Skip to main content

OpenAI

All functionality related to OpenAI

OpenAI is American artificial intelligence (AI) research laboratory consisting of the non-profit OpenAI Incorporated and its for-profit subsidiary corporation OpenAI Limited Partnership. OpenAI conducts AI research with the declared intention of promoting and developing a friendly AI. OpenAI systems run on an Azure-based supercomputing platform from Microsoft.

The OpenAI API is powered by a diverse set of models with different capabilities and price points.

ChatGPT is the Artificial Intelligence (AI) chatbot developed by OpenAI.

Installation and Setup

Install the integration package with

pip install langchain-openai

Get an OpenAI api key and set it as an environment variable (OPENAI_API_KEY)

LLM

See a usage example.

from langchain_openai import OpenAI

API Reference:

If you are using a model hosted on Azure, you should use different wrapper for that:

from langchain_openai import AzureOpenAI

API Reference:

For a more detailed walkthrough of the Azure wrapper, see here

Chat model

See a usage example.

from langchain_openai import ChatOpenAI

API Reference:

If you are using a model hosted on Azure, you should use different wrapper for that:

from langchain_openai import AzureChatOpenAI

API Reference:

For a more detailed walkthrough of the Azure wrapper, see here

Embedding Model

See a usage example

from langchain_openai import OpenAIEmbeddings

API Reference:

Document Loader

See a usage example.

from langchain_community.document_loaders.chatgpt import ChatGPTLoader

API Reference:

Retriever

See a usage example.

from langchain.retrievers import ChatGPTPluginRetriever

Tools

Dall-E Image Generator

OpenAI Dall-E are text-to-image models developed by OpenAI using deep learning methodologies to generate digital images from natural language descriptions, called "prompts".

See a usage example.

from langchain_community.utilities.dalle_image_generator import DallEAPIWrapper

API Reference:

Adapter

See a usage example.

from langchain.adapters import openai as lc_openai

Tokenizer

There are several places you can use the tiktoken tokenizer. By default, it is used to count tokens for OpenAI LLMs.

You can also use it to count tokens when splitting documents with

from langchain.text_splitter import CharacterTextSplitter
CharacterTextSplitter.from_tiktoken_encoder(...)

API Reference:

For a more detailed walkthrough of this, see this notebook

Chain

See a usage example.

from langchain.chains import OpenAIModerationChain

API Reference:


Help us out by providing feedback on this documentation page: