mirror of
https://github.com/danny-avila/LibreChat.git
synced 2025-12-17 00:40:14 +01:00
317a1bd8da
* refactor: pass model in message edit payload, use encoder in standalone util function * feat: add summaryBuffer helper * refactor(api/messages): use new countTokens helper and add auth middleware at top * wip: ConversationSummaryBufferMemory * refactor: move pre-generation helpers to prompts dir * chore: remove console log * chore: remove test as payload will no longer carry tokenCount * chore: update getMessagesWithinTokenLimit JSDoc * refactor: optimize getMessagesForConversation and also break on summary, feat(ci): getMessagesForConversation tests * refactor(getMessagesForConvo): count '00000000-0000-0000-0000-000000000000' as root message * chore: add newer model to token map * fix: condition was point to prop of array instead of message prop * refactor(BaseClient): use object for refineMessages param, rename 'summary' to 'summaryMessage', add previous_summary refactor(getMessagesWithinTokenLimit): replace text and tokenCount if should summarize, summary, and summaryTokenCount are present fix/refactor(handleContextStrategy): use the right comparison length for context diff, and replace payload first message when a summary is present * chore: log previous_summary if debugging * refactor(formatMessage): assume if role is defined that it's a valid value * refactor(getMessagesWithinTokenLimit): remove summary logic refactor(handleContextStrategy): add usePrevSummary logic in case only summary was pruned refactor(loadHistory): initial message query will return all ordered messages but keep track of the latest summary refactor(getMessagesForConversation): use object for single param, edit jsdoc, edit all files using the method refactor(ChatGPTClient): order messages before buildPrompt is called, TODO: add convoSumBuffMemory logic * fix: undefined handling and summarizing only when shouldRefineContext is true * chore(BaseClient): fix test results omitting system role for summaries and test edge case * chore: export summaryBuffer from index file * refactor(OpenAIClient/BaseClient): move refineMessages to subclass, implement LLM initialization for summaryBuffer * feat: add OPENAI_SUMMARIZE to enable summarizing, refactor: rename client prop 'shouldRefineContext' to 'shouldSummarize', change contextStrategy value to 'summarize' from 'refine' * refactor: rename refineMessages method to summarizeMessages for clarity * chore: clarify summary future intent in .env.example * refactor(initializeLLM): handle case for either 'model' or 'modelName' being passed * feat(gptPlugins): enable summarization for plugins * refactor(gptPlugins): utilize new initializeLLM method and formatting methods for messages, use payload array for currentMessages and assign pastMessages sooner * refactor(agents): use ConversationSummaryBufferMemory for both agent types * refactor(formatMessage): optimize original method for langchain, add helper function for langchain messages, add JSDocs and tests * refactor(summaryBuffer): add helper to createSummaryBufferMemory, and use new formatting helpers * fix: forgot to spread formatMessages also took opportunity to pluralize filename * refactor: pass memory to tools, namely openapi specs. not used and may never be used by new method but added for testing * ci(formatMessages): add more exhaustive checks for langchain messages * feat: add debug env var for OpenAI * chore: delete unnecessary comments * chore: add extra note about summary feature * fix: remove tokenCount from payload instructions * fix: test fail * fix: only pass instructions to payload when defined or not empty object * refactor: fromPromptMessages is deprecated, use renamed method fromMessages * refactor: use 'includes' instead of 'startsWith' for extended OpenRouter compatibility * fix(PluginsClient.buildPromptBody): handle undefined message strings * chore: log langchain titling error * feat: getModelMaxTokens helper * feat: tokenSplit helper * feat: summary prompts updated * fix: optimize _CUT_OFF_SUMMARIZER prompt * refactor(summaryBuffer): use custom summary prompt, allow prompt to be passed, pass humanPrefix and aiPrefix to memory, along with any future variables, rename messagesToRefine to context * fix(summaryBuffer): handle edge case where messagesToRefine exceeds summary context, refactor(BaseClient): allow custom maxContextTokens to be passed to getMessagesWithinTokenLimit, add defined check before unshifting summaryMessage, update shouldSummarize based on this refactor(OpenAIClient): use getModelMaxTokens, use cut-off message method for summary if no messages were left after pruning * fix(handleContextStrategy): handle case where incoming prompt is bigger than model context * chore: rename refinedContent to splitText * chore: remove unnecessary debug log
378 lines
16 KiB
Text
378 lines
16 KiB
Text
##########################
|
|
# Server configuration:
|
|
##########################
|
|
|
|
APP_TITLE=LibreChat
|
|
|
|
# The server will listen to localhost:3080 by default. You can change the target IP as you want.
|
|
# If you want to make this server available externally, for example to share the server with others
|
|
# or expose this from a Docker container, set host to 0.0.0.0 or your external IP interface.
|
|
# Tips: Setting host to 0.0.0.0 means listening on all interfaces. It's not a real IP.
|
|
# Use localhost:port rather than 0.0.0.0:port to access the server.
|
|
# Set Node env to development if running in dev mode.
|
|
HOST=localhost
|
|
PORT=3080
|
|
|
|
# Automated Moderation System
|
|
# The Automated Moderation System uses a scoring mechanism to track user violations. As users commit actions
|
|
# like excessive logins, registrations, or messaging, they accumulate violation scores. Upon reaching
|
|
# a set threshold, the user and their IP are temporarily banned. This system ensures platform security
|
|
# by monitoring and penalizing rapid or suspicious activities.
|
|
|
|
BAN_VIOLATIONS=true # Whether or not to enable banning users for violations (they will still be logged)
|
|
BAN_DURATION=1000 * 60 * 60 * 2 # how long the user and associated IP are banned for
|
|
BAN_INTERVAL=20 # a user will be banned everytime their score reaches/crosses over the interval threshold
|
|
|
|
# The score for each violation
|
|
|
|
LOGIN_VIOLATION_SCORE=1
|
|
REGISTRATION_VIOLATION_SCORE=1
|
|
CONCURRENT_VIOLATION_SCORE=1
|
|
MESSAGE_VIOLATION_SCORE=1
|
|
NON_BROWSER_VIOLATION_SCORE=20
|
|
|
|
# Login and registration rate limiting.
|
|
|
|
LOGIN_MAX=7 # The max amount of logins allowed per IP per LOGIN_WINDOW
|
|
LOGIN_WINDOW=5 # in minutes, determines the window of time for LOGIN_MAX logins
|
|
REGISTER_MAX=5 # The max amount of registrations allowed per IP per REGISTER_WINDOW
|
|
REGISTER_WINDOW=60 # in minutes, determines the window of time for REGISTER_MAX registrations
|
|
|
|
# Message rate limiting (per user & IP)
|
|
|
|
LIMIT_CONCURRENT_MESSAGES=true # Whether to limit the amount of messages a user can send per request
|
|
CONCURRENT_MESSAGE_MAX=2 # The max amount of messages a user can send per request
|
|
|
|
LIMIT_MESSAGE_IP=true # Whether to limit the amount of messages an IP can send per MESSAGE_IP_WINDOW
|
|
MESSAGE_IP_MAX=40 # The max amount of messages an IP can send per MESSAGE_IP_WINDOW
|
|
MESSAGE_IP_WINDOW=1 # in minutes, determines the window of time for MESSAGE_IP_MAX messages
|
|
|
|
# Note: You can utilize both limiters, but default is to limit by IP only.
|
|
LIMIT_MESSAGE_USER=false # Whether to limit the amount of messages an IP can send per MESSAGE_USER_WINDOW
|
|
MESSAGE_USER_MAX=40 # The max amount of messages an IP can send per MESSAGE_USER_WINDOW
|
|
MESSAGE_USER_WINDOW=1 # in minutes, determines the window of time for MESSAGE_USER_MAX messages
|
|
|
|
# Change this to proxy any API request.
|
|
# It's useful if your machine has difficulty calling the original API server.
|
|
# PROXY=
|
|
|
|
# Change this to your MongoDB URI if different. I recommend appending LibreChat.
|
|
MONGO_URI=mongodb://127.0.0.1:27018/LibreChat
|
|
|
|
##########################
|
|
# OpenAI Endpoint:
|
|
##########################
|
|
|
|
# Access key from OpenAI platform.
|
|
# Leave it blank to disable this feature.
|
|
# Set to "user_provided" to allow the user to provide their API key from the UI.
|
|
OPENAI_API_KEY=user_provided
|
|
|
|
DEBUG_OPENAI=false # Set to true to enable debug mode for the OpenAI endpoint
|
|
|
|
# Identify the available models, separated by commas *without spaces*.
|
|
# The first will be default.
|
|
# Leave it blank to use internal settings.
|
|
# OPENAI_MODELS=gpt-3.5-turbo,gpt-3.5-turbo-16k,gpt-3.5-turbo-0301,text-davinci-003,gpt-4,gpt-4-0314,gpt-4-0613
|
|
|
|
# Titling is enabled by default when initiating a conversation.
|
|
# Uncomment the following variable to disable this feature.
|
|
# TITLE_CONVO=false
|
|
|
|
# (Optional) The default model used for titling by is gpt-3.5-turbo-0613
|
|
# You can change it by uncommenting the following and setting the desired model
|
|
# Must be compatible with the OpenAI Endpoint.
|
|
# OPENAI_TITLE_MODEL=gpt-3.5-turbo
|
|
|
|
# (Optional/Experimental) Enable message summarization by uncommenting the following:
|
|
# Note: this may affect response time when a summary is being generated.
|
|
# OPENAI_SUMMARIZE=true
|
|
|
|
# Not yet implemented: this will be a conversation option enabled by default to save users on tokens
|
|
# We are using the ConversationSummaryBufferMemory method to summarize messages.
|
|
# To learn more about this, see this article:
|
|
# https://www.pinecone.io/learn/series/langchain/langchain-conversational-memory/
|
|
|
|
# (Optional) The default model used for summarizing is gpt-3.5-turbo
|
|
# You can change it by uncommenting the following and setting the desired model
|
|
# Must be compatible with the OpenAI Endpoint.
|
|
# OPENAI_SUMMARY_MODEL=gpt-3.5-turbo
|
|
|
|
# Reverse proxy settings for OpenAI:
|
|
# https://github.com/waylaidwanderer/node-chatgpt-api#using-a-reverse-proxy
|
|
# OPENAI_REVERSE_PROXY=
|
|
|
|
##########################
|
|
# OpenRouter (overrides OpenAI and Plugins Endpoints):
|
|
##########################
|
|
|
|
# OpenRouter is a legitimate proxy service to a multitude of LLMs, both closed and open source, including:
|
|
# OpenAI models, Anthropic models, Meta's Llama models, pygmalionai/mythalion-13b
|
|
# and many more open source models. Newer integrations are usually discounted, too!
|
|
|
|
# Note: this overrides the OpenAI and Plugins Endpoints.
|
|
# See ./docs/install/free_ai_apis.md for more info.
|
|
|
|
# OPENROUTER_API_KEY=
|
|
|
|
##########################
|
|
# 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.
|
|
# Note "AZURE_OPENAI_API_COMPLETIONS_DEPLOYMENT_NAME" and "AZURE_OPENAI_API_EMBEDDINGS_DEPLOYMENT_NAME" are optional but might be used in the future
|
|
|
|
# AZURE_API_KEY=
|
|
# AZURE_OPENAI_API_INSTANCE_NAME=
|
|
# AZURE_OPENAI_API_DEPLOYMENT_NAME=
|
|
# AZURE_OPENAI_API_VERSION=
|
|
# AZURE_OPENAI_API_COMPLETIONS_DEPLOYMENT_NAME=
|
|
# AZURE_OPENAI_API_EMBEDDINGS_DEPLOYMENT_NAME=
|
|
|
|
# Identify the available models, separated by commas *without spaces*.
|
|
# The first will be default.
|
|
# Leave it blank to use internal settings.
|
|
AZURE_OPENAI_MODELS=gpt-3.5-turbo,gpt-4
|
|
|
|
# To use Azure with the Plugins endpoint, you need the variables above, and uncomment the following variable:
|
|
# NOTE: This may not work as expected and Azure OpenAI may not support OpenAI Functions yet
|
|
# Omit/leave it commented to use the default OpenAI API
|
|
|
|
# PLUGINS_USE_AZURE="true"
|
|
|
|
##########################
|
|
# ChatGPT Endpoint:
|
|
##########################
|
|
|
|
# ChatGPT Browser Client (free but use at your own risk)
|
|
# Access token from https://chat.openai.com/api/auth/session
|
|
# Exposes your access token to `CHATGPT_REVERSE_PROXY`
|
|
# Set to "user_provided" to allow the user to provide its token from the UI.
|
|
# Leave it blank to disable this endpoint
|
|
CHATGPT_TOKEN=user_provided
|
|
|
|
# Identify the available models, separated by commas. The first will be default.
|
|
# Leave it blank to use internal settings.
|
|
CHATGPT_MODELS=text-davinci-002-render-sha,gpt-4
|
|
# NOTE: you can add gpt-4-plugins, gpt-4-code-interpreter, and gpt-4-browsing to the list above and use the models for these features;
|
|
# however, the view/display portion of these features are not supported, but you can use the underlying models, which have higher token context
|
|
# Also: text-davinci-002-render-paid is deprecated as of May 2023
|
|
|
|
# Reverse proxy setting for OpenAI
|
|
# https://github.com/waylaidwanderer/node-chatgpt-api#using-a-reverse-proxy
|
|
# By default it will use the node-chatgpt-api recommended proxy, (it's a third party server)
|
|
# CHATGPT_REVERSE_PROXY=<YOUR REVERSE PROXY>
|
|
|
|
##########################
|
|
# BingAI Endpoint:
|
|
##########################
|
|
|
|
# Also used for Sydney and jailbreak
|
|
# To get your Access token for Bing, login to https://www.bing.com
|
|
# Use dev tools or an extension while logged into the site to copy the content of the _U cookie.
|
|
# If this fails, follow these instructions https://github.com/danny-avila/LibreChat/issues/370#issuecomment-1560382302 to provide the full cookie strings
|
|
# or check out our discord https://discord.com/channels/1086345563026489514/1143941308684177429
|
|
# Set to "user_provided" to allow the user to provide its token from the UI.
|
|
# Leave it blank to disable this endpoint.
|
|
BINGAI_TOKEN=user_provided
|
|
|
|
# BingAI Host:
|
|
# Necessary for some people in different countries, e.g. China (https://cn.bing.com)
|
|
# Leave it blank to use default server.
|
|
# BINGAI_HOST=https://cn.bing.com
|
|
|
|
#############################
|
|
# Plugins:
|
|
#############################
|
|
|
|
# Identify the available models, separated by commas *without spaces*.
|
|
# The first will be default.
|
|
# Leave it blank to use internal settings.
|
|
# PLUGIN_MODELS=gpt-3.5-turbo,gpt-3.5-turbo-16k,gpt-3.5-turbo-0301,gpt-4,gpt-4-0314,gpt-4-0613
|
|
|
|
DEBUG_PLUGINS=true # Set to false or comment out to disable debug mode for plugins
|
|
|
|
# For securely storing credentials, you need a fixed key and IV. You can set them here for prod and dev environments
|
|
# If you don't set them, the app will crash on startup.
|
|
# You need a 32-byte key (64 characters in hex) and 16-byte IV (32 characters in hex)
|
|
# Use this replit to generate some quickly: https://replit.com/@daavila/crypto#index.js
|
|
# Here are some examples (THESE ARE NOT SECURE!)
|
|
CREDS_KEY=f34be427ebb29de8d88c107a71546019685ed8b241d8f2ed00c3df97ad2566f0
|
|
CREDS_IV=e2341419ec3dd3d19b13a1a87fafcbfb
|
|
|
|
# AI-Assisted Google Search
|
|
# This bot supports searching google for answers to your questions with assistance from GPT!
|
|
# See detailed instructions here: https://github.com/danny-avila/LibreChat/blob/main/docs/features/plugins/google_search.md
|
|
GOOGLE_API_KEY=
|
|
GOOGLE_CSE_ID=
|
|
|
|
# StableDiffusion WebUI
|
|
# This bot supports StableDiffusion WebUI, using it's API to generated requested images.
|
|
# See detailed instructions here: https://github.com/danny-avila/LibreChat/blob/main/docs/features/plugins/stable_diffusion.md
|
|
# Use "http://127.0.0.1:7860" with local install and "http://host.docker.internal:7860" for docker
|
|
SD_WEBUI_URL=http://host.docker.internal:7860
|
|
|
|
# Azure Cognitive Search
|
|
# This plugin supports searching Azure Cognitive Search for answers to your questions.
|
|
# See detailed instructions here: https://github.com/danny-avila/LibreChat/blob/main/docs/features/plugins/azure_cognitive_search.md
|
|
AZURE_COGNITIVE_SEARCH_SERVICE_ENDPOINT=
|
|
AZURE_COGNITIVE_SEARCH_INDEX_NAME=
|
|
AZURE_COGNITIVE_SEARCH_API_KEY=
|
|
|
|
AZURE_COGNITIVE_SEARCH_API_VERSION=
|
|
AZURE_COGNITIVE_SEARCH_SEARCH_OPTION_QUERY_TYPE=
|
|
AZURE_COGNITIVE_SEARCH_SEARCH_OPTION_TOP=
|
|
AZURE_COGNITIVE_SEARCH_SEARCH_OPTION_SELECT=
|
|
|
|
##########################
|
|
# PaLM (Google) Endpoint:
|
|
##########################
|
|
|
|
# Follow the instruction here to setup:
|
|
# https://github.com/danny-avila/LibreChat/blob/main/docs/install/apis_and_tokens.md
|
|
|
|
PALM_KEY=user_provided
|
|
|
|
# In case you need a reverse proxy for this endpoint:
|
|
# GOOGLE_REVERSE_PROXY=
|
|
|
|
##########################
|
|
# Anthropic Endpoint:
|
|
##########################
|
|
# Access key from https://console.anthropic.com/
|
|
# Leave it blank to disable this feature.
|
|
# Set to "user_provided" to allow the user to provide their API key from the UI.
|
|
# Note that access to claude-1 may potentially become unavailable with the release of claude-2.
|
|
ANTHROPIC_API_KEY=user_provided
|
|
ANTHROPIC_MODELS=claude-1,claude-instant-1,claude-2
|
|
|
|
##########################
|
|
# Proxy: To be Used by all endpoints
|
|
##########################
|
|
|
|
PROXY=
|
|
|
|
##########################
|
|
# Search:
|
|
##########################
|
|
|
|
# ENABLING SEARCH MESSAGES/CONVOS
|
|
# Requires the installation of the free self-hosted Meilisearch or a paid Remote Plan (Remote not tested)
|
|
# The easiest setup for this is through docker-compose, which takes care of it for you.
|
|
SEARCH=true
|
|
|
|
# HIGHLY RECOMMENDED: Disable anonymized telemetry analytics for MeiliSearch for absolute privacy.
|
|
MEILI_NO_ANALYTICS=true
|
|
|
|
# REQUIRED FOR SEARCH: MeiliSearch Host, mainly for the API server to connect to the search server.
|
|
# Replace '0.0.0.0' with 'meilisearch' if serving MeiliSearch with docker-compose.
|
|
MEILI_HOST=http://0.0.0.0:7700
|
|
|
|
# REQUIRED FOR SEARCH: MeiliSearch HTTP Address, mainly for docker-compose to expose the search server.
|
|
# Replace '0.0.0.0' with 'meilisearch' if serving MeiliSearch with docker-compose.
|
|
MEILI_HTTP_ADDR=0.0.0.0:7700
|
|
|
|
# REQUIRED FOR SEARCH: In production env., a secure key is needed. You can generate your own.
|
|
# This master key must be at least 16 bytes, composed of valid UTF-8 characters.
|
|
# MeiliSearch will throw an error and refuse to launch if no master key is provided,
|
|
# or if it is under 16 bytes. MeiliSearch will suggest a secure autogenerated master key.
|
|
# Using docker, it seems recognized as production so use a secure key.
|
|
# This is a ready made secure key for docker-compose, you can replace it with your own.
|
|
MEILI_MASTER_KEY=DrhYf7zENyR6AlUCKmnz0eYASOQdl6zxH7s7MKFSfFCt
|
|
|
|
##########################
|
|
# User System:
|
|
##########################
|
|
|
|
# Allow Public Registration
|
|
ALLOW_REGISTRATION=true
|
|
|
|
# Allow Social Registration
|
|
ALLOW_SOCIAL_LOGIN=false
|
|
|
|
# Allow Social Registration (WORKS ONLY for Google, Github, Discord)
|
|
ALLOW_SOCIAL_REGISTRATION=false
|
|
|
|
# JWT Secrets
|
|
# You should use secure values. The examples given are 32-byte keys (64 characters in hex)
|
|
# Use this replit to generate some quickly: https://replit.com/@daavila/crypto#index.js
|
|
JWT_SECRET=16f8c0ef4a5d391b26034086c628469d3f9f497f08163ab9b40137092f2909ef
|
|
JWT_REFRESH_SECRET=eaa5191f2914e30b9387fd84e254e4ba6fc51b4654968a9b0803b456a54b8418
|
|
|
|
# Google:
|
|
# Add your Google Client ID and Secret here, you must register an app with Google Cloud to get these values
|
|
# https://cloud.google.com/
|
|
GOOGLE_CLIENT_ID=
|
|
GOOGLE_CLIENT_SECRET=
|
|
GOOGLE_CALLBACK_URL=/oauth/google/callback
|
|
|
|
# Facebook:
|
|
# Add your Facebook Client ID and Secret here, you must register an app with Facebook to get these values
|
|
# https://developers.facebook.com/
|
|
FACEBOOK_CLIENT_ID=
|
|
FACEBOOK_CLIENT_SECRET=
|
|
FACEBOOK_CALLBACK_URL=/oauth/facebook/callback
|
|
|
|
# OpenID:
|
|
# See OpenID provider to get the below values
|
|
# Create random string for OPENID_SESSION_SECRET
|
|
# For Azure AD
|
|
# ISSUER: https://login.microsoftonline.com/(tenant id)/v2.0/
|
|
# SCOPE: openid profile email
|
|
OPENID_CLIENT_ID=
|
|
OPENID_CLIENT_SECRET=
|
|
OPENID_ISSUER=
|
|
OPENID_SESSION_SECRET=
|
|
OPENID_SCOPE="openid profile email"
|
|
OPENID_CALLBACK_URL=/oauth/openid/callback
|
|
# If LABEL and URL are left empty, then the default OpenID label and logo are used.
|
|
OPENID_BUTTON_LABEL=
|
|
OPENID_IMAGE_URL=
|
|
|
|
# Set the expiration delay for the secure cookie with the JWT token
|
|
# Recommend session expiry to be 15 minutes
|
|
# Delay is in millisecond e.g. 7 days is 1000*60*60*24*7
|
|
SESSION_EXPIRY=1000 * 60 * 15
|
|
REFRESH_TOKEN_EXPIRY=(1000 * 60 * 60 * 24) * 7
|
|
|
|
# Github:
|
|
# Get the Client ID and Secret from your Discord Application
|
|
# Add your Discord Client ID and Client Secret here:
|
|
|
|
GITHUB_CLIENT_ID=your_client_id
|
|
GITHUB_CLIENT_SECRET=your_client_secret
|
|
GITHUB_CALLBACK_URL=/oauth/github/callback # this should be the same for everyone
|
|
|
|
# Discord:
|
|
# Get the Client ID and Secret from your Discord Application
|
|
# Add your Github Client ID and Client Secret here:
|
|
|
|
DISCORD_CLIENT_ID=your_client_id
|
|
DISCORD_CLIENT_SECRET=your_client_secret
|
|
DISCORD_CALLBACK_URL=/oauth/discord/callback # this should be the same for everyone
|
|
|
|
###########################
|
|
# Application Domains
|
|
###########################
|
|
|
|
# Note:
|
|
# Server = Backend
|
|
# Client = Public (the client is the url you visit)
|
|
# For the Google login to work in dev mode, you will need to change DOMAIN_SERVER to localhost:3090 or place it in .env.development
|
|
|
|
DOMAIN_CLIENT=http://localhost:3080
|
|
DOMAIN_SERVER=http://localhost:3080
|
|
|
|
###########################
|
|
# Email
|
|
###########################
|
|
|
|
# Email is used for password reset. Note that all 4 values must be set for email to work.
|
|
EMAIL_SERVICE= # eg. gmail
|
|
EMAIL_USERNAME= # eg. your email address if using gmail
|
|
EMAIL_PASSWORD= # eg. this is the "app password" if using gmail
|
|
EMAIL_FROM= # eg. email address for from field like noreply@librechat.ai
|