All functionality related to OpenAI

OpenAI is American artificial intelligence (AI) research laboratoryconsisting of the non-profitOpenAI Incorporatedand its for-profit subsidiary corporationOpenAI Limited Partnership.OpenAI conducts AI research with the declared intention of promoting and developing a friendly AI.OpenAI systems run on anAzure-based supercomputing platform fromMicrosoft.

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

ChatGPT is the Artificial Intelligence (AI) chatbot developed byOpenAI.

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)

Chat model​

See ausage example.

from langchain_openaiimport ChatOpenAI

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

from langchain_openaiimport AzureChatOpenAI

For a more detailed walkthrough of theAzure wrapper, seehere.

LLM​

See ausage example.

from langchain_openaiimport OpenAI

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

from langchain_openaiimport AzureOpenAI

For a more detailed walkthrough of theAzure wrapper, seehere.

Embedding Model​

See ausage example

from langchain_openaiimport OpenAIEmbeddings

Document Loader​

See ausage example.

from langchain_community.document_loaders.chatgptimport ChatGPTLoader

Retriever​

See ausage example.

from langchain.retrieversimport ChatGPTPluginRetriever

Tools​

Dall-E Image Generator​

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

See ausage example.

from langchain_community.utilities.dalle_image_generatorimport DallEAPIWrapper

Adapter​

See ausage example.

from langchain.adaptersimport openaias lc_openai

Tokenizer​

There are several places you can use thetiktoken tokenizer. By default, it is used to count tokensfor OpenAI LLMs.

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

from langchain.text_splitterimport CharacterTextSplitter
CharacterTextSplitter.from_tiktoken_encoder(...)

For a more detailed walkthrough of this, seethis notebook

Chain​

See ausage example.

from langchain.chainsimport OpenAIModerationChain