mirror of
https://github.com/danny-avila/LibreChat.git
synced 2025-12-17 08:50:15 +01:00
* Basic implementation of ChatGPT conversation import * remove debug code * Handle citations * Fix updatedAt in import * update default model * Use job scheduler to handle import requests * import job status endpoint * Add wrapper around Agenda * Rate limits for import endpoint * rename import api path * Batch save import to mongo * Improve naming * Add documenting comments * Test for importers * Change button for importing conversations * Frontend changes * Import job status endpoint * Import endpoint response * Add translations to new phrases * Fix conversations refreshing * cleanup unused functions * set timeout for import job status polling * Add documentation * get extra spaces back * Improve error message * Fix translation files after merge * fix translation files 2 * Add zh translation for import functionality * Sync mailisearch index after import * chore: add dummy uri for jest tests, as MONGO_URI should only be real for E2E tests * docs: fix links * docs: fix conversationsImport section * fix: user role issue for librechat imports * refactor: import conversations from json - organize imports - add additional jsdocs - use multer with diskStorage to avoid loading file into memory outside of job - use filepath instead of loading data string for imports - replace console logs and some logger.info() with logger.debug - only use multer for import route * fix: undefined metadata edge case and replace ChatGtp -> ChatGpt * Refactor importChatGptConvo function to handle undefined metadata edge case and replace ChatGtp with ChatGpt * fix: chatgpt importer * feat: maintain tree relationship for librechat messages * chore: use enum * refactor: saveMessage to use single object arg, replace console logs, add userId to log message * chore: additional comment * chore: multer edge case * feat: first pass, maintain tree relationship * chore: organize * chore: remove log * ci: add heirarchy test for chatgpt * ci: test maintaining of heirarchy for librechat * wip: allow non-text content type messages * refactor: import content part object json string * refactor: more content types to format * chore: consolidate messageText formatting * docs: update on changes, bump data-provider/config versions, update readme * refactor(indexSync): singleton pattern for MeiliSearchClient * refactor: debug log after batch is done * chore: add back indexSync error handling --------- Co-authored-by: jakubmieszczak <jakub.mieszczak@zendesk.com> Co-authored-by: Danny Avila <danny@librechat.ai>
4.7 KiB
4.7 KiB
| title | description | weight |
|---|---|---|
| 🖥️ Config Changelog | Changelog for the custom configuration file | -10 |
🖥️ 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.
- Name Validation: Ensures that the endpoint name is not one of the default
-
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.