* WIP model selection per workspace (migrations and openai saves properly

* revert OpenAiOption

* add support for models per workspace for anthropic, localAi, ollama, openAi, and togetherAi

* remove unneeded comments

* update logic for when LLMProvider is reset, reset Ai provider files with master

* remove frontend/api reset of workspace chat and move logic to updateENV
add postUpdate callbacks to envs

* set preferred model for chat on class instantiation

* remove extra param

* linting

* remove unused var

* refactor chat model selection on workspace

* linting

* add fallback for base path to localai models

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>

* add check to skip empty messages

* add comment explaining prisma + sqlite not supporting createMany()

* Add support for fetching single document in documents folder

* Add document object to upload + support link scraping via API

* hotfixes for documentation

* update api docs

* no lazy onboarding

* no lazy onboarding steps

* Do not lazy load onboarding to prevent lazy-load white flash

* truncate title to shorter length so x button is not hidden for longer title names in the citation modal

* absolutely position x button on citation modal

* Query mode to return no-result when no context found

* update default error for sync chat

* remove unnecessary type conversion

normalize paths for submit URLs

* improve native embedder handling of large files

* perf changes

* ignore storage tmp

* [FEAT]: Docker Tags specific to a build version #572

* fix: dockerhub repo name

* feat: add Docker build caches

* fix: docker username

Fix the DockerHub repository owner name

* issue #543 support milvus vector db

* migrate Milvus to use MilvusClient instead of ORM
normalize env setup for docs/implementation
feat: embedder model dimension added

* update comments

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>

* prevent manager in multi-user from updatingENV via HTTP

* remove unneeded args

Change pwd check to O(1) check to prevent timing attacks

Patch minor XSS opportunity where user can self-XSS themselvess. There is not real vuln here as any instance is not public facing

connect #516

* Dynamic vector count on workspace settings
Add count to be workspace specific, fallback to system count
Update layout of data in settings
Update OpenAI per-token embedding price

* linting

* add Together AI LLM support

* update readme to support together ai

* Patch togetherAI implementation

* add model sorting/option labels by organization for model selection

* linting + add data handling for TogetherAI

* change truthy statement
patch validLLMSelection method

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>

Fixed mass_assignment vuln

Co-authored-by: dastaj <78434825+dastaj@users.noreply.github.com>

* patch swagger host to be relative

* change tag on feature request template

patch swagger host to be relative

* Setup issue templates
Allow ability to include blank issue
resolves #557
todo: PR template

* update templates + add PR template

* newlines

* WIP slash commands

* add slash command image

* WIP slash commands

* slash command menu feature complete

* move icons to slash command local

* update how slash command component works

* relint with new linter

* Finalize slash command input
Change empty workspace text layout
Patch dev unmount issues on Chatworkspace/index.jsx

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>

* Update build process to support multi-platform builds
Bump @lancedb/vectordb to 0.1.19 for ARM&AMD compatibility
Patch puppeteer on ARM builds because of broken chromium
resolves #539
resolves #548

---------

Co-authored-by: shatfield4 <seanhatfield5@gmail.com>

patch lockfiles with new devdeps

Implement support for GitHub codespaces and VSCode devcontainers
---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
Co-authored-by: Sean Hatfield <seanhatfield5@gmail.com>