:pencil: [Config] Release v1.1

:gem: [Feature] Enable gpt-3.5 in chat_api

:recycle: [Refactor] Rename message_streamer to huggingface_streamer

:recycle: [Refactor] Configure api info with config.json

:pencil: [CI] Trigger sync actions only when new version released

:gem: [Feature] Support multiple messages for gpt-3.5 model, and refactor proxies

:recycle: [Refactor] Use tclogger, and configure envs better

:gem: [Feature] Enable stream output of chat completions

:gem: [Feature] Enable conversation with openai

:hammer: [WIP] Try to enable conversation api

:zap: [Enhance] Handle if http_proxy is None, and prettify logs

:gem: [Feature] New api for chat_requiements, and moduralize logs

:recycle: [Refactor] Prettify initializaiton of OpenaiAPI requests params

:gem: [Feature] Enable get models of chat.openai.com

:boom: [Fix] Revert chat templates with mannual version as nous-mixtral-8x7b behaves weirdly

:recycle: [Refactor] Use official chat_template to replace mannual parses for several models, and remove unused message split functions

:boom: [Fix] [Errno 13] Permission denied: '/.cache'

:recycle: [Refactor] Move AVAILABLE_MODELS(_DICTS) to constants

:recycle: [Refactor] Move STOP_SEQUENCES_MAP and TOKEN_LIMIT_MAP to constants

:recycle: [Refactor] Move MODELS_MAP to constants

:gem: [Feature] Support new model: openchat-3.5-0106

:gem: [Feature] New model enabled: gemma-7b

:hammer: [Test] Enable deployment in vercel

:zap: [Enhance] Set min and max for top_p

:gem: [Feature] Add top_p and set 0.95 as default

:gem: [Feature] Add use_cache parameter, and set default temperature to 0.5

:boom: [Fix] Missing system message for original mistral models

:zap: [Enhance] Display schema of /api/v1 for user-friendly compatibility

:gem: [Feature] ChatAPIApp: New /readme route

:pencil: [Doc] New model, and prettify formats

:zap: [Enhance] ChatAPIApp: Only include schema for non-prefix route

:gem: [Feature] New model enabled: nous-mixtral-8-7b

:zap: [Enhance] Align /models response with openai format

:pencil: [Doc] Update available models

:zap: [Enhance] add /api/v1 prefix for hf banning and ui compatability

:zap: [Enhance] Remove openchat-3.5 from available models

:boom: [Fix] inputs_tokens + max_new_tokens must <= 32768

:boom: [Fix] temperature must be strictly positive

:boom: [Fix] Error 500 when temperature is null

:boom: [Fix] Error 422 when max_tokens is null

:zap: [Enhance] Auto calculate max_tokens if not set

:zap: [Enhance] Remove leading whitespaces of first response

:boom: [Fix] Ignore invalid HF Token

:pencil: [Doc] Available models: More comments on dropped models

:pencil: [Doc] Readme: New models, api key and no-stream mode, and models to support

:gem: [Feature] MessageComposer: Support openchat-3.5, and generalize preprocessing stages

:gem: [Feature] MessageStreamer: Support stop sequence and auto removal

:zap: [Enhance] Update available models description

:zap: [Enhance] Support provide api_key with os env HF_TOKEN

:gem: [Feature] Support call hf api with api_key via HTTP Bearer