Skip to content

Introduction to Large Language Models with GPT & LangChain

ChatGPT is wildly popular, with over a billion visits per month. Although this web interface is great for many non-technical use cases, for programming and automation tasks, it is better to access GPT (the AI that powers ChatGPT) via the OpenAI API.

As well as GPT, you'll also make use of LangChain, a programming framework for working with generative AI.

You'll cover:

  • Getting set up with an OpenAI developer account and integration with Workspace.
  • Calling the chat functionality in the OpenAI API, with and without langchain.
  • Simple prompt engineering.
  • Holding a conversation with GPT.
  • Ideas for incorporating GPT into a data analysis or data science workflow.

You'll be using GPT to explore a dataset about electric cars in Washington state, USA.

Maintenance note, May 2024

Since this code-along was released, the Python packages for working with the OpenAI API have changed their syntax. The instructions, hints, and code have been updated to use the latest syntax, but the video has not been updated. Consequently, it is now slightly out of sync. Trust the workbook, not the video.

Before you begin

You'll need a developer account with OpenAI.

See getting-started.ipynb for steps on how to create an API key and store it in Workspace. In particular, you'll need to follow the instructions in the "Getting started with OpenAI" and "Setting up Workspace Integrations" sections.

Task 0: Setup

We need to update the openai package, and install the langchain and langchain-openai packages. These are currently being developed quickly, sometimes with breaking changes, so we fix the versions.

langchain depends on a recent version of typing_extensions, so we need to update that package, again fixing the version.

The versions suggested here are the latest package versions as of May 2024. If you prefer to try the latest versions, search on PyPI to find them. Note that these future versions have not been tested by DataCamp, so some instructions may not match the code you need to write.

Instructions

Run the following code to install the openai, langchain, langchain-openai, and typing_extensions packages.

# Install the openai package, locked to version 1.27
!pip install openai==1.27

# Install the langchain package, locked to version 0.1.19
!pip install langchain==0.1.19

# Install the langchain-openai package, locked to version 0.1.6
!pip install langchain-openai==0.1.6

# Update the typing_extensions package, locked to version 4.11.0
!pip install typing_extensions==4.11.0
Hidden output

In order to chat with GPT, we need first need to load the openai and os packages to set the API key from the environment variables you just created.

Instructions

  • Import the os package.
  • Import the openai package.
  • Set openai.api_key to the OPENAI_API_KEY environment variable.
# Import the os package
import os



# Import the openai package
import openai

# Set openai.api_key to the OPENAI_API_KEY environment variable
openai_api_key = os.environ["OPENAI_API_KEY"]

We need to import the langchain package. It has many submodules, so to save typing later, we'll also import some specific functions from those submodules.

Instructions

  • Import the langchain package as lc.
  • From the langchain_openai package, import OpenAI. Notice the underscore in the package name.
  • From the langchain.schema module, import AIMessage, HumanMessage, SystemMessage.
# Import the langchain package as lc
import langchain as lc

# From the langchain_openai package, import OpenAI, ChatOpenAI
from langchain.chat_models import ChatOpenAI

# From the langchain.schema module, import AIMessage, HumanMessage, SystemMessage
from langchain.schema import AIMessage, HumanMessage, SystemMessage
‌
‌
‌