Release v0.2.0-beta
Pre-release
Pre-release
Release Note v0.2.0-beta
Release Note
Windows Portable Edition
- Adjust the model hosting method:
- Enable Gemini Pro and ChatGPT APIs by default
- Use Gemini Pro by default to launch RAG applications for WebQA and DocQA
- Deprecate env.bat and use run.bat to launch the executor instead
- Enhance executor functionality:
- Allow direct configuration of execution instructions, parameters, and other information
- Adjust init.bat to be a simple tool to help create run.bat. Users can also directly write run.bat to launch the required model
- Fix the error of a non-existent PHP download link in v0.1.0 (archived due to version update)
- Integrate RAG into the simplified launch framework of the Windows version
- Specify file path improvements:
- In the executors folder of the Windows version, files will be specified using relative paths by default
- Fix the executor error of the Custom category
- Permission adjustment:
- Only groups with Manage Tab permission can be directly assigned permission to use the model when the model is added
- Fix the issue in the Windows version where Redis uses localhost as the IP, causing DNS queries to be delayed by 2 seconds each time
Docker Edition
- Integrate RAG (DocQA / WebQA / DB QA) into the executor's Docker image and compose the system
- Provide a compose example of Gemini Pro using a global API key
- Complete the missing words in the document
Executor
- Provide a TAIDE API executor, which can be directly connected to the TAIDE API of TECO
- Port RAG executor (DocQA / WebQA / DB QA / SearchQA) to the new framework
- Let the RAG executor support automatic model search, i18n, and interrupt generation
Kernel
- Provide an API to list currently available executors
Multi-chat
- Adjust the timeout waiting time for the no-message state:
- Extend from 1 minute to 2 minutes to accommodate the waiting time for the RAG processing speed gap
- Fix the bug of AdminSeeder:
- Fix the issue of granting duplicate model usage permissions
- Add the function of sending Kuwa tokens from the website to the executor:
- To fix the past issue of unowned API tokens for RAG
- Add a method to adjust the default model image path:
- Can be configured via LLM_DEFAULT_IMG in the .env file
- Fix the bug that the API in v0.1.0 could not be used normally
Known Issues and Limitations
- Since RAG-related applications may generate longer inputs, it is easy to cause timeout errors if they are connected to CPU models on the local side. It is suggested to connect to cloud models or use GPU-based local models
v0.2.0-beta 發行說明
發行說明
Windows Portable 版
- 調整模型架設方式:
- 預設啟用 Gemini Pro 與 ChatGPT 的 API
- 預設使用 Gemini Pro 來啟動 WebQA 與 DocQA 的 RAG 應用
- 廢除 env.bat,改用 run.bat來啟動executor
- 改進 executor 功能:
- 允許直接設定執行指令、參數等資訊
- 調整 init.bat 作為單純輔助建立 run.bat 的工具,使用者也可直接撰寫run.bat來啟動所需模型
- 修正 v0.1.0版 PHP 下載連結不存在的錯誤(因版本更新而被封存)
- 整合 RAG 至 Windows 版本簡易啟動框架下
- 指定檔案路徑改善
- 在 Windows 版本的 executors 資料夾下,檔案預設會使用相對路徑指定
- 修正 Custom 類別的 executor 錯誤
- 權限調整:
- 只有管理 Tab 權限的群組可以在模型新增的時候直接被賦予該模型使用權限
- 修正 Windows 版本中 Redis 因使用 localhost 作為 IP 導致 DNS 查詢每次需延遲 2 秒的問題
Docker 版
- 整合 RAG (DocQA / WebQA / DB QA) 至 executor 的 Docker image 與 compose 系統中
- 提供 Gemini Pro 使用全域 API key 的 compose 範例
- 補完文件缺漏字句
Executor
- 提供 TAIDE API executor,可直接串接國網的 TAIDE API
- 移植 RAG executor (DocQA / WebQA / DB QA / SearchQA) 到新版框架上
- 讓 RAG executor 支援自動模型尋找、i18n與中斷生成
Kernel
- 提供列出目前可用 executor 的 API
Multi-chat
- 調整無訊息狀態的 timeout 等待時間:
- 從 1 分鐘延長至 2 分鐘,以因應 RAG 處理速度的空窗等待時間
- 修復 AdminSeeder 的 bug:
- 修正給予重複的模型使用權限的問題
- 新增網站傳送 kuwa token 到 executor 上的功能:
- 用以修正 RAG 過去無歸屬的 API token 問題
- 增加調整預設模型圖片路徑的方法:
- 可透過 .env 檔案的 LLM_DEFAULT_IMG 進行設定
- 修正 v0.1.0 的 API 無法正常使用的 Bug
已知問題及限制
- RAG 相關應用因會產生較長的輸入,若串接地端 CPU 模型容易產生超時錯誤,建議串接雲端模型,或是使用 GPU 的地端模型