๐ฅ๏ธ Config Changelog
v1.0.9
-
Added
conversationsImportto rateLimits along with the new feature for importing conversations from LibreChat, ChatGPT, and Chatbot UI.
v1.0.8
-
Added additional fields to
interface config
to toggle access to specific features:
-
endpointsMenu,modelSelect,parameters,sidePanel,presets
-
-
Now ensures the following fields always have defaults set:
-
cache,imageOutputType,fileStrategy,registration
-
-
Added
modelSpecsfor a configurable UI experience, simplifying model selection with specific presets and tools. -
Added
filteredToolsto disable specific plugins/tools without any changes to the codebase-
Affects both
gptPluginsandassistantsendpoints
-
Affects both
-
iconURLcan now be to set to one of the main endpoints to use existing project icons- "openAI" | "azureOpenAI" | "google" | "anthropic" | "assistants" | "gptPlugins"
- Invalid YAML format is now logged for easier debugging
v1.0.7
-
Removed
stopfrom OpenAI/custom endpoint default parameters -
Added
current_modeloption fortitleModelandsummaryModelendpoint settings in order to use the active conversation's model for those methods.
v1.0.6
-
Added
imageOutputTypefield to specify the output type for image generation. -
Added
secureImageLinksto optionally lock down access to generated images.
v1.0.5
- Added Azure OpenAI Assistants configuration settings
- Added initial interface settings (privacy policy & terms of service)
-
Added the following fields to the
Azure Group Config
:
-
serverless,addParams,dropParams,forcePrompt
-
v1.0.4
- Added initial Azure OpenAI configuration settings
v1.0.3
- Added OpenAI Assistants configuration settings
- Added the following fields to custom endpoint settings:
- Added Rate Limit Configuration settings
- Added File Configuration settings
v1.0.2
-
Added
userIdQueryto custom endpoint models settings - Added Registration Configuration settings
-
Added
headersto custom endpoint settings
v1.0.1
-
Added
fileStrategyto custom config
v1.0.0
This initial release introduces a robust configuration schema using Zod for validation, designed to manage API endpoints and associated settings in a structured and type-safe manner.
Features:
-
Endpoint Configuration Schema (
endpointSchema) : -
Name Validation
: Ensures that the endpoint name is not one of the default
EModelEndpointvalues. - API Key : Requires a string value for API key identification.
- Base URL : Requires a string value for the base URL of the endpoint.
-
Models Configuration
:
- Default Models : Requires an array of strings with at least one model specified.
- Fetch Option : Optional boolean to enable model fetching.
-
Additional Optional Settings :
- Title Convo : Optional boolean to toggle conversation titles.
- Title Method : Optional choice between 'completion' and 'functions' methods.
- Title Model : Optional string for model specification in titles.
- Summarize : Optional boolean for enabling summary features.
- Summary Model : Optional string specifying the model used for summaries.
- Force Prompt : Optional boolean to force prompt inclusion.
- Model Display Label : Optional string for labeling the model in UI displays.
-
Main Configuration Schema (
configSchema) : - Version : String to specify the config schema version.
- Cache : Boolean to toggle caching mechanisms.
-
Endpoints
:
-
Custom Endpoints
: Array of partially applied
endpointSchemato allow custom endpoint configurations.
-
Custom Endpoints
: Array of partially applied
- Ensures strict object structure without additional properties.