Berry

ChatGPT clone, GPT-4, Bing, Anthropic, DALL-E-3, Plugins, Multi-User

LibreChat

VectorDB 🗃️

 RAG API 📚

LibreChat 🪶

Email login. Set to true or false to enable or disable ONLY email login

Email registration of new users. Set to true or false to enable or disable Email registration

Allow users to connect to LibreChat with various social networks, see below. Set to true or false to enable or disable

Enable or disable registration of new user using various social network. Set to true or false to enable or disable

https://docs.librechat.ai/install/configuration/dotenv.html#anthropic

https://docs.librechat.ai/install/configuration/dotenv.html#customization

https://docs.librechat.ai/install/configuration/dotenv.html#azure

How long the user and associated IP are banned for (in milliseconds)

The user will be banned everytime their score reaches/crosses over the interval threshold

Whether or not to enable banning users for violations (they will still be logged)

https://docs.librechat.ai/install/configuration/dotenv.html#bingai

https://docs.librechat.ai/install/configuration/dotenv.html#chatgpt

https://docs.librechat.ai/install/configuration/dotenv.html#balance

The max amount of messages a user can send per request

here you can put a local path of a volume or a link. In railway the best way imo it's to upload the file on Github and paste here the link of the file

change the default "All AI conversations in one place"

Enable verbose server output in the console with 'true' , though it's not recommended due to high verbosity.

https://docs.librechat.ai/install/configuration/dotenv.html#logging

Set to true to enable debug mode for the OpenAI endpoint

Set to false to disable debug mode for plugins

https://docs.librechat.ai/install/configuration/dotenv.html#discord-authentication

customize the available endpoints in LibreChat

https://docs.librechat.ai/install/configuration/dotenv.html#facebook-authentication

https://docs.librechat.ai/install/configuration/dotenv.html#github-authentication

https://docs.librechat.ai/install/configuration/dotenv.html#google-authentication

https://docs.librechat.ai/install/configuration/dotenv.html#google

Whether to limit the amount of messages a user can send per request

Whether to limit the amount of messages an IP can send per MESSAGE_IP_WINDOW

Whether to limit the amount of messages an IP can send per MESSAGE_USER_WINDOW

The max amount of logins allowed per IP per LOGIN_WINDOW

https://docs.librechat.ai/install/configuration/dotenv.html#score-for-each-violation

In minutes, determines the window of time for LOGIN_MAX logins

disable anonymized telemetry analytics for MeiliSearch for absolute privacy

The max amount of messages an IP can send per MESSAGE_IP_WINDOW

In minutes, determines the window of time for MESSAGE_IP_MAX messages

In minutes, determines the window of time for MESSAGE_USER_MAX messages

https://docs.librechat.ai/install/configuration/dotenv.html#prevent-public-search-engines-indexing

https://docs.librechat.ai/install/configuration/dotenv.html#openai

For Local LLM APIs, sometimes use prompt payload (not messages) to mimic /v1/completions instead of /v1/chat/completions for specific LocalAI models

Set to true or false, Whether or not to enable OpenAI moderation on the OpenAI and Plugins endpoints

https://docs.librechat.ai/install/configuration/dotenv.html#moderation

must be compatible with the OpenAI Endpoint

https://docs.librechat.ai/install/configuration/dotenv.html#openrouter

In minutes, determines the window of time for REGISTER_MAX registrations

enables search in messages and conversations