Feat: Add Azure support (#219)

feat(api): add support for Azure OpenAI API

- Add Azure OpenAI API environment variables to .env.example
- Modify chatgpt-client.js to use Azure OpenAI API if environment variables are present
- Modify askOpenAI.js to use arrow function syntax
- Modify handlers.js to add console.log statement for partial variable
This commit is contained in:
Danny Avila 2023-05-09 17:42:55 -04:00 committed by GitHub
parent e2dc994b63
commit 5dd9c11326
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
7 changed files with 144 additions and 25 deletions

View file

@ -36,6 +36,23 @@ OPENAI_MODELS=gpt-3.5-turbo,gpt-3.5-turbo-0301,text-davinci-003,gpt-4
# https://github.com/waylaidwanderer/node-chatgpt-api#using-a-reverse-proxy
# OPENAI_REVERSE_PROXY=
##########################
# AZURE Endpoint:
##########################
# To use Azure with this project, set the following variables. These will be used to build the API URL.
# Chat completion:
# `https://{AZURE_OPENAI_API_INSTANCE_NAME}.openai.azure.com/openai/deployments/{AZURE_OPENAI_API_DEPLOYMENT_NAME}/chat/completions?api-version={AZURE_OPENAI_API_VERSION}`;
# You should also consider changing the `OPENAI_MODELS` variable above to the models available in your instance/deployment.
# Note: I've noticed that the Azure API is much faster than the OpenAI API, so the streaming looks almost instantaneous.
# AZURE_OPENAI_API_KEY=
# AZURE_OPENAI_API_INSTANCE_NAME=
# AZURE_OPENAI_API_DEPLOYMENT_NAME=
# AZURE_OPENAI_API_VERSION=
# AZURE_OPENAI_API_COMPLETIONS_DEPLOYMENT_NAME= # Optional, but may be used in future updates
# AZURE_OPENAI_API_EMBEDDINGS_DEPLOYMENT_NAME= # Optional, but may be used in future updates
##########################
# BingAI Endpoint:
##########################