchain.chat_models import ChatOpenAI"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "09473dce",
   "metadata": {},
   "source": [
    "Here we define the response schema we want to receive."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "432ac44a",
   "metadata": {},
   "outputs": [],
   "source": [
    "response_schemas = [\n",
    "    ResponseSchema(name=\"answer\", description=\"answer to the user's question\"),\n",
    "    ResponseSchema(name=\"source\", description=\"source used to answer the user's question, should be a website.\")\n",
    "]\n",
    "output_parser = StructuredOutputParser.from_response_schemas(response_schemas)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7b92ce96",
   "metadata": {},
   "source": [
    "We now get a string that contains instructions for how the response should be formatted, and we then insert that into our prompt."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "593cfc25",
   "metadata": {},
   "outputs": [],
   "source": [
    "format_instructions = output_parser.get_format_instructions()\n",
    "prompt = PromptTemplate(\n",
    "    template=\"answer the users question as best as possible.\\n{format_instructions}\\n{question}\",\n",
    "    input_variables=[\"question\"],\n",
    "    partial_variables={\"format_instructions\": format_instructions}\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0943e783",
   "metadata": {},
   "source": [
    "We can now use this to format a prompt to send to the language model, and then parse the returned result."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "106f1ba6",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = OpenAI(temperature=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "86d9d24f",
   "metadata": {},
   "outputs": [],
   "source": [
    "_input = prompt.format_prompt(question=\"what's the capital of france\")\n",
    "output = model(_input.to_string())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "956bdc99",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'answer': 'Paris', 'source': 'https://en.wikipedia.org/wiki/Paris'}"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "output_parser.parse(output)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "da639285",
   "metadata": {},
   "source": [
    "And here's an example of using this in a chat model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "8f483d7d",
   "metadata": {},
   "outputs": [],
   "source": [
    "chat_model = ChatOpenAI(temperature=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "f761cbf1",
   "metadata": {},
   "outputs": [],
   "source": [
    "prompt = ChatPromptTemplate(\n",
    "    messages=[\n",
    "        HumanMessagePromptTemplate.from_template(\"answer the users question as best as possible.\\n{format_instructions}\\n{question}\")  \n",
    "    ],\n",
    "    input_variables=[\"question\"],\n",
    "    partial_variables={\"format_instructions\": format_instructions}\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "edd73ae3",
   "metadata": {},
   "outputs": [],
   "source": [
    "_input = prompt.format_prompt(question=\"what's the capital of france\")\n",
    "output = chat_model(_input.to_messages())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "a3c8b91e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'answer': 'Paris', 'source': 'https://en.wikipedia.org/wiki/Paris'}"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "output_parser.parse(output.content)"
   ]
  }
 ],
 "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
}