support for gemini-1.0-pro model and fixes to prompt window limit

implement bing search engine for agents

* implement custom icon on login screen for single & multi user + custom app name feature

* hide field when not relevant

* set customApp name

* show original anythingllm login logo unless custom logo is set

* nit-picks

* remove console log

---------

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

* Patch handling of end chunk stream events for OpenAI endpoints

* update LiteLLM to use generic handler

* update for empty choices

* Improve RAG responses via source backfilling

* Hide irrelevant citations from UI

* add support for gemini-1.5-flash-latest

* update comment in gemini LLM provider

* implement clear all chats button + export button styles updates

* Hide clear button if no chats are visible
update clear function

---------

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

resolves #1491

* Update CHROMA_SETUP.md

* Update ASTRA_SETUP.md

* Allow setting of safety thresholds for Gemini

* linting

* add support for voyageai embedder

* remove unneeded import

* linting

* Add ENV examples
Update how chunks are processed for Voyage
use correct langchain import
Add data handling

---------

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

resolves #1439

* Patch WSS upgrade for manual HTTPS certs

* update comment

* refactor

* litellm LLM provider support

* fix lint error

* change import orders
fix issue with model retrieval

---------

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

* Support SQL Agent skill

* add MSSQL agent connector

* Add frontend to agent skills
remove FAKE_DB mock
reset skills to pickup child-skill dynamically

* add prompt examples for tools on untooled

* add better logging on SQL agents

* Wipe toolruns on each chat relay so tools can be used within the same session

* update comments

* WIP website depth scraping, (sort of works)

* website depth data connector stable + add maxLinks option

* linting + loading small ui tweak

* refactor website depth data connector for stability, speed, & readability

* patch: remove console log
Guard clause on URL validitiy check
reasonable overrides

---------

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

* Add Speech-to-text and Text-to-speech providers

* add files and update comment

* update comments

* patch: bad playerRef check

* add api key support for oobabooga web ui

* dont expose API Key for TextWebGenUi

---------

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

Make LanceDB the vector database default provider in backend to prevent issues where somehow this key is not set by the user resulting in a Pinecone error even though they never said they wanted Pinecone to be their vector db

validate messages schema for gemini provider

* prevent accidental lockout from restrict chars in single pass mode

* update error message