Skip to content

[E-1] 14-Chains / 03-StructuredOutputChain #375

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
teddylee777 merged 3 commits into from
Jan 19, 2025
Merged

[E-1] 14-Chains / 03-StructuredOutputChain #375

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
07989c8
[E-1] 14-Chains / 03-StructuredOutputChain
ThePurpleCollar Jan 15, 2025
e615a17
Included langchain project name & Updated imported package to a newe…
ErikaPark Jan 15, 2025
19fce93
[E-1] 14-Chains / 03-StructuredOutputChain
ThePurpleCollar Jan 17, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
262 changes: 262 additions & 0 deletions 14-Chains/03-Structured-Output-Chain.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,262 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "635d8ebb",
"metadata": {},
"source": [
"# Structured Output Chain \n",
"\n",
"- Author: [JeongHo Shin](https://github.com/ThePurpleCollar)\n",
"- Design: \n",
"- Peer Review: \n",
"- This is a part of [LangChain Open Tutorial](https://github.com/LangChain-OpenTutorial/LangChain-OpenTutorial)\n",
"\n",
"[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/LangChain-OpenTutorial/LangChain-OpenTutorial/blob/main/99-TEMPLATE/00-BASE-TEMPLATE-EXAMPLE.ipynb) [![Open in GitHub](https://img.shields.io/badge/Open%20in%20GitHub-181717?style=flat-square&logo=github&logoColor=white)](https://github.com/LangChain-OpenTutorial/LangChain-OpenTutorial/blob/main/99-TEMPLATE/00-BASE-TEMPLATE-EXAMPLE.ipynb)\n",
"\n",
"## Overview\n",
"\n",
"This tutorial demonstrates how to implement Structured output generation using LangChain and OpenAI's language models.\n",
"\n",
"We'll build a quiz generation system that creates multiple-choice questions with consistent formatting and structure.\n",
"\n",
"\n",
"### Table of Contents\n",
"\n",
"- [Overview](#overview)\n",
"- [Environment Setup](#environment-setup)\n",
"- [Implementing Structured Output Chain](#implementing-structured-output-chain)\n",
"- [Invoking Generation Chain](#invoking-generation-chain)\n",
"\n",
"### References\n",
"\n",
"----"
]
},
{
"cell_type": "markdown",
"id": "c6c7aba4",
"metadata": {},
"source": [
"## Environment Setup\n",
"\n",
"Setting up your environment is the first step. See the [Environment Setup](https://wikidocs.net/257836) guide for more details.\n",
"\n",
"\n",
"**[Note]**\n",
"\n",
"The langchain-opentutorial is a package of easy-to-use environment setup guidance, useful functions and utilities for tutorials.\n",
"Check out the [`langchain-opentutorial`](https://github.com/LangChain-OpenTutorial/langchain-opentutorial-pypi) for more details."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "21943adb",
"metadata": {},
"outputs": [],
"source": [
"%%capture --no-stderr\n",
"%pip install langchain-opentutorial"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "f25ec196",
"metadata": {},
"outputs": [],
"source": [
"# Install required packages\n",
"from langchain_opentutorial import package\n",
"\n",
"package.install(\n",
" [\n",
" \"langsmith\",\n",
" \"langchain\",\n",
" \"langchain_core\",\n",
" \"langchain-anthropic\",\n",
" \"langchain_community\",\n",
" \"langchain_text_splitters\",\n",
" \"langchain_openai\",\n",
" ],\n",
" verbose=False,\n",
" upgrade=False,\n",
")"
]
},
{
"cell_type": "markdown",
"id": "690a9ae0",
"metadata": {},
"source": [
"You can set API keys in a `.env` file or set them manually.\n",
"\n",
"[Note] If you’re not using the `.env` file, no worries! Just enter the keys directly in the cell below, and you’re good to go."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "327c2c7c",
"metadata": {},
"outputs": [],
"source": [
"from dotenv import load_dotenv\n",
"from langchain_opentutorial import set_env\n",
"\n",
"# Attempt to load environment variables from a .env file; if unsuccessful, set them manually.\n",
"if not load_dotenv():\n",
" set_env(\n",
" {\n",
" \"OPENAI_API_KEY\": \"\",\n",
" \"LANGCHAIN_API_KEY\": \"\",\n",
" \"LANGCHAIN_TRACING_V2\": \"true\",\n",
" \"LANGCHAIN_ENDPOINT\": \"https://api.smith.langchain.com\",\n",
" \"LANGCHAIN_PROJECT\": \"Structured-Output-Chain\", \n",
" }\n",
" )"
]
},
{
"cell_type": "markdown",
"id": "aa00c3f4",
"metadata": {},
"source": [
"## Implementing Structured Output Chain\n",
"\n",
"This tutorial walks you through the process of generating 4-option multiple-choice quizzes for a given topic.\n",
"\n",
"The `Quiz` class defines the structure of the quiz, including the question, difficulty level, and four answer options.\n",
"\n",
"A `ChatOpenAI` instance leverages the **GPT-4o** model for natural language processing, while a `ChatPromptTemplate` specifies the conversational instructions for generating the quizzes dynamically."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "ea361da4",
"metadata": {},
"outputs": [],
"source": [
"# Import required modules and libraries\n",
"from langchain.chains.openai_functions import create_structured_output_runnable\n",
"from langchain_openai import ChatOpenAI\n",
"from langchain_core.prompts import ChatPromptTemplate\n",
"from pydantic import BaseModel, Field\n",
"from typing import List\n",
"\n",
"# Define the Quiz class - Represents the structure of a 4-option multiple-choice quiz\n",
"class Quiz(BaseModel):\n",
" \"\"\"Extracts information for a 4-option multiple-choice quiz\"\"\"\n",
"\n",
" question: str = Field(..., description=\"The quiz question\") # Quiz question\n",
" level: str = Field(\n",
" ..., description=\"The difficulty level of the quiz (easy, medium, hard)\"\n",
" )\n",
" options: List[str] = Field(..., description=\"The 4 answer options for the quiz\") # Answer options\n",
"\n",
"\n",
"# Set up the GPT-4o model with appropriate parameters\n",
"llm = ChatOpenAI(model=\"gpt-4o\", temperature=0.1)\n",
"\n",
"# Define a prompt template to guide the model in generating quizzes\n",
"prompt = ChatPromptTemplate.from_messages(\n",
" [\n",
" (\n",
" \"system\",\n",
" \"You're a world-famous quizzer and generate quizzes in structured formats.\",\n",
" ),\n",
" (\n",
" \"human\",\n",
" \"Please create a 4-option multiple-choice quiz related to the topic provided below. \"\n",
" \"If possible, base the question on existing trivia but do not directly include details from the topic in the question. \"\n",
" \"\\nTOPIC:\\n{topic}\",\n",
" ),\n",
" (\"human\", \"Tip: Make sure to answer in the correct format\"),\n",
" ]\n",
")\n",
"\n",
"# Create a structured output model to match the Quiz class structure\n",
"llm_with_structured_output = llm.with_structured_output(Quiz)\n",
"\n",
"# Combine the prompt and the structured output model into a single chain\n",
"chain = prompt | llm_with_structured_output"
]
},
{
"cell_type": "markdown",
"id": "e56c8b97",
"metadata": {},
"source": [
"## Invoking Generation Chain"
]
},
{
"cell_type": "markdown",
"id": "609faf0a",
"metadata": {},
"source": [
"In this section, we demonstrate how to invoke the **Structured Output Chain** to generate quizzes dynamically. The chain combines a prompt template and a structured output model to ensure the output adheres to the desired Quiz structure."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "69cb77da",
"metadata": {},
"outputs": [],
"source": [
"# Request the generation of a quiz based on a given topic\n",
"generated_quiz = chain.invoke({\"topic\": \"Korean Food\"})"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "b358b3bc",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Which of the following is a traditional Korean dish made by fermenting vegetables, primarily napa cabbage and Korean radishes, with a variety of seasonings? (Difficulty: medium)\n",
"\n",
"1) Kimchi\n",
"2) Sushi\n",
"3) Tacos\n",
"4) Paella\n"
]
}
],
"source": [
"# Print the generated quiz\n",
"print(f\"{generated_quiz.question} (Difficulty: {generated_quiz.level})\\n\")\n",
"for i, opt in enumerate(generated_quiz.options):\n",
" print(f\"{i+1}) {opt}\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "langchain-opentutorial-W8hXPYms-py3.11",
"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": "3.11.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}