LibreChat/docs/install/configuration/config_changelog.md
Denis Palnitsky ab6fbe48f1
📥 feat: Import Conversations from LibreChat, ChatGPT, Chatbot UI (#2355)
* 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>
2024-05-02 02:48:26 -04:00

4.7 KiB

title description weight
🖥️ Config Changelog Changelog for the custom configuration file -10

🖥️ Config Changelog

v1.0.9

  • Added conversationsImport to 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 modelSpecs for a configurable UI experience, simplifying model selection with specific presets and tools.
  • Added filteredTools to disable specific plugins/tools without any changes to the codebase
    • Affects both gptPlugins and assistants endpoints
  • iconURL can 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 stop from OpenAI/custom endpoint default parameters
  • Added current_model option for titleModel and summaryModel endpoint settings in order to use the active conversation's model for those methods.

v1.0.6

v1.0.5

v1.0.4

v1.0.3

v1.0.2

v1.0.1

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:

  1. Endpoint Configuration Schema (endpointSchema):

    • Name Validation: Ensures that the endpoint name is not one of the default EModelEndpoint values.
    • 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.
  2. 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 endpointSchema to allow custom endpoint configurations.
    • Ensures strict object structure without additional properties.