Environment variables for selfhost deployments.
Few examples to get you started
CODE
Authentication with OpenAI API KeyUsers required to input access password to use the API, they can also using their own api key to use NextChat.
Variable Name | Value |
---|---|
CODE | password1 |
OPENAI_API_KEY | sk_xxxxx |
Variable Name | Value |
---|---|
OPENAI_API_KEY | sk_xxxxx |
Variable Name | Value |
---|---|
AZURE_URL | https://{azure-resource-url}/openai/deployments/{deploy-name} |
AZURE_API_KEY | azure_key_123456 |
AZURE_API_VERSION | 2022-06-01-preview |
Variable Name | Value |
---|---|
GOOGLE_API_KEY | google_key_123456 |
Variable Name | Required | Default Value | Description | Example |
---|---|---|---|---|
CODE | Optional | Access password, separated by comma. | password1,password2 | |
OPENAI_API_KEY | Required | Your OpenAI API key, join multiple API keys with comma. | key1,key2 | |
BASE_URL | Optional | https://api.openai.com | Override OpenAI API request base URL. | http://your-openai-proxy.com |
OPENAI_ORG_ID | Optional | Specify OpenAI organization ID. | org-1234 | |
AZURE_URL | Optional | Azure deploy URL. | https://{azure-resource-url}/openai/deployments/{deploy-name} | |
AZURE_API_KEY | Optional | Azure API Key. | azure_key_123456 | |
AZURE_API_VERSION | Optional | Azure API Version, find it at Azure Documentation. | 2022-06-01-preview | |
GOOGLE_API_KEY | Optional | Google Gemini Pro API Key. | google_key_123456 | |
GOOGLE_URL | Optional | Google Gemini Pro API URL. | https://googleapis.com/gemini/v1 | |
HIDE_USER_API_KEY | Optional | Empty | If you do not want users to input their own API key, set this value to 1. | 1 |
DISABLE_GPT4 | Optional | Empty | If you do not want users to use GPT-4, set this value to 1. | 1 |
ENABLE_BALANCE_QUERY | Optional | Empty | If you do want users to query balance, set this value to 1, or you should set it to 0. | 1 |
DISABLE_FAST_LINK | Optional | Empty | If you want to disable parse settings from URL, set this to 1. | 1 |
CUSTOM_MODELS | Optional | Empty | To control custom models, use + to add a custom model, use - to hide a model, use name=displayName to customize model name, separated by comma. | +llama,+claude-2,-gpt-3.5-turbo,gpt-4-1106-preview=gpt-4-turbo |