🅰️ feat: Azure OpenAI Assistants API Support (#1992)

* chore: rename dir from `assistant` to plural

* feat: `assistants` field for azure config, spread options in AppService

* refactor: rename constructAzureURL param for azure as `azureOptions`

* chore: bump openai and bun

* chore(loadDefaultModels): change naming of assistant -> assistants

* feat: load azure settings with currect baseURL for assistants' initializeClient

* refactor: add `assistants` flags to groups and model configs, add mapGroupToAzureConfig

* feat(loadConfigEndpoints): initialize assistants endpoint if azure flag `assistants` is enabled

* feat(AppService): determine assistant models on startup, throw Error if none

* refactor(useDeleteAssistantMutation): send model along with assistant id for delete mutations

* feat: support listing and deleting assistants with azure

* feat: add model query to assistant avatar upload

* feat: add azure support for retrieveRun method

* refactor: update OpenAIClient initialization

* chore: update README

* fix(ci): tests passing

* refactor(uploadOpenAIFile): improve logging and use more efficient REST API method

* refactor(useFileHandling): add model to metadata to target Azure region compatible with current model

* chore(files): add azure naming pattern for valid file id recognition

* fix(assistants): initialize openai with first available assistant model if none provided

* refactor(uploadOpenAIFile): add content type for azure, initialize formdata before azure options

* refactor(sleep): move sleep function out of Runs and into `~/server/utils`

* fix(azureOpenAI/assistants): make sure to only overwrite models with assistant models if `assistants` flag is enabled

* refactor(uploadOpenAIFile): revert to old method

* chore(uploadOpenAIFile): use enum for file purpose

* docs: azureOpenAI update guide with more info, examples

* feat: enable/disable assistant capabilities and specify retrieval models

* refactor: optional chain conditional statement in loadConfigModels.js

* docs: add assistants examples

* chore: update librechat.example.yaml

* docs(azure): update note of file upload behavior in Azure OpenAI Assistants

* chore: update docs and add descriptive message about assistant errors

* fix: prevent message submission with invalid assistant or if files loading

* style: update Landing icon & text when assistant is not selected

* chore: bump librechat-data-provider to 0.4.8

* fix(assistants/azure): assign req.body.model for proper azure init to abort runs
This commit is contained in:
Danny Avila 2024-03-14 17:21:42 -04:00 committed by GitHub
parent 1b243c6f8c
commit 5cd5c3bef8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
60 changed files with 1044 additions and 300 deletions

View file

@ -2,7 +2,7 @@
# https://docs.librechat.ai/install/configuration/custom_config.html
# Configuration version (required)
version: 1.0.4
version: 1.0.5
# Cache settings: Set to true to enable caching
cache: true
@ -59,6 +59,10 @@ endpoints:
# # 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"]
custom:
# Groq Example
- name: 'groq'