Unexpected Application Error when using `modelSpec` in browser #4318

sreevatsank1999 · 2024-10-03T05:53:59Z

sreevatsank1999
Oct 3, 2024

What happened?

I get the following error when I try to select a modelSpec from the dropdown menu in the browser

Unexpected Application Error!
[ { "received": "None", "code": "invalid_enum_value", "options": [ "azureOpenAI", "openAI", "bingAI", "chatGPTBrowser", "google", "gptPlugins", "anthropic", "assistants", "azureAssistants", "agents", "custom", "bedrock" ], "path": [ "endpointType" ], "message": "Invalid enum value. Expected 'azureOpenAI' | 'openAI' | 'bingAI' | 'chatGPTBrowser' | 'google' | 'gptPlugins' | 'anthropic' | 'assistants' | 'azureAssistants' | 'agents' | 'custom' | 'bedrock', received 'None'" } ]
ZodError
    at get error (https://chat-wcsng.nrp-nautilus.io/assets/vendor.BujiSg_e.js:84:12611)
    at yr.parse (https://chat-wcsng.nrp-nautilus.io/assets/vendor.BujiSg_e.js:84:14848)
    at Q8 (https://chat-wcsng.nrp-nautilus.io/assets/index.js:3365:184842)
    at A7 (https://chat-wcsng.nrp-nautilus.io/assets/vendor.BujiSg_e.js:38:19557)
    at k$ (https://chat-wcsng.nrp-nautilus.io/assets/vendor.BujiSg_e.js:40:3150)
    at Qee (https://chat-wcsng.nrp-nautilus.io/assets/vendor.BujiSg_e.js:40:44947)
    at zee (https://chat-wcsng.nrp-nautilus.io/assets/vendor.BujiSg_e.js:40:39876)
    at pSe (https://chat-wcsng.nrp-nautilus.io/assets/vendor.BujiSg_e.js:40:39799)
    at v2 (https://chat-wcsng.nrp-nautilus.io/assets/vendor.BujiSg_e.js:40:39648)
    at j$ (https://chat-wcsng.nrp-nautilus.io/assets/vendor.BujiSg_e.js:40:36004)

Refreshing the screen clears the error

I am experiencing this error after upgrading to the latest main branch commit 2ca257d from a version from 2 weeks ago

Steps to Reproduce

Login
Select a modelSpec from the dropdown menu

Config files of deployment:

.env

#=====================================================================#
#                       LibreChat Configuration                       #
#=====================================================================#
# Please refer to the reference documentation for assistance          #
# with configuring your LibreChat environment.                        #
#                                                                     #
# https://www.librechat.ai/docs/configuration/dotenv                  #
#=====================================================================#

#==================================================#
#               Server Configuration               #
#==================================================#

HOST=localhost
PORT=3080

MONGO_URI=mongodb://127.0.0.1:27017/LibreChat

DOMAIN_CLIENT=https://chat-wcsng.nrp-nautilus.io
DOMAIN_SERVER=https://chat-wcsng.nrp-nautilus.io

NO_INDEX=true

#===============#
# JSON Logging  #
#===============#

# Use when process console logs in cloud deployment like GCP/AWS
CONSOLE_JSON=true

#===============#
# Debug Logging #
#===============#

DEBUG_LOGGING=false
DEBUG_CONSOLE=true

#=============#
# Permissions #
#=============#

# UID=1000
# GID=1000

#===============#
# Configuration #
#===============#
# Use an absolute path, a relative path, or a URL

# CONFIG_PATH="/alternative/path/to/librechat.yaml"

#===================================================#
#                     Endpoints                     #
#===================================================#

# ENDPOINTS=openAI,assistants,azureOpenAI,bingAI,google,gptPlugins,anthropic
ENDPOINTS=openAI,assistants,bingAI,google,gptPlugins,anthropic

# PROXY=

#===================================#
# Known Endpoints - librechat.yaml  #
#===================================#
# https://www.librechat.ai/docs/configuration/librechat_yaml/ai_endpoints

# ANYSCALE_API_KEY=
# APIPIE_API_KEY=
# COHERE_API_KEY=
# DEEPSEEK_API_KEY=
# DATABRICKS_API_KEY=
# FIREWORKS_API_KEY=
# GROQ_API_KEY=
# HUGGINGFACE_TOKEN=
# MISTRAL_API_KEY=
# OPENROUTER_KEY=
# PERPLEXITY_API_KEY=
# SHUTTLEAI_API_KEY=
# TOGETHERAI_API_KEY=
# UNIFY_API_KEY=

#============#
# Anthropic  #
#============#

# ANTHROPIC_API_KEY=
ANTHROPIC_MODELS=claude-3-5-sonnet-20240620,claude-3-opus-20240229,claude-3-haiku-20240307
# ANTHROPIC_REVERSE_PROXY=
ANTHROPIC_TITLE_MODEL=claude-3-haiku-20240307
#============#
# Azure      #
#============#

# Note: these variables are DEPRECATED
# Use the `librechat.yaml` configuration for `azureOpenAI` instead
# You may also continue to use them if you opt out of using the `librechat.yaml` configuration

# AZURE_OPENAI_DEFAULT_MODEL=gpt-3.5-turbo # Deprecated
# AZURE_OPENAI_MODELS=gpt-3.5-turbo,gpt-4 # Deprecated
# AZURE_USE_MODEL_AS_DEPLOYMENT_NAME=TRUE # Deprecated
# AZURE_API_KEY= # Deprecated
# AZURE_OPENAI_API_INSTANCE_NAME= # Deprecated
# AZURE_OPENAI_API_DEPLOYMENT_NAME= # Deprecated
# AZURE_OPENAI_API_VERSION= # Deprecated
# AZURE_OPENAI_API_COMPLETIONS_DEPLOYMENT_NAME= # Deprecated
# AZURE_OPENAI_API_EMBEDDINGS_DEPLOYMENT_NAME= # Deprecated
# PLUGINS_USE_AZURE="true" # Deprecated

#============#
# BingAI     #
#============#

BINGAI_TOKEN=user_provided
# BINGAI_HOST=https://cn.bing.com

#=================#
#   AWS Bedrock   #
#=================#

# BEDROCK_AWS_DEFAULT_REGION=us-east-1 # A default region must be provided
# BEDROCK_AWS_ACCESS_KEY_ID=someAccessKey
# BEDROCK_AWS_SECRET_ACCESS_KEY=someSecretAccessKey

# Note: This example list is not meant to be exhaustive. If omitted, all known, supported model IDs will be included for you.
# BEDROCK_AWS_MODELS=anthropic.claude-3-5-sonnet-20240620-v1:0,meta.llama3-1-8b-instruct-v1:0

# See all Bedrock model IDs here: https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns

# Notes on specific models:
# 'ai21.j2-mid-v1', # Not supported, as it doesn't support streaming
# 'ai21.j2-ultra-v1', # Not supported, as it doesn't support conversation history

#============#
# Google     #
#============#

# GOOGLE_KEY=
# GOOGLE_REVERSE_PROXY=

# Gemini API  
GOOGLE_MODELS=gemini-1.5-flash,gemini-1.5-pro
GOOGLE_TITLE_MODEL=gemini-1.5-flash
# Vertex AI
# GOOGLE_MODELS=gemini-1.5-flash-preview-0514,gemini-1.5-pro-preview-0514,gemini-1.0-pro-vision-001,gemini-1.0-pro-002,gemini-1.0-pro-001,gemini-pro-vision,gemini-1.0-pro

# GOOGLE_TITLE_MODEL=gemini-pro

# Google Safety Settings
# NOTE: These settings apply to both Vertex AI and Gemini API (AI Studio)
#
# For Vertex AI:
# To use the BLOCK_NONE setting, you need either:
# (a) Access through an allowlist via your Google account team, or
# (b) Switch to monthly invoiced billing: https://cloud.google.com/billing/docs/how-to/invoiced-billing
#
# For Gemini API (AI Studio):
# BLOCK_NONE is available by default, no special account requirements.
#
# Available options: BLOCK_NONE, BLOCK_ONLY_HIGH, BLOCK_MEDIUM_AND_ABOVE, BLOCK_LOW_AND_ABOVE
#
# GOOGLE_SAFETY_SEXUALLY_EXPLICIT=BLOCK_ONLY_HIGH
# GOOGLE_SAFETY_HATE_SPEECH=BLOCK_ONLY_HIGH
# GOOGLE_SAFETY_HARASSMENT=BLOCK_ONLY_HIGH
# GOOGLE_SAFETY_DANGEROUS_CONTENT=BLOCK_ONLY_HIGH

#============#
# OpenAI     #
#============#

# OPENAI_API_KEY=
OPENAI_MODELS=gpt-4o-mini,o1-mini,o1-preview,gpt-4o,gpt-4

DEBUG_OPENAI=false

TITLE_CONVO=true
OPENAI_TITLE_MODEL=gpt-4o-mini

OPENAI_SUMMARIZE=true
OPENAI_SUMMARY_MODEL=gpt-4o-mini

# OPENAI_FORCE_PROMPT=true

# OPENAI_REVERSE_PROXY=

# OPENAI_ORGANIZATION=

#====================#
#   Assistants API   #
#====================#

ASSISTANTS_API_KEY=user_provided
# ASSISTANTS_BASE_URL=
ASSISTANTS_MODELS=gpt-4o-mini,gpt-4o,gpt-4

#==========================#
#   Azure Assistants API   #
#==========================#

# Note: You should map your credentials with custom variables according to your Azure OpenAI Configuration
# The models for Azure Assistants are also determined by your Azure OpenAI configuration.

# More info, including how to enable use of Assistants with Azure here:
# https://www.librechat.ai/docs/configuration/librechat_yaml/ai_endpoints/azure#using-assistants-with-azure

#============#
# OpenRouter #
#============#
# !!!Warning: Use the variable above instead of this one. Using this one will override the OpenAI endpoint
# OPENROUTER_API_KEY=

#============#
# Plugins    #
#============#

PLUGIN_MODELS=gpt-4o-mini,gpt-4o,gpt-4

DEBUG_PLUGINS=false

# CREDS_KEY=
# CREDS_IV=

# Azure AI Search
#-----------------
# AZURE_AI_SEARCH_SERVICE_ENDPOINT=
# AZURE_AI_SEARCH_INDEX_NAME=
# AZURE_AI_SEARCH_API_KEY=

# AZURE_AI_SEARCH_API_VERSION=
# AZURE_AI_SEARCH_SEARCH_OPTION_QUERY_TYPE=
# AZURE_AI_SEARCH_SEARCH_OPTION_TOP=
# AZURE_AI_SEARCH_SEARCH_OPTION_SELECT=

# DALL·E
#----------------
# DALLE_API_KEY=
# DALLE3_API_KEY=
# DALLE2_API_KEY=
# DALLE3_SYSTEM_PROMPT=
# DALLE2_SYSTEM_PROMPT=
# DALLE_REVERSE_PROXY=
# DALLE3_BASEURL=
# DALLE2_BASEURL=

# DALL·E (via Azure OpenAI)
# Note: requires some of the variables above to be set
#----------------
# DALLE3_AZURE_API_VERSION=
# DALLE2_AZURE_API_VERSION=

# Google
#-----------------
# GOOGLE_SEARCH_API_KEY=
# GOOGLE_CSE_ID=

# SerpAPI
#-----------------
# SERPAPI_API_KEY=

# Stable Diffusion
#-----------------
# SD_WEBUI_URL=

# Tavily
#-----------------
# TAVILY_API_KEY=

# Traversaal
#-----------------
# TRAVERSAAL_API_KEY=

# WolframAlpha
#-----------------
# WOLFRAM_APP_ID=

# Zapier
#-----------------
# ZAPIER_NLA_API_KEY=


#==================================================#
#                      Search                      #
#==================================================#

SEARCH=true
MEILI_NO_ANALYTICS=true
MEILI_HOST=http://127.0.0.1:7700
# MEILI_MASTER_KEY=

#==================================================#
#          Speech to Text & Text to Speech         #
#==================================================#

# STT_API_KEY=
# TTS_API_KEY=

#==================================================#
#                        RAG                       #
#==================================================#
# More info: https://www.librechat.ai/docs/configuration/rag_api

RAG_API_URL=http://127.0.0.1:8000
RAG_PORT=8000 
EMBEDDINGS_PROVIDER=ollama
OLLAMA_BASE_URL=http://xyz:11434
EMBEDDINGS_MODEL=nomic-embed-text

#===================================================#
#                    User System                    #
#===================================================#

#========================#
# Moderation             #
#========================#

OPENAI_MODERATION=false
# OPENAI_MODERATION_API_KEY=
# OPENAI_MODERATION_REVERSE_PROXY=

BAN_VIOLATIONS=true
BAN_DURATION=1000 * 60 * 60 * 2
BAN_INTERVAL=20

LOGIN_VIOLATION_SCORE=1
REGISTRATION_VIOLATION_SCORE=1
CONCURRENT_VIOLATION_SCORE=1
MESSAGE_VIOLATION_SCORE=1
NON_BROWSER_VIOLATION_SCORE=20

LOGIN_MAX=7
LOGIN_WINDOW=5
REGISTER_MAX=5
REGISTER_WINDOW=60

LIMIT_CONCURRENT_MESSAGES=true
CONCURRENT_MESSAGE_MAX=4

LIMIT_MESSAGE_IP=true
MESSAGE_IP_MAX=25
MESSAGE_IP_WINDOW=1

LIMIT_MESSAGE_USER=true
MESSAGE_USER_MAX=25
MESSAGE_USER_WINDOW=1

ILLEGAL_MODEL_REQ_SCORE=5

#========================#
# Balance                #
#========================#

CHECK_BALANCE=true

#========================#
# Registration and Login #
#========================#

ALLOW_EMAIL_LOGIN=false
ALLOW_REGISTRATION=false
ALLOW_SOCIAL_LOGIN=true
ALLOW_SOCIAL_REGISTRATION=true
ALLOW_PASSWORD_RESET=false
ALLOW_ACCOUNT_DELETION=false # note: enabled by default if omitted/commented out
ALLOW_UNVERIFIED_EMAIL_LOGIN=false

SESSION_EXPIRY=(1000 * 60 * 60 * 24) * 3
REFRESH_TOKEN_EXPIRY=(1000 * 60 * 60 * 24) * 7

# JWT_SECRET=
# JWT_REFRESH_SECRET=

# Discord
# DISCORD_CLIENT_ID=
# DISCORD_CLIENT_SECRET=
# DISCORD_CALLBACK_URL=/oauth/discord/callback

# Facebook
# FACEBOOK_CLIENT_ID=
# FACEBOOK_CLIENT_SECRET=
# FACEBOOK_CALLBACK_URL=/oauth/facebook/callback

# GitHub
# GITHUB_CLIENT_ID=
# GITHUB_CLIENT_SECRET=
# GITHUB_CALLBACK_URL=/oauth/github/callback

# Google
GOOGLE_CLIENT_ID=
GOOGLE_CLIENT_SECRET=
GOOGLE_CALLBACK_URL=/oauth/google/callback

# OpenID
# OPENID_CLIENT_ID=
# OPENID_CLIENT_SECRET=
# OPENID_ISSUER=
# OPENID_SESSION_SECRET=
# OPENID_SCOPE="openid profile email"
# OPENID_CALLBACK_URL=/oauth/openid/callback
# OPENID_REQUIRED_ROLE=
# OPENID_REQUIRED_ROLE_TOKEN_KIND=
# OPENID_REQUIRED_ROLE_PARAMETER_PATH=

# OPENID_BUTTON_LABEL=
# OPENID_IMAGE_URL=

## LDAP
# LDAP_URL=
# LDAP_BIND_DN=
# LDAP_BIND_CREDENTIALS=
# LDAP_USER_SEARCH_BASE=
# LDAP_SEARCH_FILTER=mail={{username}}
# LDAP_CA_CERT_PATH=
# LDAP_TLS_REJECT_UNAUTHORIZED=
# LDAP_LOGIN_USES_USERNAME=true
# LDAP_ID=
# LDAP_USERNAME=
# LDAP_FULL_NAME=

#========================#
# Email Password Reset   #
#========================#

# EMAIL_SERVICE=
# EMAIL_HOST=
# EMAIL_PORT=25
# EMAIL_ENCRYPTION=
# EMAIL_ENCRYPTION_HOSTNAME=
# EMAIL_ALLOW_SELFSIGNED=
# EMAIL_USERNAME=
# EMAIL_PASSWORD=
# EMAIL_FROM_NAME=
# [email protected]

#========================#
# Firebase CDN           #
#========================#

# FIREBASE_API_KEY=
# FIREBASE_AUTH_DOMAIN=
# FIREBASE_PROJECT_ID=
# FIREBASE_STORAGE_BUCKET=
# FIREBASE_MESSAGING_SENDER_ID=
# FIREBASE_APP_ID=

#========================#
# Shared Links           #
#========================#

ALLOW_SHARED_LINKS=true
ALLOW_SHARED_LINKS_PUBLIC=true

#==============================#
# Static File Cache Control    #
#==============================#

# Leave commented out to use defaults: 1 day (86400 seconds) for s-maxage and 2 days (172800 seconds) for max-age
# NODE_ENV must be set to production for these to take effect
# STATIC_CACHE_MAX_AGE=172800
# STATIC_CACHE_S_MAX_AGE=86400

# If you have another service in front of your LibreChat doing compression, disable express based compression here
# DISABLE_COMPRESSION=true

#===================================================#
#                        UI                         #
#===================================================#

APP_TITLE="ChatStudio"
CUSTOM_FOOTER="ChatStudio: A One-Stop Solution for All Your LLM Needs | WCSNG"
HELP_AND_FAQ_URL=https://librechat.ai

SHOW_BIRTHDAY_ICON=true

# Google tag manager id
#ANALYTICS_GTM_ID=user provided google tag manager id

#==================================================#
#                      Others                      #
#==================================================#
#   You should leave the following commented out   #

# NODE_ENV=

# REDIS_URI=
# USE_REDIS=

# E2E_USER_EMAIL=
# E2E_USER_PASSWORD=

librechat.yaml

# For more information, see the Configuration Guide:
# https://www.librechat.ai/docs/configuration/librechat_yaml

# Configuration version (required)
version: 1.1.5

# Cache settings: Set to true to enable caching
cache: true

# Custom interface configuration
interface:
  # Privacy policy settings
  privacyPolicy:
    externalUrl: 'https://librechat.ai/privacy-policy'
    openNewTab: true

  # Terms of service
  termsOfService:
    externalUrl: 'https://librechat.ai/tos'
    openNewTab: true

  endpointsMenu: true
  modelSelect: true
  parameters: true
  sidePanel: true
  presets: true
  prompts: true
  bookmarks: true
  multiConvo: true

# Example Registration Object Structure (optional)
registration:
  socialLogins: ['google']
  allowedDomains:
  - "ucsd.edu"

rateLimits:
  fileUploads:
    ipMax: 100
    ipWindowInMinutes: 60  # Rate limit window for file uploads per IP
    userMax: 50
    userWindowInMinutes: 60  # Rate limit window for file uploads per user
  conversationsImport:
    ipMax: 100
    ipWindowInMinutes: 60  # Rate limit window for conversation imports per IP
    userMax: 50
    userWindowInMinutes: 60  # Rate limit window for conversation imports per user

# Plugins enabled
includedTools: ["google", "wolfram", "web-browser", "dalle", "stable-diffusion", "scholarai", "askyourpdf", "image_prompt_enhancer"]

# Model Specifications
modelSpecs:
  enforce: false
  prioritize: false
  list:
    - name: defaultgpt
      label: Standard
      description: ""
      default: false
      showIconInMenu: true
      showIconInHeader: false
      preset:
        endpoint: None 
        maxContextTokens: 4096
        resendFiles: false
        imageDetail: "low"
    - name: hushgpt
      label: hushGPT
      description: "A no non-sense model, it is direct and concise"
      iconURL: "https://chat-wcsng.nrp-nautilus.io/assets/hushgpt.svg"
      default: true
      showIconInMenu: true
      showIconInHeader: false
      preset:
        endpoint: None 
        promptPrefix: "Be concise and direct in your response"
        maxContextTokens: 4096
        resendFiles: false
        imageDetail: "low"

# Definition of custom endpoints
endpoints:
  assistants:
  #   disableBuilder: false # Disable Assistants Builder Interface by setting to `true`
    pollIntervalMs: 3000  # Polling interval for checking assistant updates
    timeoutMs: 180000  # Timeout for assistant operations
  #   # Should only be one or the other, either `supportedIds` or `excludedIds`
  #   supportedIds: ["asst_supportedAssistantId1", "asst_supportedAssistantId2"]
  #   # excludedIds: ["asst_excludedAssistantId"]
  #   # (optional) Models that support retrieval, will default to latest known OpenAI models that support the feature
    retrievalModels: ["gpt-4-turbo-preview"]
  #   # (optional) Assistant Capabilities available to all users. Omit the ones you wish to exclude. Defaults to list below.
    capabilities: ["code_interpreter", "retrieval", "actions", "tools", "image_vision"]
  custom:
    - name: "Perplexity"
      apiKey: "${PERPLEXITY_API_KEY}"
      baseURL: "https://api.perplexity.ai/"
      models:
        default: [
          "mistral-7b-instruct",
          "sonar-small-chat",
          "sonar-small-online",
          "sonar-medium-chat",
          "sonar-medium-online"
          ]
        fetch: false # fetching list of models is not supported
      titleConvo: true
      titleModel: "sonar-medium-chat"
      summarize: true
      summaryModel: "sonar-medium-chat"
      forcePrompt: false
      dropParams: ["stop", "frequency_penalty"]
      modelDisplayLabel: "Perplexity"

    - name: "Self Hosted"
      apiKey: "ollama"
      # use 'host.docker.internal' instead of localhost if running LibreChat in a docker container
      baseURL: "http://xyz:11434/v1/chat/completions" 
      models:
        default: [
          "llama3.1:70b",
          "llava:34b",
          "codestral:22b",
          "deepseek-coder:33b",
          "codellama:70b"
          ]
        # fetching list of models is supported but the `name` field must start
        # with `ollama` (case-insensitive), as it does in this example.
        fetch: false
      titleConvo: true
      titleModel: "current_model"
      summarize: true
      summaryModel: "current_model"
      forcePrompt: false
      modelDisplayLabel: "Ollama"

fileConfig:
  endpoints:
    assistants:
      fileLimit: 250
      fileSizeLimit: 15  # Maximum size for an individual file in MB
      totalSizeLimit: 500  # Maximum total size for all files in a single request in MB
      supportedMimeTypes:
        - "image/.*"
        - "application/pdf"
        - "text/.*"
        - "application/msword"
        - "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
    openAI:
      disabled: false  # Disables file uploading to the OpenAI endpoint
    default:
      totalSizeLimit: 200
    # YourCustomEndpointName:
    #   fileLimit: 2
    #   fileSizeLimit: 5
  serverFileSizeLimit: 25000  # Global server file size limit in MB
  avatarSizeLimit: 2  # Limit for user avatar image size in MB
# See the Custom Configuration Guide for more information on Assistants Config:
# https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/assistants_endpoint

What browsers are you seeing the problem on?

Firefox, Microsoft Edge, Mobile (Android)

Relevant log output

Console logs from Edge browser

[Violation] 'message' handler took 156ms
index.js:3004  Illegal target endpoint None [object Object]
V1 @ index.js:3004
js @ index.js:3004
(anonymous) @ index.js:3021
(anonymous) @ vendor.BujiSg_e.js:47
(anonymous) @ vendor.BujiSg_e.js:47
z7 @ vendor.BujiSg_e.js:40
tEe @ vendor.BujiSg_e.js:47
one @ vendor.BujiSg_e.js:47
(anonymous) @ vendor.BujiSg_e.js:47
(anonymous) @ index.js:3021
(anonymous) @ index.js:3365
bE @ vendor.BujiSg_e.js:40
zm @ vendor.BujiSg_e.js:40
vSe @ vendor.BujiSg_e.js:40
_d @ vendor.BujiSg_e.js:40
iB @ vendor.BujiSg_e.js:40
Kf @ vendor.BujiSg_e.js:38
(anonymous) @ vendor.BujiSg_e.js:40
setTimeout
(anonymous) @ vendor.BujiSg_e.js:76
vre @ vendor.BujiSg_e.js:76
mz @ vendor.BujiSg_e.js:76
s @ vendor.BujiSg_e.js:76
i @ vendor.BujiSg_e.js:76
dispatch @ vendor.BujiSg_e.js:76
setData @ vendor.BujiSg_e.js:76
onSuccess @ vendor.BujiSg_e.js:76
v @ vendor.BujiSg_e.js:76
Promise.then
S @ vendor.BujiSg_e.js:76
yre @ vendor.BujiSg_e.js:76
fetch @ vendor.BujiSg_e.js:76
executeFetch @ vendor.BujiSg_e.js:76
setOptions @ vendor.BujiSg_e.js:76
(anonymous) @ vendor.BujiSg_e.js:84
bE @ vendor.BujiSg_e.js:40
zm @ vendor.BujiSg_e.js:40
vSe @ vendor.BujiSg_e.js:40
_d @ vendor.BujiSg_e.js:40
iB @ vendor.BujiSg_e.js:40
Kf @ vendor.BujiSg_e.js:38
(anonymous) @ vendor.BujiSg_e.js:40
XMLHttpRequest.send
xhrSendProcessor @ main.js?attr=UKfjq9D3qWBATyAO28WIEuBuxVMiHw570UfSZ59O3y0uaBhJy1kmYRJ_9lpyWg7O5yEVjl7H8GxgxyBan6xePw:2773
window.XMLHttpRequest.send @ main.js?attr=UKfjq9D3qWBATyAO28WIEuBuxVMiHw570UfSZ59O3y0uaBhJy1kmYRJ_9lpyWg7O5yEVjl7H8GxgxyBan6xePw:2786
(anonymous) @ vendor.BujiSg_e.js:86
xhr @ vendor.BujiSg_e.js:86
Iz @ vendor.BujiSg_e.js:88
_request @ vendor.BujiSg_e.js:89
request @ vendor.BujiSg_e.js:88
(anonymous) @ vendor.BujiSg_e.js:89
(anonymous) @ vendor.BujiSg_e.js:84
(anonymous) @ index.js:3008
(anonymous) @ index.js:3008
(anonymous) @ index.js:3008
(anonymous) @ index.js:3008
fn @ index.js:3008
jh @ index.js:3008
Nh @ index.js:3008
Mw.ie.onMutate @ index.js:3008
fn @ vendor.BujiSg_e.js:76
S @ vendor.BujiSg_e.js:76
yre @ vendor.BujiSg_e.js:76
t @ vendor.BujiSg_e.js:76
execute @ vendor.BujiSg_e.js:76
await in execute
mutate @ vendor.BujiSg_e.js:76
(anonymous) @ vendor.BujiSg_e.js:84
(anonymous) @ index.js:3021
(anonymous) @ index.js:3021
bE @ vendor.BujiSg_e.js:40
zm @ vendor.BujiSg_e.js:40
iB @ vendor.BujiSg_e.js:40
Kf @ vendor.BujiSg_e.js:38
vSe @ vendor.BujiSg_e.js:40
_d @ vendor.BujiSg_e.js:40
jee @ vendor.BujiSg_e.js:40
N @ vendor.BujiSg_e.js:25
u @ vendor.BujiSg_e.js:25
6[Violation] 'setTimeout' handler took <N>ms
[Violation] Forced reflow while executing JavaScript took 79ms
vendor.BujiSg_e.js:40 [Violation] 'requestAnimationFrame' handler took 81ms
vendor.BujiSg_e.js:25 [Violation] 'message' handler took 157ms
index.js:3004  Illegal target endpoint None [object Object]
V1 @ index.js:3004
js @ index.js:3004
(anonymous) @ index.js:3021
(anonymous) @ vendor.BujiSg_e.js:47
(anonymous) @ vendor.BujiSg_e.js:47
z7 @ vendor.BujiSg_e.js:40
tEe @ vendor.BujiSg_e.js:47
one @ vendor.BujiSg_e.js:47
(anonymous) @ vendor.BujiSg_e.js:47
(anonymous) @ index.js:3021
r @ index.js:3365
onClick @ index.js:3365
g @ index.js:3365
Dwe @ vendor.BujiSg_e.js:37
Lwe @ vendor.BujiSg_e.js:37
jwe @ vendor.BujiSg_e.js:37
CF @ vendor.BujiSg_e.js:37
VJ @ vendor.BujiSg_e.js:37
(anonymous) @ vendor.BujiSg_e.js:37
z7 @ vendor.BujiSg_e.js:40
hJ @ vendor.BujiSg_e.js:37
yC @ vendor.BujiSg_e.js:37
m7 @ vendor.BujiSg_e.js:37
eOe @ vendor.BujiSg_e.js:37
vendor.BujiSg_e.js:40  ZodError: [
  {
    "received": "None",
    "code": "invalid_enum_value",
    "options": [
      "azureOpenAI",
      "openAI",
      "bingAI",
      "chatGPTBrowser",
      "google",
      "gptPlugins",
      "anthropic",
      "assistants",
      "azureAssistants",
      "agents",
      "custom",
      "bedrock"
    ],
    "path": [
      "endpointType"
    ],
    "message": "Invalid enum value. Expected 'azureOpenAI' | 'openAI' | 'bingAI' | 'chatGPTBrowser' | 'google' | 'gptPlugins' | 'anthropic' | 'assistants' | 'azureAssistants' | 'agents' | 'custom' | 'bedrock', received 'None'"
  }
]
    at get error (vendor.BujiSg_e.js:84:12611)
    at yr.parse (vendor.BujiSg_e.js:84:14848)
    at Q8 (index.js:3365:184842)
    at A7 (vendor.BujiSg_e.js:38:19557)
    at k$ (vendor.BujiSg_e.js:40:3150)
    at Qee (vendor.BujiSg_e.js:40:44947)
    at zee (vendor.BujiSg_e.js:40:39876)
    at pSe (vendor.BujiSg_e.js:40:39799)
    at v2 (vendor.BujiSg_e.js:40:39648)
    at j$ (vendor.BujiSg_e.js:40:36004)
M$ @ vendor.BujiSg_e.js:40
See.o.componentDidCatch.n.callback @ vendor.BujiSg_e.js:40
jF @ vendor.BujiSg_e.js:38
tB @ vendor.BujiSg_e.js:40
Lee @ vendor.BujiSg_e.js:40
fSe @ vendor.BujiSg_e.js:40
vSe @ vendor.BujiSg_e.js:40
_d @ vendor.BujiSg_e.js:40
iB @ vendor.BujiSg_e.js:40
Kf @ vendor.BujiSg_e.js:38
(anonymous) @ vendor.BujiSg_e.js:40
vendor.BujiSg_e.js:66  React Router caught the following error during render ZodError: [
  {
    "received": "None",
    "code": "invalid_enum_value",
    "options": [
      "azureOpenAI",
      "openAI",
      "bingAI",
      "chatGPTBrowser",
      "google",
      "gptPlugins",
      "anthropic",
      "assistants",
      "azureAssistants",
      "agents",
      "custom",
      "bedrock"
    ],
    "path": [
      "endpointType"
    ],
    "message": "Invalid enum value. Expected 'azureOpenAI' | 'openAI' | 'bingAI' | 'chatGPTBrowser' | 'google' | 'gptPlugins' | 'anthropic' | 'assistants' | 'azureAssistants' | 'agents' | 'custom' | 'bedrock', received 'None'"
  }
]
    at get error (vendor.BujiSg_e.js:84:12611)
    at yr.parse (vendor.BujiSg_e.js:84:14848)
    at Q8 (index.js:3365:184842)
    at A7 (vendor.BujiSg_e.js:38:19557)
    at k$ (vendor.BujiSg_e.js:40:3150)
    at Qee (vendor.BujiSg_e.js:40:44947)
    at zee (vendor.BujiSg_e.js:40:39876)
    at pSe (vendor.BujiSg_e.js:40:39799)
    at v2 (vendor.BujiSg_e.js:40:39648)
    at j$ (vendor.BujiSg_e.js:40:36004) {componentStack: '\n    at Q8 (https://chat-wcsng.nrp-nautilus.io/ass…wcsng.nrp-nautilus.io/assets/index.js:3070:21013)'}
componentDidCatch @ vendor.BujiSg_e.js:66
See.o.componentDidCatch.n.callback @ vendor.BujiSg_e.js:40
jF @ vendor.BujiSg_e.js:38
tB @ vendor.BujiSg_e.js:40
Lee @ vendor.BujiSg_e.js:40
fSe @ vendor.BujiSg_e.js:40
vSe @ vendor.BujiSg_e.js:40
_d @ vendor.BujiSg_e.js:40
iB @ vendor.BujiSg_e.js:40
Kf @ vendor.BujiSg_e.js:38
(anonymous) @ vendor.BujiSg_e.js:40
vendor.BujiSg_e.js:40 [Violation] 'click' handler took 1171ms
bootstrap-autofill-overlay-menu.js:887 [Violation] 'requestIdleCallback' handler took 59ms

Screenshots

Code of Conduct

I agree to follow this project's Code of Conduct

danny-avila · 2024-10-03T11:10:56Z

danny-avila
Oct 3, 2024
Maintainer

Can you share the model spec you are using?

1 reply

sreevatsank1999 Oct 3, 2024
Author

modelSpec is in the librechat.yml config in the OP.

Here is for convenience:

modelSpec

# Model Specifications
modelSpecs:
  enforce: false
  prioritize: false
  list:
    - name: defaultgpt
      label: Standard
      description: ""
      default: false
      showIconInMenu: true
      showIconInHeader: false
      preset:
        endpoint: None 
        maxContextTokens: 4096
        resendFiles: false
        imageDetail: "low"
    - name: hushgpt
      label: hushGPT
      description: "A no non-sense model, it is direct and concise"
      iconURL: "https://chat-wcsng.nrp-nautilus.io/assets/hushgpt.svg"
      default: true
      showIconInMenu: true
      showIconInHeader: false
      preset:
        endpoint: None 
        promptPrefix: "Be concise and direct in your response"
        maxContextTokens: 4096
        resendFiles: false
        imageDetail: "low"

wipash · 2024-10-03T22:43:42Z

wipash
Oct 3, 2024

I have a similar issue using a custom perplexity endpoint and modelSpec:

Error

Unexpected Application Error!
[ { "received": "perplexity", "code": "invalid_enum_value", "options": [ "azureOpenAI", "openAI", "bingAI", "chatGPTBrowser", "google", "gptPlugins", "anthropic", "assistants", "azureAssistants", "agents", "custom", "bedrock" ], "path": [ "endpointType" ], "message": "Invalid enum value. Expected 'azureOpenAI' | 'openAI' | 'bingAI' | 'chatGPTBrowser' | 'google' | 'gptPlugins' | 'anthropic' | 'assistants' | 'azureAssistants' | 'agents' | 'custom' | 'bedrock', received 'perplexity'" } ]
ZodError
    at get error (https://chat.holmesgroup.ai/assets/vendor.BujiSg_e.js:84:12611)
    at yr.parse (https://chat.holmesgroup.ai/assets/vendor.BujiSg_e.js:84:14848)
    at Q8 (https://chat.holmesgroup.ai/assets/index.DOfEXLPm.js:3365:184842)
    at A7 (https://chat.holmesgroup.ai/assets/vendor.BujiSg_e.js:38:19557)
    at k$ (https://chat.holmesgroup.ai/assets/vendor.BujiSg_e.js:40:3150)
    at Qee (https://chat.holmesgroup.ai/assets/vendor.BujiSg_e.js:40:44947)
    at zee (https://chat.holmesgroup.ai/assets/vendor.BujiSg_e.js:40:39876)
    at pSe (https://chat.holmesgroup.ai/assets/vendor.BujiSg_e.js:40:39799)
    at v2 (https://chat.holmesgroup.ai/assets/vendor.BujiSg_e.js:40:39648)
    at j$ (https://chat.holmesgroup.ai/assets/vendor.BujiSg_e.js:40:36004)

Custom Endpoint

endpoints:
  custom:
    - name: Perplexity
      apiKey: "$${PERPLEXITY_API_KEY}"
      baseURL: "https://api.perplexity.ai/"
      models:
        default:
          [
            "llama-3.1-sonar-small-128k-online",
            "llama-3.1-sonar-large-128k-online",
            "llama-3.1-sonar-huge-128k-online",
            "llama-3.1-sonar-small-128k-chat",
            "llama-3.1-sonar-large-128k-chat",
            "llama-3.1-8b-instruct",
            "llama-3.1-70b-instruct",
          ]
        fetch: false # fetching list of models is not supported
      titleConvo: true
      titleModel: "llama-3.1-sonar-small-128k-chat"
      summarize: false
      summaryModel: "llama-3.1-sonar-small-128k-chat"
      forcePrompt: false
      dropParams: ["stop", "frequency_penalty"]
      modelDisplayLabel: "Perplexity"

modelSpecs

modelSpecs:
  enforce: false
  prioritize: false
  list:
    - name: "perplexity"
      label: "Perplexity"
      description: "Perplexity is an AI-driven search engine."
      showIconInMenu: true
      showIconInHeader: true
      default: false
      preset:
        endpoint: "perplexity"
        model: "llama-3.1-sonar-huge-128k-online"
        maxContextTokens: 127000 # Maximum context tokens
        max_tokens: 4096 # Maximum output tokens
        temperature: 0.7
        modelLabel: "Perplexity"
        greeting: "Hey, what would you like to search the internet for? Please note that you'll get errors using this model if you have turned on the Artifacts feature."

I have this env var set: ENDPOINTS="openAI,google,anthropic,custom"

3 replies

wipash Oct 3, 2024

Actually as soon as I posted this I realised the error. There's a capitalisation mismatch between my modelSpec preset endpoint (perplexity) and the custom endpoint name (Perplexity). Fixing that resolved this error.

@sreevatsank1999 you can probably fix your error by setting the endpoint in your modelSpecs to match one of your custom endpoint names (or whichever endpoint it's supposed to be). The docs say that it's nullable, but maybe that broke recently?

sreevatsank1999 Oct 3, 2024
Author

Yeah! right I think that might be it. However I need the "Null" functionality.

I want to be able to choose any endpoint with specific parameters and prompt.

sreevatsank1999 Oct 10, 2024
Author

@danny-avila Is the endpoint parameter still nullable? If yes, then this should be a bug

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

Unexpected Application Error when using `modelSpec` in browser #4318

Uh oh!

{{title}}

Uh oh!

Uh oh!

{{editor}}'s edit

{{editor}}'s edit

Uh oh!

Replies: 2 comments 4 replies

Uh oh!

{{title}}

Uh oh!

Uh oh!

{{title}}

Uh oh!

Uh oh!

{{title}}

Uh oh!

Uh oh!

{{title}}

Uh oh!

Uh oh!

{{title}}

Uh oh!

Uh oh!

{{title}}

Uh oh!

Select a reply

Uh oh!

Uh oh!

Unexpected Application Error when using modelSpec in browser #4318

Uh oh!

Uh oh!

sreevatsank1999 Oct 3, 2024

What happened?

Steps to Reproduce

What browsers are you seeing the problem on?

Relevant log output

Screenshots

Code of Conduct

Replies: 2 comments · 4 replies

Uh oh!

danny-avila Oct 3, 2024 Maintainer

Uh oh!

sreevatsank1999 Oct 3, 2024 Author

Uh oh!

wipash Oct 3, 2024

Uh oh!

wipash Oct 3, 2024

Uh oh!

sreevatsank1999 Oct 3, 2024 Author

Uh oh!

sreevatsank1999 Oct 10, 2024 Author

Unexpected Application Error when using `modelSpec` in browser #4318

sreevatsank1999
Oct 3, 2024

Replies: 2 comments 4 replies

danny-avila
Oct 3, 2024
Maintainer

sreevatsank1999 Oct 3, 2024
Author

wipash
Oct 3, 2024

sreevatsank1999 Oct 3, 2024
Author

sreevatsank1999 Oct 10, 2024
Author